Papers
About this collection: This is a curated repository of recent research papers at the intersection of AI and computer systems design. The collection focuses specifically on AI for Hardware — papers that demonstrate how artificial intelligence techniques are being applied to optimize, design, and verify hardware systems, from analog circuits to chip architecture to system-level optimization.
Why we maintain this: Finding relevant Architecture 2.0 papers scattered across conferences like DAC, ICCAD, ASPLOS, ISCA, and arXiv can be time-consuming. This centralized, searchable collection makes it easy for students and researchers to quickly discover papers relevant to AI-driven hardware design, whether you're looking for the latest in LLM-assisted verification, neural architecture search for accelerators, or ML-driven chip placement algorithms.
The collection is updated periodically throughout the semester as new relevant papers emerge. Use the category filters and search function to quickly find papers in your area of interest.
Total papers: 1025
Barbarians at the Gate: How AI is Upending Systems Research
Paper ↗
Abstract
Artificial Intelligence (AI) is starting to transform the research process as we know it by automating the discovery of new solutions. Given a task, the typical AI-driven approach is (i) to generate a set of diverse solutions, and then (ii) to verify these solutions and select one that solves the problem. Crucially, this approach assumes the existence of a reliable verifier, i.e., one that can accurately determine whether a solution solves the given problem. We argue that systems research, long focused on designing and evaluating new performance-oriented algorithms, is particularly well-suited for AI-driven solution discovery. This is because system performance problems naturally admit reliable verifiers: solutions are typically implemented in real systems or simulators, and verification reduces to running these software artifacts against predefined workloads and measuring performance. We term this approach as AI-Driven Research for Systems (ADRS), which iteratively generates, evaluates, and refines solutions. Using penEvolve, an existing open-source ADRS instance, we present case studies across diverse domains, including load balancing for multi-region cloud scheduling, Mixture-of-Experts inference, LLM-based SQL queries, and transaction scheduling. In multiple instances, ADRS discovers algorithms that outperform state-of-the-art human designs (e.g., achieving up to 5.0x runtime improvements or 50% cost reductions). We distill best practices for guiding algorithm evolution, from prompt design to evaluator construction, for existing frameworks. We then discuss the broader implications for the systems community: as AI assumes a central role in algorithm design, we argue that human researchers will increasingly focus on problem formulation and strategic guidance. Our results highlight both the disruptive potential and the urgent need to adapt systems research practices in the age of AI.
From Agentification to Self-Evolving Agentic AI for Wireless Networks: Concepts, Approaches, and Future Research Directions
Paper ↗
Abstract
Self-evolving agentic artificial intelligence (AI) offers a new paradigm for future wireless systems by enabling autonomous agents to continually adapt and improve without human intervention. Unlike static AI models, self-evolving agents embed an autonomous evolution cycle that updates models, tools, and workflows in response to environmental dynamics. This paper presents a comprehensive overview of self-evolving agentic AI, highlighting its layered architecture, life cycle, and key techniques, including tool intelligence, workflow optimization, self-reflection, and evolutionary learning. We further propose a multi-agent cooperative self-evolving agentic AI framework, where multiple large language models (LLMs) are assigned role-specialized prompts under the coordination of a supervisor agent. Through structured dialogue, iterative feedback, and systematic validation, the system autonomously executes the entire life cycle without human intervention. A case study on antenna evolution in low-altitude wireless networks (LAWNs) demonstrates how the framework autonomously upgrades fixed antenna optimization into movable antenna optimization. Experimental results show that the proposed self-evolving agentic AI autonomously improves beam gain and restores degraded performance by up to 52.02%, consistently surpassing the fixed baseline with little to no human intervention and validating its adaptability and robustness for next-generation wireless intelligence.
DeepV: A Model-Agnostic Retrieval-Augmented Framework for Verilog Code Generation with a High-Quality Knowledge Base
Paper ↗
Abstract
As large language models (LLMs) continue to be integrated into modern technology, there has been an increased push towards code generation applications, which also naturally extends to hardware design automation. LLM-based solutions for register transfer level (RTL) code generation for intellectual property (IP) designs have grown, especially with fine-tuned LLMs, prompt engineering, and agentic approaches becoming popular in literature. However, a gap has been exposed in these techniques, as they fail to integrate novel IPs into the model's knowledge base, subsequently resulting in poorly generated code. Additionally, as general-purpose LLMs continue to improve, fine-tuned methods on older models will not be able to compete to produce more accurate and efficient designs. Although some retrieval augmented generation (RAG) techniques exist to mitigate challenges presented in fine-tuning approaches, works tend to leverage low-quality codebases, incorporate computationally expensive fine-tuning in the frameworks, or do not use RAG directly in the RTL generation step. In this work, we introduce DeepV: a model-agnostic RAG framework to generate RTL designs by enhancing context through a large, high-quality dataset without any RTL-specific training. Our framework benefits the latest commercial LLM, OpenAI's GPT-5, with a near 17% increase in performance on the VerilogEval benchmark. We host DeepV for use by the community in a Hugging Face (HF) Space: https://huggingface.co/spaces/FICS-LLM/DeepV.
Spec2Control: Automating PLC/DCS Control-Logic Engineering from Natural Language Requirements with LLMs - A Multi-Plant Evaluation
Paper ↗
Abstract
Distributed control systems (DCS) manage the automation for many industrial production processes (e.g., power plants, chemical refineries, steel mills). Programming the software for such systems remains a largely manual and tedious process, incurring costs of millions of dollars for extensive facilities. Large language models (LLMs) have been found helpful in generating DCS control logic, resulting in commercial copilot tools. Today, these tools are focused on textual notations, they provide limited automation, and have not been tested on large datasets with realistic test cases. We introduce Spec2Control, a highly automated LLM workflow to generate graphical control logic directly from natural language user requirements. Experiments using an open dataset with 10 control narratives and 65 complex test cases demonstrate that Spec2Control can successfully identify control strategies, can generate 98.6% of correct control strategy connections autonomously, and can save between 94-96% of human labor. Spec2Control is being integrated into commercial ABB engineering tools, but is also available as an open-source variant for independent validation.
Adversarial Agent Collaboration for C to Rust Translation
Paper ↗
Abstract
Translating C to memory-safe languages, like Rust, prevents critical memory safety vulnerabilities that are prevalent in legacy C software. Existing approaches for C to safe Rust translation, including LLM-assisted ones, do not generalize on larger (> 500 LoC) C codebases because they depend on complex program analyses that frequently break. In this work, we present ACToR (Adversarial C To Rust translator), a simple LLM agent-based approach. Inspired by GANs, ACToR pits a generator agent against a discriminator agent, which collaborate to iteratively generate a Rust translation. On each iteration, the translator agent synthesizes and refines a Rust translation to pass an existing suite of tests, and then the discriminator agent finds new failing tests. We demonstrate that ACToR translates all of the 63 real-world command line utilities considered in our benchmarks, which have an average size of 485 lines of code, and it achieves over 90% test pass rate with zero human intervention. To our knowledge, it is the first such system that reliably translates C programs of this scale. Furthermore, ACToR improves translation correctness by up to 18.9% compared to baseline, non-adversarial approaches.
Algorithm Generation via Creative Ideation
Paper ↗
Abstract
Designing system algorithms remains challenging, where the discontinuous nature of the solution space often forces system engineers to rely on generic heuristics at the expense of performance. We study whether LLMs can practically drive algorithm generation, and find that they are biased towards well-known generic designs, rather than making the creative leaps needed to navigate the discontinuous solution space. To address this limitation, we introduce MetaMuse, a framework for creative ideation built on three self-reflection principles: (1) quantifying solution diversity and usefulness in measurable performance space, rather than abstract idea space, (2) steering ideation through external stimuli, rather than internal randomness, and (3) constructing executable solutions using waypoint reasoning, rather than free-form chain-of-thought. Extensive evaluation shows that MetaMuse can generate high-performing solutions for two critical problems at a global cloud provider: cache replacement (reducing cache misses by up to 35.76%) and online bin packing (reducing bin usage by up to 30.93%).
A4FN: an Agentic AI Architecture for Autonomous Flying Networks
Paper ↗
Abstract
This position paper presents A4FN, an Agentic Artificial Intelligence (AI) architecture for intent-driven automation in Flying Networks (FNs) using Unmanned Aerial Vehicles (UAVs) as access nodes. A4FN leverages Generative AI and Large Language Models (LLMs) to enable real-time, context-aware network control via a distributed agentic system. It comprises two components: the Perception Agent (PA), which semantically interprets multimodal input -- including imagery, audio, and telemetry data -- from UAV-mounted sensors to derive Service Level Specifications (SLSs); and the Decision-and-Action Agent (DAA), which reconfigures the network based on inferred intents. A4FN embodies key properties of Agentic AI, including autonomy, goal-driven reasoning, and continuous perception-action cycles. Designed for mission-critical, infrastructure-limited scenarios such as disaster response, it supports adaptive reconfiguration, dynamic resource management, and interoperability with emerging wireless technologies. The paper details the A4FN architecture, its core innovations, and open research challenges in multi-agent coordination and Agentic AI integration in next-generation FNs.
EvoEngineer: Mastering Automated CUDA Kernel Code Evolution with Large Language Models
Paper ↗
Abstract
CUDA kernel optimization has become a critical bottleneck for AI performance, as deep learning training and inference efficiency directly depends on highly optimized GPU kernels. Despite the promise of Large Language Models (LLMs) for automating kernel optimization, this field suffers from a fragmented ecosystem of isolated and incomparable approaches with unclear problem formulations. Furthermore, general-purpose LLM code evolution methods cannot meet strict correctness requirements of CUDA kernel optimization. We address these fundamental challenges by first formalizing CUDA kernel optimization as a code optimization task with a clear objective, constraints, and evaluation metrics. We then establish the first systematic LLM-based code evolution framework, EvoEngineer, that provides guidance for designing and adapting optimization strategies to achieve a balance between performance and correctness. Finally, we implement a kernel optimization system based on this framework and conduct extensive experiments on 91 real-world CUDA kernels. Our results demonstrate that EvoEngineer achieves a principled balance between performance and correctness, with the highest averaged median speedup of \textbf{2.72}$\times$ over baseline CUDA kernels and a code validity rate of \textbf{69.8}\%, outperforming existing methods on both dimensions. Our method achieves a maximum speedup of \textbf{36.75}$\times$ among all operations over PyTorch kernels and delivers the highest speedup on \textbf{28} (\textbf{56.0\%}) of 50 operations that achieve over \textbf{2$\times$} acceleration.
Automated Constraint Specification for Job Scheduling by Regulating Generative Model with Domain-Specific Representation
Paper ↗
Abstract
Advanced Planning and Scheduling (APS) systems have become indispensable for modern manufacturing operations, enabling optimized resource allocation and production efficiency in increasingly complex and dynamic environments. While algorithms for solving abstracted scheduling problems have been extensively investigated, the critical prerequisite of specifying manufacturing requirements into formal constraints remains manual and labor-intensive. Although recent advances of generative models, particularly Large Language Models (LLMs), show promise in automating constraint specification from heterogeneous raw manufacturing data, their direct application faces challenges due to natural language ambiguity, non-deterministic outputs, and limited domain-specific knowledge. This paper presents a constraint-centric architecture that regulates LLMs to perform reliable automated constraint specification for production scheduling. The architecture defines a hierarchical structural space organized across three levels, implemented through domain-specific representation to ensure precision and reliability while maintaining flexibility. Furthermore, an automated production scenario adaptation algorithm is designed and deployed to efficiently customize the architecture for specific manufacturing configurations. Experimental results demonstrate that the proposed approach successfully balances the generative capabilities of LLMs with the reliability requirements of manufacturing systems, significantly outperforming pure LLM-based approaches in constraint specification tasks.
Semantic-Aware Scheduling for GPU Clusters with Large Language Models
Paper ↗
Abstract
Deep learning (DL) schedulers are pivotal in optimizing resource allocation in GPU clusters, but operate with a critical limitation: they are largely blind to the semantic context of the jobs they manage. This forces them to rely on limited metadata, leading to high profiling overhead, unreliable duration estimation, inadequate failure handling, and poor observability. To this end, we propose SchedMate, a framework that bridges this semantic gap by systematically extracting deep insights from overlooked, unstructured data sources: source code, runtime logs, and historical jobs. SchedMate enhances existing schedulers non-intrusively through three LLM-based components. Our implementation integrates seamlessly with existing deep learning schedulers. Evaluations on a 128-GPU physical cluster and extensive simulations on production traces show SchedMate reduces average job completion times by up to 1.91x, substantially enhancing the scheduling performance, demonstrating the critical role of semantic-awareness in modern DL scheduling.
QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL
Paper ↗
Abstract
Designing and optimizing task-specific quantum circuits are crucial to leverage the advantage of quantum computing. Recent large language model (LLM)-based quantum circuit generation has emerged as a promising automatic solution. However, the fundamental challenges remain unaddressed: (i) parameterized quantum gates require precise numerical values for optimal performance, which also depend on multiple aspects, including the number of quantum gates, their parameters, and the layout/depth of the circuits. (ii) LLMs often generate low-quality or incorrect quantum circuits due to the lack of quantum domain-specific knowledge. We propose QUASAR, an agentic reinforcement learning (RL) framework for quantum circuits generation and optimization based on tool-augmented LLMs. To align the LLM with quantum-specific knowledge and improve the generated quantum circuits, QUASAR designs (i) a quantum circuit verification approach with external quantum simulators and (ii) a sophisticated hierarchical reward mechanism in RL training. Extensive evaluation shows improvements in both syntax and semantic performance of the generated quantum circuits. When augmenting a 4B LLM, QUASAR has achieved the validity of 99.31% in Pass@1 and 100% in Pass@10, outperforming industrial LLMs of GPT-4o, GPT-5 and DeepSeek-V3 and several supervised-fine-tuning (SFT)-only and RL-only baselines.
Opal: A Modular Framework for Optimizing Performance using Analytics and LLMs
Paper ↗
Abstract
Large Language Models (LLMs) show promise for automated code optimization but struggle without performance context. This work introduces Opal, a modular framework that connects performance analytics insights with the vast body of published by guiding LLMs to generate informed, trustworthy optimizations. Unlike traditional performance tools that identify bottlenecks but stop short of actionable suggestions, Opal bridges this long-standing gap by linking dynamic insights from hardware counters and Roofline analysis to stall events to optimization decisions. We evaluate Opal across 1640 experiments on real-world GPU kernels and find that in over 98.5% of cases, even a single insight source yields speedups, ranging on average from 19.34% to 52.3%. Our prompt template produced correct code in all but one case, where a vague diagnostic caused an unsafe suggestion. By automatically optimizing GPU kernels using performance analytics and LLMs, Opal marks a leap toward democratizing expert-level performance engineering for all.
ErrorPrism: Reconstructing Error Propagation Paths in Cloud Service Systems
Paper ↗
Abstract
Reliability management in cloud service systems is challenging due to the cascading effect of failures. Error wrapping, a practice prevalent in modern microservice development, enriches errors with context at each layer of the function call stack, constructing an error chain that describes a failure from its technical origin to its business impact. However, this also presents a significant traceability problem when recovering the complete error propagation path from the final log message back to its source. Existing approaches are ineffective at addressing this problem. To fill this gap, we present ErrorPrism in this work for automated reconstruction of error propagation paths in production microservice systems. ErrorPrism first performs static analysis on service code repositories to build a function call graph and map log strings to relevant candidate functions. This significantly reduces the path search space for subsequent analysis. Then, ErrorPrism employs an LLM agent to perform an iterative backward search to accurately reconstruct the complete, multi-hop error path. Evaluated on 67 production microservices at ByteDance, ErrorPrism achieves 97.0% accuracy in reconstructing paths for 102 real-world errors, outperforming existing static analysis and LLM-based approaches. ErrorPrism provides an effective and practical tool for root cause analysis in industrial microservice systems.
Introducing Large Language Models into the Design Flow of Time Sensitive Networking
Paper ↗
Abstract
The growing demand for real-time, safety-critical systems has significantly increased both the adoption and complexity of Time Sensitive Networking (TSN). Configuring an optimized TSN network is highly challenging, requiring careful planning, design, verification, validation, and deployment. Large Language Models (LLMs) have recently demonstrated strong capabilities in solving complex tasks, positioning them as promising candidates for automating end-to-end TSN deployment, referred to as TSN orchestration. This paper outlines the steps involved in TSN orchestration and the associated challenges. To assess the capabilities of existing LLM models, we conduct an initial proof-of-concept case study focused on TSN configuration across multiple models. Building on these insights, we propose an LLM-assisted orchestration framework. Unlike prior research on LLMs in computer networks, which has concentrated on general configuration and management, TSN-specific orchestration has not yet been investigated. We present the building blocks for automating TSN using LLMs, describe the proposed pipeline, and analyze opportunities and limitations for real-world deployment. Finally, we highlight key challenges and research directions, including the development of TSN-focused datasets, standardized benchmark suites, and the integration of external tools such as Network Calculus (NC) engines and simulators. This work provides the first roadmap toward assessing the feasibility of LLM-assisted TSN orchestration.
Toward an Unbiased Collective Memory for Efficient LLM-Based Agentic 6G Cross-Domain Management
Paper ↗
Abstract
This paper introduces a novel framework for proactive cross-domain resource orchestration in 6G RAN-Edge networks, featuring large language model (LLM)-augmented agents. The system comprises specialized RAN (energy efficiency) and Edge (latency assurance) agents that engage in iterative negotiation, supported by advanced reasoning and planning capabilities. Agents dynamically interact with a digital twin (DT) to test their proposals and leverage a long-term collective memory where their joint successful and failed agreements along with the related network contexts are distilled into strategies to either follow or avoid and subsequently stored. Given that agents are subject to a plethora of cognitive distortions when retrieving those past experiences -- such as primacy, recency, confirmation and availability biases -- we propose in this work a novel unbiased memory design (A reusable mockup version of the unbiased memory source code is available for non-commercial use at https://github.com/HatimChergui/unbiased-collective-memory). featuring (i) semantic retrieval of past strategies via Jaccard similarity; (ii) learning from failures through amplified weighting of SLA violations and mandatory inclusion of failed negotiation cases to mitigate confirmation bias; (iii) diversity enforcement to minimize availability bias and (iv) recency and primacy weighting with slow decay to counteract temporal biases. Evaluation results showcase the impact of existing biases and how the unbiased memory allows to tackle them by learning from both successful and failed strategies, either present or old, resulting in $\times 4.5$ and $\times 3.5$ reductions of unresolved negotiations compared to non-memory and vanilla memory baselines, respectively, while totally mitigating SLA violations as well as improving latency and energy saving distributions.
LogPilot: Intent-aware and Scalable Alert Diagnosis for Large-scale Online Service Systems
Paper ↗
Abstract
Effective alert diagnosis is essential for ensuring the reliability of large-scale online service systems. However, on-call engineers are often burdened with manually inspecting massive volumes of logs to identify root causes. While various automated tools have been proposed, they struggle in practice due to alert-agnostic log scoping and the inability to organize complex data effectively for reasoning. To overcome these limitations, we introduce LogPilot, an intent-aware and scalable framework powered by Large Language Models (LLMs) for automated log-based alert diagnosis. LogPilot introduces an intent-aware approach, interpreting the logic in alert definitions (e.g., PromQL) to precisely identify causally related logs and requests. To achieve scalability, it reconstructs each request's execution into a spatiotemporal log chain, clusters similar chains to identify recurring execution patterns, and provides representative samples to the LLMs for diagnosis. This clustering-based approach ensures the input is both rich in diagnostic detail and compact enough to fit within the LLM's context window. Evaluated on real-world alerts from Volcano Engine Cloud, LogPilot improves the usefulness of root cause summarization by 50.34% and exact localization accuracy by 54.79% over state-of-the-art methods. With a diagnosis time under one minute and a cost of only $0.074 per alert, LogPilot has been successfully deployed in production, offering an automated and practical solution for service alert diagnosis.
LLM-Powered Code Analysis and Optimization for Gaussian Splatting Kernels
Paper ↗
Abstract
3D Gaussian splatting (3DGS) is a transformative technique with profound implications on novel view synthesis and real-time rendering. Given its importance, there have been many attempts to improve its performance. However, with the increasing complexity of GPU architectures and the vast search space of performance-tuning parameters, it is a challenging task. Although manual optimizations have achieved remarkable speedups, they require domain expertise and the optimization process can be highly time consuming and error prone. In this paper, we propose to exploit large language models (LLMs) to analyze and optimize Gaussian splatting kernels. To our knowledge, this is the first work to use LLMs to optimize highly specialized real-world GPU kernels. We reveal the intricacies of using LLMs for code optimization and analyze the code optimization techniques from the LLMs. We also propose ways to collaborate with LLMs to further leverage their capabilities. For the original 3DGS code on the MipNeRF360 datasets, LLMs achieve significant speedups, 19% with Deepseek and 24% with GPT-5, demonstrating the different capabilities of different LLMs. By feeding additional information from performance profilers, the performance improvement from LLM-optimized code is enhanced to up to 42% and 38% on average. In comparison, our best-effort manually optimized version can achieve a performance improvement up to 48% and 39% on average, showing that there are still optimizations beyond the capabilities of current LLMs. On the other hand, even upon a newly proposed 3DGS framework with algorithmic optimizations, Seele, LLMs can still further enhance its performance by 6%, showing that there are optimization opportunities missed by domain experts. This highlights the potential of collaboration between domain experts and LLMs.
EEsizer: LLM-Based AI Agent for Sizing of Analog and Mixed Signal Circuit
Paper ↗
Abstract
The design of Analog and Mixed-Signal (AMS) integrated circuits (ICs) often involves significant manual effort, especially during the transistor sizing process. While Machine Learning techniques in Electronic Design Automation (EDA) have shown promise in reducing complexity and minimizing human intervention, they still face challenges such as numerous iterations and a lack of knowledge about AMS circuit design. Recently, Large Language Models (LLMs) have demonstrated significant potential across various fields, showing a certain level of knowledge in circuit design and indicating their potential to automate the transistor sizing process. In this work, we propose EEsizer, an LLM-based AI agent that integrates large language models with circuit simulators and custom data analysis functions, enabling fully automated, closed-loop transistor sizing without relying on external knowledge. By employing prompt engineering and Chain-of-Thought reasoning, the agent iteratively explores design directions, evaluates performance, and refines solutions with minimal human intervention. We first benchmarked 8 LLMs on six basic circuits and selected three high-performing models to optimize a 20-transistor CMOS operational amplifier, targeting multiple performance metrics, including rail-to-rail operation from 180 nm to 90 nm technology nodes. Notably, OpenAI o3 successfully achieved the user-intended target at 90 nm across three different test groups, with a maximum of 20 iterations, demonstrating adaptability and robustness at advanced nodes. To assess design robustness, we manually designed a bias circuit and performed a variation analysis using Gaussian-distributed variations on transistor dimensions and threshold voltages.
PEARL: Peer-Enhanced Adaptive Radio via On-Device LLM
Paper ↗
Abstract
We present PEARL (Peer-Enhanced Adaptive Radio via On-Device LLM), a framework for cooperative cross-layer optimization in device-to-device (D2D) communication. Building on our previous work on single-device on-device LLMs, PEARL extends the paradigm by leveraging both publisher and subscriber states to guide Wi-Fi Aware (WA) parameter selection. A context-aware reward, which normalizes latency by application tolerances and modulates energy by device battery states, provides richer supervision for KL-based finetuning. We study two lightweight variants: PEARL (Head + Low-Rank Adaptation (LoRA)) achieves the best overall performance, while PEARL-Lite (Head-only) delivers sub-20 ms inference at near-identical objective scores. Across synthetic scenarios grounded in real measurements, PEARL improves objective scores over heuristic and compact model baselines and reduces energy by up to 16% in cooperative low-battery cases. These results demonstrate that peer-aware context, reward-aligned training, and head-based efficiency make LLMs practical for always-on, on-device cross-layer control.
AssertFix: Empowering Automated Assertion Fix via Large Language Models
Paper ↗
Abstract
Assertion-based verification (ABV) is critical in ensuring that register-transfer level (RTL) designs conform to their functional specifications. SystemVerilog Assertions (SVA) effectively specify design properties, but writing and maintaining them manually is challenging and error-prone. Although recent progress of assertion generation methods leveraging large language models (LLMs) have shown great potential in improving assertion quality, they typically treat assertion generation as a final step, leaving the burden of fixing of the incorrect assertions to human effects, which may significantly limits the application of these methods. To address the above limitation, we propose an automatic assertion fix framework based on LLMs, named AssertFix. AsserFix accurately locates the RTL code related to the incorrect assertion, systematically identifies the root causes of the assertion errors, classifies the error type and finally applies dedicated fix strategies to automatically correct these errors, improving the overall quality of the generated assertions. Experimental results show that AssertFix achieves noticeable improvements in both fix rate and verification coverage across the Opencore benchmarks.
PAT-Agent: Autoformalization for Model Checking
Paper ↗
Abstract
Recent advances in large language models (LLMs) offer promising potential for automating formal methods. However, applying them to formal verification remains challenging due to the complexity of specification languages, the risk of hallucinated output, and the semantic gap between natural language and formal logic. We introduce PAT-Agent, an end-to-end framework for natural language autoformalization and formal model repair that combines the generative capabilities of LLMs with the rigor of formal verification to automate the construction of verifiable formal models. In PAT-Agent, a Planning LLM first extracts key modeling elements and generates a detailed plan using semantic prompts, which then guides a Code Generation LLM to synthesize syntactically correct and semantically faithful formal models. The resulting code is verified using the Process Analysis Toolkit (PAT) model checker against user-specified properties, and when discrepancies occur, a Repair Loop is triggered to iteratively correct the model using counterexamples. To improve flexibility, we built a web-based interface that enables users, particularly non-FM-experts, to describe, customize, and verify system behaviors through user-LLM interactions. Experimental results on 40 systems show that PAT-Agent consistently outperforms baselines, achieving high verification success with superior efficiency. The ablation studies confirm the importance of both planning and repair components, and the user study demonstrates that our interface is accessible and supports effective formal modeling, even for users with limited formal methods experience.
AssertGen: Enhancement of LLM-aided Assertion Generation through Cross-Layer Signal Bridging
Paper ↗
Abstract
Assertion-based verification (ABV) serves as a crucial technique for ensuring that register-transfer level (RTL) designs adhere to their specifications. While Large Language Model (LLM) aided assertion generation approaches have recently achieved remarkable progress, existing methods are still unable to effectively identify the relationship between design specifications and RTL designs, which leads to the insufficiency of the generated assertions. To address this issue, we propose AssertGen, an assertion generation framework that automatically generates SystemVerilog assertions (SVA). AssertGen first extracts verification objectives from specifications using a chain-of-thought (CoT) reasoning strategy, then bridges corresponding signals between these objectives and the RTL code to construct a cross-layer signal chain, and finally generates SVAs based on the LLM. Experimental results demonstrate that AssertGen outperforms the existing state-of-the-art methods across several key metrics, such as pass rate of formal property verification (FPV), cone of influence (COI), proof core and mutation testing coverage.
SysMoBench: Evaluating AI on Formally Modeling Complex Real-World Systems
Paper ↗
Abstract
Formal models are essential to specifying large, complex computer systems and verifying their correctness, but are notoriously expensive to write and maintain. Recent advances in generative AI show promise in generating certain forms of specifications. However, existing work mostly targets small code, not complete systems. It is unclear whether AI can deal with realistic system artifacts, as this requires abstracting their complex behavioral properties into formal models. We present SysMoBench, a benchmark that evaluates AI's ability to formally model large, complex systems. We focus on concurrent and distributed systems, which are keystones of today's critical computing infrastructures, encompassing operating systems and cloud infrastructure. We use TLA+, the de facto specification language for concurrent and distributed systems, though the benchmark can be extended to other specification languages. We address the primary challenge of evaluating AI-generated models by automating metrics like syntactic and runtime correctness, conformance to system code, and invariant correctness. SysMoBench currently includes nine diverse system artifacts: the Raft implementation of Etcd and Redis, the Spinlock and Mutex in Asterinas OS, etc.; more artifacts are being actively added. SysMoBench enables us to understand the capabilities and limitations of today's LLMs and agents, putting tools in this area on a firm footing and opening up promising new research directions.
BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software
Paper ↗
Abstract
Automatically compiling open-source software (OSS) projects is a vital, labor-intensive, and complex task, which makes it a good challenge for LLM Agents. Existing methods rely on manually curated rules and workflows, which cannot adapt to OSS that requires customized configuration or environment setup. Recent attempts using Large Language Models (LLMs) used selective evaluation on a subset of highly rated OSS, a practice that underestimates the realistic challenges of OSS compilation. In practice, compilation instructions are often absent, dependencies are undocumented, and successful builds may even require patching source files or modifying build scripts. We propose a more challenging and realistic benchmark, BUILD-BENCH, comprising OSS that are more diverse in quality, scale, and characteristics. Furthermore, we propose a strong baseline LLM-based agent, OSS-BUILD-AGENT, an effective system with enhanced build instruction retrieval module that achieves state-of-the-art performance on BUILD-BENCH and is adaptable to heterogeneous OSS characteristics. We also provide detailed analysis regarding different compilation method design choices and their influence to the whole task, offering insights to guide future advances. We believe performance on BUILD-BENCH can faithfully reflect an agent's ability to tackle compilation as a complex software engineering tasks, and, as such, our benchmark will spur innovation with a significant impact on downstream applications in the fields of software development and software security.
Bridging Language Models and Formal Methods for Intent-Driven Optical Network Design
Paper ↗
Abstract
Intent-Based Networking (IBN) aims to simplify network management by enabling users to specify high-level goals that drive automated network design and configuration. However, translating informal natural-language intents into formally correct optical network topologies remains challenging due to inherent ambiguity and lack of rigor in Large Language Models (LLMs). To address this, we propose a novel hybrid pipeline that integrates LLM-based intent parsing, formal methods, and Optical Retrieval-Augmented Generation (RAG). By enriching design decisions with domain-specific optical standards and systematically incorporating symbolic reasoning and verification techniques, our pipeline generates explainable, verifiable, and trustworthy optical network designs. This approach significantly advances IBN by ensuring reliability and correctness, essential for mission-critical networking tasks.
Boosting Pointer Analysis With Large Language Model-Enhanced Allocation Function Detection
Paper ↗
Abstract
Pointer analysis is foundational for many static analysis tasks, yet its effectiveness is often hindered by imprecise modeling of heap allocations, particularly in C/C++ programs where user-defined allocation functions (AFs) are pervasive. Existing approaches largely overlook these custom allocators, leading to coarse aliasing and reduced analysis precision. In this paper, we present AFD, a novel technique that enhances pointer analysis by automatically identifying and modeling custom allocation functions. AFD employs a hybrid approach: it uses value-flow analysis to detect straightforward wrappers and leverages Large Language Models (LLMs) to reason about more complex allocation patterns with side effects. This targeted enhancement enables precise modeling of heap objects at each call site, achieving context-sensitivity-like benefits without the associated overhead. We evaluate AFD on 15 real-world C projects, identifying over 600 custom AFs. Integrating AFD into a baseline pointer analysis yields a 26x increase in modeled heap objects and a 39% reduction in alias set sizes, with only 1.4x runtime overhead. Furthermore, our enhanced analysis improves indirect call resolution and uncovers 17 previously undetected memory bugs. These results demonstrate that precise modeling of custom allocation functions offers a scalable and practical path to improving pointer analysis in large software systems.
Boosting Pointer Analysis With Large Language Model-Enhanced Allocation Function Detection
Paper ↗
Abstract
Pointer analysis is foundational for many static analysis tasks, yet its effectiveness is often hindered by imprecise modeling of heap allocations, particularly in C/C++ programs where user-defined allocation functions (AFs) are pervasive. Existing approaches largely overlook these custom allocators, leading to coarse aliasing and reduced analysis precision. In this paper, we present AFD, a novel technique that enhances pointer analysis by automatically identifying and modeling custom allocation functions. AFD employs a hybrid approach: it uses value-flow analysis to detect straightforward wrappers and leverages Large Language Models (LLMs) to reason about more complex allocation patterns with side effects. This targeted enhancement enables precise modeling of heap objects at each call site, achieving context-sensitivity-like benefits without the associated overhead. We evaluate AFD on 15 real-world C projects, identifying over 600 custom AFs. Integrating AFD into a baseline pointer analysis yields a 26x increase in modeled heap objects and a 39% reduction in alias set sizes, with only 1.4x runtime overhead. Furthermore, our enhanced analysis improves indirect call resolution and uncovers 17 previously undetected memory bugs. These results demonstrate that precise modeling of custom allocation functions offers a scalable and practical path to improving pointer analysis in large software systems.
NeuroScalar: A Deep Learning Framework for Fast, Accurate, and In-the-Wild Cycle-Level Performance Prediction
Paper ↗
Abstract
The evaluation of new microprocessor designs is constrained by slow, cycle-accurate simulators that rely on unrepresentative benchmark traces. This paper introduces a novel deep learning framework for high-fidelity, ``in-the-wild'' simulation on production hardware. Our core contribution is a DL model trained on microarchitecture-independent features to predict cycle-level performance for hypothetical processor designs. This unique approach allows the model to be deployed on existing silicon to evaluate future hardware. We propose a complete system featuring a lightweight hardware trace collector and a principled sampling strategy to minimize user impact. This system achieves a simulation speed of 5 MIPS on a commodity GPU, imposing a mere 0.1% performance overhead. Furthermore, our co-designed Neutrino on-chip accelerator improves performance by 85x over the GPU. We demonstrate that this framework enables accurate performance analysis and large-scale hardware A/B testing on a massive scale using real-world applications.
NeuroScalar: A Deep Learning Framework for Fast, Accurate, and In-the-Wild Cycle-Level Performance Prediction
Paper ↗
Abstract
The evaluation of new microprocessor designs is constrained by slow, cycle-accurate simulators that rely on unrepresentative benchmark traces. This paper introduces a novel deep learning framework for high-fidelity, ``in-the-wild'' simulation on production hardware. Our core contribution is a DL model trained on microarchitecture-independent features to predict cycle-level performance for hypothetical processor designs. This unique approach allows the model to be deployed on existing silicon to evaluate future hardware. We propose a complete system featuring a lightweight hardware trace collector and a principled sampling strategy to minimize user impact. This system achieves a simulation speed of 5 MIPS on a commodity GPU, imposing a mere 0.1% performance overhead. Furthermore, our co-designed Neutrino on-chip accelerator improves performance by 85x over the GPU. We demonstrate that this framework enables accurate performance analysis and large-scale hardware A/B testing on a massive scale using real-world applications.
NeuroScalar: A Deep Learning Framework for Fast, Accurate, and In-the-Wild Cycle-Level Performance Prediction
Paper ↗
Abstract
The evaluation of new microprocessor designs is constrained by slow, cycle-accurate simulators that rely on unrepresentative benchmark traces. This paper introduces a novel deep learning framework for high-fidelity, ``in-the-wild'' simulation on production hardware. Our core contribution is a DL model trained on microarchitecture-independent features to predict cycle-level performance for hypothetical processor designs. This unique approach allows the model to be deployed on existing silicon to evaluate future hardware. We propose a complete system featuring a lightweight hardware trace collector and a principled sampling strategy to minimize user impact. This system achieves a simulation speed of 5 MIPS on a commodity GPU, imposing a mere 0.1% performance overhead. Furthermore, our co-designed Neutrino on-chip accelerator improves performance by 85x over the GPU. We demonstrate that this framework enables accurate performance analysis and large-scale hardware A/B testing on a massive scale using real-world applications.
SK2Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to Skin
Paper ↗
Abstract
Large Language Models (LLMs) have emerged as a promising approach for binary decompilation. However, the existing LLM-based decompilers still are somewhat limited in effectively presenting a program's source-level structure with its original identifiers. To mitigate this, we introduce SK2Decompile, a novel two-phase approach to decompile from the skeleton (semantic structure) to the skin (identifier) of programs. Specifically, we first apply a Structure Recovery model to translate a program's binary code to an Intermediate Representation (IR) as deriving the program's "skeleton", i.e., preserving control flow and data structures while obfuscating all identifiers with generic placeholders. We also apply reinforcement learning to reward the model for producing program structures that adhere to the syntactic and semantic rules expected by compilers. Second, we apply an Identifier Naming model to produce meaningful identifiers which reflect actual program semantics as deriving the program's "skin". We train the Identifier Naming model with a separate reinforcement learning objective that rewards the semantic similarity between its predictions and the reference code. Such a two-phase decompilation process facilitates advancing the correctness and readability of decompilation independently. Our evaluations indicate that SK2Decompile, significantly outperforms the SOTA baselines, achieving 21.6% average re-executability rate gain over GPT-5-mini on the HumanEval dataset and 29.4% average R2I improvement over Idioms on the GitHub2025 benchmark.
SK2Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to Skin
Paper ↗
Abstract
Large Language Models (LLMs) have emerged as a promising approach for binary decompilation. However, the existing LLM-based decompilers still are somewhat limited in effectively presenting a program's source-level structure with its original identifiers. To mitigate this, we introduce SK2Decompile, a novel two-phase approach to decompile from the skeleton (semantic structure) to the skin (identifier) of programs. Specifically, we first apply a Structure Recovery model to translate a program's binary code to an Intermediate Representation (IR) as deriving the program's "skeleton", i.e., preserving control flow and data structures while obfuscating all identifiers with generic placeholders. We also apply reinforcement learning to reward the model for producing program structures that adhere to the syntactic and semantic rules expected by compilers. Second, we apply an Identifier Naming model to produce meaningful identifiers which reflect actual program semantics as deriving the program's "skin". We train the Identifier Naming model with a separate reinforcement learning objective that rewards the semantic similarity between its predictions and the reference code. Such a two-phase decompilation process facilitates advancing the correctness and readability of decompilation independently. Our evaluations indicate that SK2Decompile, significantly outperforms the SOTA baselines, achieving 21.6% average re-executability rate gain over GPT-5-mini on the HumanEval dataset and 29.4% average R2I improvement over Idioms on the GitHub2025 benchmark.
Code once, Run Green: Automated Green Code Translation in Serverless Computing
Paper ↗
Abstract
The rapid digitization and the increasing use of emerging technologies such as AI models have significantly contributed to the emissions of computing infrastructure. Efforts to mitigate this impact typically focus on the infrastructure level such as powering data centers with renewable energy, or through the specific design of energy-efficient software. However, both strategies rely on stakeholder intervention, making their adoption in legacy and already-deployed systems unlikely. As a result, past architectural and implementation decisions continue to incur additional energy usage - a phenomenon we refer to as energy debt. Hence, in this paper, we investigate the potential of serverless computing platforms to automatically reduce energy debt by leveraging the unique access to function source code. Specifically, we explore whether large language models (LLMs) can translate serverless functions into more energy-efficient programming languages while preserving functional correctness. To this end, we design and implement ReFaaS and integrate it into the Fission serverless framework. We evaluate multiple LLMs on their ability to perform such code translations and analyze their impact on energy consumption. Our preliminary results indicate that translated functions can reduce invocation energy by up to 70%, achieving net energy savings after approximately 3,000 to 5,000 invocations, depending on the LLM used. Nonetheless, the approach faces several challenges: not all functions are suitable for translation, and for some, the amortization threshold is significantly higher or unreachable. Despite these limitations, we identify four key research challenges whose resolution could unlock long-term, automated mitigation of energy debt in serverless computing.
Code once, Run Green: Automated Green Code Translation in Serverless Computing
Paper ↗
Abstract
The rapid digitization and the increasing use of emerging technologies such as AI models have significantly contributed to the emissions of computing infrastructure. Efforts to mitigate this impact typically focus on the infrastructure level such as powering data centers with renewable energy, or through the specific design of energy-efficient software. However, both strategies rely on stakeholder intervention, making their adoption in legacy and already-deployed systems unlikely. As a result, past architectural and implementation decisions continue to incur additional energy usage - a phenomenon we refer to as energy debt. Hence, in this paper, we investigate the potential of serverless computing platforms to automatically reduce energy debt by leveraging the unique access to function source code. Specifically, we explore whether large language models (LLMs) can translate serverless functions into more energy-efficient programming languages while preserving functional correctness. To this end, we design and implement ReFaaS and integrate it into the Fission serverless framework. We evaluate multiple LLMs on their ability to perform such code translations and analyze their impact on energy consumption. Our preliminary results indicate that translated functions can reduce invocation energy by up to 70%, achieving net energy savings after approximately 3,000 to 5,000 invocations, depending on the LLM used. Nonetheless, the approach faces several challenges: not all functions are suitable for translation, and for some, the amortization threshold is significantly higher or unreachable. Despite these limitations, we identify four key research challenges whose resolution could unlock long-term, automated mitigation of energy debt in serverless computing.
VibeCodeHPC: An Agent-Based Iterative Prompting Auto-Tuner for HPC Code Generation Using LLMs
Paper ↗
Abstract
We propose VibeCodeHPC, an automatic tuning system for HPC programs based on multi-agent LLMs for code generation. VibeCodeHPC tunes programs through multi-agent role allocation and iterative prompt refinement. We describe the system configuration with four roles: Project Manager (PM), System Engineer (SE), Programmer (PG), and Continuous Delivery (CD). We introduce dynamic agent deployment and activity monitoring functions to facilitate effective multi-agent collaboration. In our case study, we convert and optimize CPU-based matrix-matrix multiplication code written in C to GPU code using CUDA. The multi-agent configuration of VibeCodeHPC achieved higher-quality code generation per unit time compared to a solo-agent configuration. Additionally, the dynamic agent deployment and activity monitoring capabilities facilitated more effective identification of requirement violations and other issues.
InvBench: Can LLMs Accelerate Program Verification with Invariant Synthesis?
Paper ↗
Abstract
Program verification relies on loop invariants, yet automatically discovering strong invariants remains a long-standing challenge. We introduce a principled framework for evaluating LLMs on invariant synthesis. Our approach uses a verifier-based decision procedure with a formal soundness guarantee and assesses not only correctness but also the speedup that invariants provide in verification. We evaluate 7 state-of-the-art LLMs, and existing LLM-based verifiers against the traditional solver UAutomizer. While LLM-based verifiers represent a promising direction, they do not yet offer a significant advantage over UAutomizer. Model capability also proves critical, as shown by sharp differences in speedups across models, and our benchmark remains an open challenge for current LLMs. Finally, we show that supervised fine-tuning and Best-of-N sampling can improve performance: fine-tuning on 3589 instances raises the percentage of speedup cases for Qwen3-Coder-480B from 8% to 29.2%, and Best-of-N sampling with N=16 improves Claude-sonnet-4 from 8.8% to 22.1%.
InvBench: Can LLMs Accelerate Program Verification with Invariant Synthesis?
Paper ↗
Abstract
Program verification relies on loop invariants, yet automatically discovering strong invariants remains a long-standing challenge. We introduce a principled framework for evaluating LLMs on invariant synthesis. Our approach uses a verifier-based decision procedure with a formal soundness guarantee and assesses not only correctness but also the speedup that invariants provide in verification. We evaluate 7 state-of-the-art LLMs, and existing LLM-based verifiers against the traditional solver UAutomizer. While LLM-based verifiers represent a promising direction, they do not yet offer a significant advantage over UAutomizer. Model capability also proves critical, as shown by sharp differences in speedups across models, and our benchmark remains an open challenge for current LLMs. Finally, we show that supervised fine-tuning and Best-of-N sampling can improve performance: fine-tuning on 3589 instances raises the percentage of speedup cases for Qwen3-Coder-480B from 8% to 29.2%, and Best-of-N sampling with N=16 improves Claude-sonnet-4 from 8.8% to 22.1%.
Toward Robust and Efficient ML-Based GPU Caching for Modern Inference
Paper ↗
Abstract
In modern GPU inference, cache efficiency remains a major bottleneck. In recommendation models, embedding hit rates largely determine throughput, while in large language models, KV-cache misses substantially increase time-to-first-token (TTFT). Heuristic policies such as \textsc{LRU} often struggle under structured access patterns. Learning-based approaches are promising, but in practice face two major limitations: they degrade sharply when predictions are inaccurate, or they gain little even with accurate predictions due to conservative designs. Some also incur high overhead, further limiting practicality. We present \textsc{LCR}, a practical framework for learning-based GPU caching that delivers performance gains while ensuring robustness and efficiency. Its core algorithm, \textsc{LARU}, enhances \textsc{LRU} with machine-learned predictions and dynamically adapts to prediction accuracy through online error estimation. When predictions are accurate, \textsc{LARU} achieves near-optimal performance. With inaccurate predictions, it degrades gracefully to near-\textsc{LRU} performance. With \textsc{LCR}, we bridge the gap between empirical progress and theoretical advances in learning-based caching. Experiments show that \textsc{LCR} delivers consistent gains under realistic conditions. In DLRM and LLM scenarios, it improves throughput by up to 24.2\% and reduces P99 TTFT by up to 28.3\%, outperforming widely used inference systems. Even under poor predictions, its performance remains stable, demonstrating practical robustness.
Toward Robust and Efficient ML-Based GPU Caching for Modern Inference
Paper ↗
Abstract
In modern GPU inference, cache efficiency remains a major bottleneck. In recommendation models, embedding hit rates largely determine throughput, while in large language models, KV-cache misses substantially increase time-to-first-token (TTFT). Heuristic policies such as \textsc{LRU} often struggle under structured access patterns. Learning-based approaches are promising, but in practice face two major limitations: they degrade sharply when predictions are inaccurate, or they gain little even with accurate predictions due to conservative designs. Some also incur high overhead, further limiting practicality. We present \textsc{LCR}, a practical framework for learning-based GPU caching that delivers performance gains while ensuring robustness and efficiency. Its core algorithm, \textsc{LARU}, enhances \textsc{LRU} with machine-learned predictions and dynamically adapts to prediction accuracy through online error estimation. When predictions are accurate, \textsc{LARU} achieves near-optimal performance. With inaccurate predictions, it degrades gracefully to near-\textsc{LRU} performance. With \textsc{LCR}, we bridge the gap between empirical progress and theoretical advances in learning-based caching. Experiments show that \textsc{LCR} delivers consistent gains under realistic conditions. In DLRM and LLM scenarios, it improves throughput by up to 24.2\% and reduces P99 TTFT by up to 28.3\%, outperforming widely used inference systems. Even under poor predictions, its performance remains stable, demonstrating practical robustness.
An LLM-based Agentic Framework for Accessible Network Control
Paper ↗
Abstract
Traditional approaches to network management have been accessible only to a handful of highly-trained network operators with significant expert knowledge. This creates barriers for lay users to easily manage their networks without resorting to experts. With recent development of powerful large language models (LLMs) for language comprehension, we design a system to make network management accessible to a broader audience of non-experts by allowing users to converse with networks in natural language. To effectively leverage advancements in LLMs, we propose an agentic framework that uses an intermediate representation to streamline configuration across diverse vendor equipment, retrieves the network state from memory in real-time, and provides an interface for external feedback. We also conduct pilot studies to collect real user data of natural language utterances for network control, and present a visualization interface to facilitate dialogue-driven user interaction and enable large-scale data collection for future development. Preliminary experiments validate the effectiveness of our proposed system components with LLM integration on both synthetic and real user utterances. Through our data collection and visualization efforts, we pave the way for more effective use of LLMs and democratize network control for everyday users.
An LLM-based Agentic Framework for Accessible Network Control
Paper ↗
Abstract
Traditional approaches to network management have been accessible only to a handful of highly-trained network operators with significant expert knowledge. This creates barriers for lay users to easily manage their networks without resorting to experts. With recent development of powerful large language models (LLMs) for language comprehension, we design a system to make network management accessible to a broader audience of non-experts by allowing users to converse with networks in natural language. To effectively leverage advancements in LLMs, we propose an agentic framework that uses an intermediate representation to streamline configuration across diverse vendor equipment, retrieves the network state from memory in real-time, and provides an interface for external feedback. We also conduct pilot studies to collect real user data of natural language utterances for network control, and present a visualization interface to facilitate dialogue-driven user interaction and enable large-scale data collection for future development. Preliminary experiments validate the effectiveness of our proposed system components with LLM integration on both synthetic and real user utterances. Through our data collection and visualization efforts, we pave the way for more effective use of LLMs and democratize network control for everyday users.
The Cream Rises to the Top: Efficient Reranking Method for Verilog Code Generation
Paper ↗
Abstract
LLMs face significant challenges in Verilog generation due to limited domain-specific knowledge. While sampling techniques improve pass@k metrics, hardware engineers need one trustworthy solution rather than uncertain candidates. To bridge this gap, we formulate it as a semantic alignment problem between requirements and Verilog implementations, and propose VCD-RNK, a discriminator model tailored for efficient Verilog code reranking. Specifically, VCD-RNKincorporates Verilog-specific reasoning by distilling expert knowledge across three dimensions: code semantic analysis, test case generation, and functional correctness assessment. By explicitly simulating the above reasoning processes during inference, VCD-RNK effectively avoids computationally intensive test execution in existing methods.
The Cream Rises to the Top: Efficient Reranking Method for Verilog Code Generation
Paper ↗
Abstract
LLMs face significant challenges in Verilog generation due to limited domain-specific knowledge. While sampling techniques improve pass@k metrics, hardware engineers need one trustworthy solution rather than uncertain candidates. To bridge this gap, we formulate it as a semantic alignment problem between requirements and Verilog implementations, and propose VCD-RNK, a discriminator model tailored for efficient Verilog code reranking. Specifically, VCD-RNKincorporates Verilog-specific reasoning by distilling expert knowledge across three dimensions: code semantic analysis, test case generation, and functional correctness assessment. By explicitly simulating the above reasoning processes during inference, VCD-RNK effectively avoids computationally intensive test execution in existing methods.
Automated Multi-Agent Workflows for RTL Design
Paper ↗
Abstract
The rise of agentic AI workflows unlocks novel opportunities for computer systems design and optimization. However, for specialized domains such as program synthesis, the relative scarcity of HDL and proprietary EDA resources online compared to more common programming tasks introduces challenges, often necessitating task-specific fine-tuning, high inference costs, and manually-crafted agent orchestration. In this work, we present VeriMaAS, a multi-agent framework designed to automatically compose agentic workflows for RTL code generation. Our key insight is to integrate formal verification feedback from HDL tools directly into workflow generation, reducing the cost of gradient-based updates or prolonged reasoning traces. Our method improves synthesis performance by 5-7% for pass@k over fine-tuned baselines, while requiring only a few hundred training examples, representing an order-of-magnitude reduction in supervision cost.
Automated Multi-Agent Workflows for RTL Design
Paper ↗
Abstract
The rise of agentic AI workflows unlocks novel opportunities for computer systems design and optimization. However, for specialized domains such as program synthesis, the relative scarcity of HDL and proprietary EDA resources online compared to more common programming tasks introduces challenges, often necessitating task-specific fine-tuning, high inference costs, and manually-crafted agent orchestration. In this work, we present VeriMaAS, a multi-agent framework designed to automatically compose agentic workflows for RTL code generation. Our key insight is to integrate formal verification feedback from HDL tools directly into workflow generation, reducing the cost of gradient-based updates or prolonged reasoning traces. Our method improves synthesis performance by 5-7% for pass@k over fine-tuned baselines, while requiring only a few hundred training examples, representing an order-of-magnitude reduction in supervision cost.
Large Language Models for 3D IC Space Planning
Paper ↗
Abstract
Three-dimensional integrated circuits (3D ICs) have emerged as a promising solution to the scaling limits of two-dimensional designs, offering higher integration density, shorter interconnects, and improved performance. As design complexity increases, effective space planning becomes essential to reduce dead space and ensure layout quality. This study investigates the use of large language models (LLMs) for 3D IC space planning through a post-order slicing tree representation, which guarantees legal space plans while aiming to minimize dead space. Open-source LLMs were fine-tuned on large-scale synthetic datasets and further evaluated on MCNC-derived 3D benchmarks. Experimental results indicate that the proposed framework achieves a favorable balance between runtime efficiency, legality, and dead-space reduction, with zero-dead-space layouts obtained in a significant portion of test cases under practical runtime budgets. Beyond synthetic benchmarks, the method generalizes to MCNC cases such as ami33 and ami49, though larger and irregular instances remain challenging. The approach also shows potential for cross-domain applications, including logistics and 3D object placement, where spatial efficiency is critical. Overall, the results suggest that LLM-based space planning can serve as a data-driven complement to traditional electronic design automation (EDA) methods, providing new insights for scalable 3D layout generation.
Metadata-Guided Adaptable Frequency Scaling across Heterogeneous Applications and Devices
Paper ↗
Abstract
Dynamic Voltage and Frequency Scaling is essential for enhancing energy efficiency in mobile platforms. However, traditional heuristic-based governors are increasingly inadequate for managing the complexity of heterogeneous System-on-Chip designs and diverse application workloads. Although reinforcement learning approaches offer improved performance, their poor generalization capability and reliance on extensive retraining for each hardware and application combination leads to significant deployment costs. In this work, we observe that device and application metadata inherently encapsulate valuable knowledge for DVFS, presenting an opportunity to overcome these limitations. We formulate DVFS for heterogeneous devices and applications as a multi-task reinforcement learning problem. We introduce MetaDVFS, which is a metadata-guided framework that systematically leverages metadata to discover and transfer shared knowledge across DVFS tasks. MetaDVFS can output a set of DVFS models with significant generalization capability for various applications of heterogeneous devices. Evaluations on five Google Pixel devices running six applications show that MetaDVFS achieves up to 17% improvement in Performance-Power Ratio and up to 26% improvement in Quality of Experience. Compared to state-of-the-art methods, MetaDVFS delivers 70.8% faster adaptation and 5.8-27.6% higher performance over standalone device-application specific training, while avoiding negative transfer effects. These results establish MetaDVFS as an effective and scalable solution for DVFS deployment in heterogeneous mobile environments.
XaaS Containers: Performance-Portable Representation With Source and IR Containers
Paper ↗
Abstract
High-performance computing (HPC) systems and cloud data centers are converging, and containers are becoming the default method of portable software deployment. Yet, while containers simplify software management, they face significant performance challenges in HPC environments as they must sacrifice hardware-specific optimizations to achieve portability. Although HPC containers can use runtime hooks to access optimized MPI libraries and GPU devices, they are limited by application binary interface (ABI) compatibility and cannot overcome the effects of early-stage compilation decisions. Acceleration as a Service (XaaS) proposes a vision of performance-portable containers, where a containerized application should achieve peak performance across all HPC systems. We present a practical realization of this vision through Source and Intermediate Representation (IR) containers, where we delay performance-critical decisions until the target system specification is known. We analyze specialization mechanisms in HPC software and propose a new LLM-assisted method for automatic discovery of specializations. By examining the compilation pipeline, we develop a methodology to build containers optimized for target architectures at deployment time. Our prototype demonstrates that new XaaS containers combine the convenience of containerization with the performance benefits of system-specialized builds.
XaaS Containers: Performance-Portable Representation With Source and IR Containers
Paper ↗
Abstract
High-performance computing (HPC) systems and cloud data centers are converging, and containers are becoming the default method of portable software deployment. Yet, while containers simplify software management, they face significant performance challenges in HPC environments as they must sacrifice hardware-specific optimizations to achieve portability. Although HPC containers can use runtime hooks to access optimized MPI libraries and GPU devices, they are limited by application binary interface (ABI) compatibility and cannot overcome the effects of early-stage compilation decisions. Acceleration as a Service (XaaS) proposes a vision of performance-portable containers, where a containerized application should achieve peak performance across all HPC systems. We present a practical realization of this vision through Source and Intermediate Representation (IR) containers, where we delay performance-critical decisions until the target system specification is known. We analyze specialization mechanisms in HPC software and propose a new LLM-assisted method for automatic discovery of specializations. By examining the compilation pipeline, we develop a methodology to build containers optimized for target architectures at deployment time. Our prototype demonstrates that new XaaS containers combine the convenience of containerization with the performance benefits of system-specialized builds.
ACCeLLiuM: Supervised Fine-Tuning for Automated OpenACC Pragma Generation
Paper ↗
Abstract
The increasing ubiquity of GPUs is accompanied by the increasing complexity of their hardware and parallel programming frameworks. Directive-based parallel programming standards like OpenACC simplify GPU programming to some extent by abstracting away low-level complexities, but a fair amount of expertise is still required in order to use those directives effectively. We introduce ACCeLLiuM, two open weights Large Language Models specifically fine-tuned for generating expert OpenACC directives for data-parallel loops, along with the supervised fine-tuning dataset that was used to train them. The ACCeLLiuM SFT dataset contains 4,033 OpenACC pragma-loop pairs mined from public GitHub C/C++ repositories, with 3,223 pairs for training and 810 for testing. Experimental evaluations show a pronounced performance gap in generating correct OpenACC pragmas between base LLMs and our fine-tuned versions. On the held-out test set, base LLMs fail to consistently generate valid pragmas, whereas LLMs fine-tuned on the ACCeLLiuM dataset generate valid pragmas with the correct directive type for $87\%$ of the data-parallel loops, and exact pragmas--including directives, clauses, clause order, and clause variables--for $50\%$ of the cases. Even when not exact, generated pragmas frequently incorporate the correct clauses in a different order than the ground-truth label, or include additional clauses that enable finer control over parallel execution, data movement, and concurrency, offering practical value beyond strict string-matching. By publicly releasing the code, models, and dataset as ACCeLLiuM we hope to establish a reproducible benchmark for LLM-powered OpenACC pragma generation, and lower the barrier to automated GPU offloading of serially written programs.
ACCeLLiuM: Supervised Fine-Tuning for Automated OpenACC Pragma Generation
Paper ↗
Abstract
The increasing ubiquity of GPUs is accompanied by the increasing complexity of their hardware and parallel programming frameworks. Directive-based parallel programming standards like OpenACC simplify GPU programming to some extent by abstracting away low-level complexities, but a fair amount of expertise is still required in order to use those directives effectively. We introduce ACCeLLiuM, two open weights Large Language Models specifically fine-tuned for generating expert OpenACC directives for data-parallel loops, along with the supervised fine-tuning dataset that was used to train them. The ACCeLLiuM SFT dataset contains 4,033 OpenACC pragma-loop pairs mined from public GitHub C/C++ repositories, with 3,223 pairs for training and 810 for testing. Experimental evaluations show a pronounced performance gap in generating correct OpenACC pragmas between base LLMs and our fine-tuned versions. On the held-out test set, base LLMs fail to consistently generate valid pragmas, whereas LLMs fine-tuned on the ACCeLLiuM dataset generate valid pragmas with the correct directive type for $87\%$ of the data-parallel loops, and exact pragmas--including directives, clauses, clause order, and clause variables--for $50\%$ of the cases. Even when not exact, generated pragmas frequently incorporate the correct clauses in a different order than the ground-truth label, or include additional clauses that enable finer control over parallel execution, data movement, and concurrency, offering practical value beyond strict string-matching. By publicly releasing the code, models, and dataset as ACCeLLiuM we hope to establish a reproducible benchmark for LLM-powered OpenACC pragma generation, and lower the barrier to automated GPU offloading of serially written programs.
CCrepairBench: A High-Fidelity Benchmark and Reinforcement Learning Framework for C++ Compilation Repair
Paper ↗
Abstract
The automated repair of C++ compilation errors presents a significant challenge, the resolution of which is critical for developer productivity. Progress in this domain is constrained by two primary factors: the scarcity of large-scale, high-fidelity datasets and the limitations of conventional supervised methods, which often fail to generate semantically correct patches.This paper addresses these gaps by introducing a comprehensive framework with three core contributions. First, we present CCrepair, a novel, large-scale C++ compilation error dataset constructed through a sophisticated generate-and-verify pipeline. Second, we propose a Reinforcement Learning (RL) paradigm guided by a hybrid reward signal, shifting the focus from mere compilability to the semantic quality of the fix. Finally, we establish the robust, two-stage evaluation system providing this signal, centered on an LLM-as-a-Judge whose reliability has been rigorously validated against the collective judgments of a panel of human experts. This integrated approach aligns the training objective with generating high-quality, non-trivial patches that are both syntactically and semantically correct. The effectiveness of our approach was demonstrated experimentally. Our RL-trained Qwen2.5-1.5B-Instruct model achieved performance comparable to a Qwen2.5-14B-Instruct model, validating the efficiency of our training paradigm. Our work provides the research community with a valuable new dataset and a more effective paradigm for training and evaluating robust compilation repair models, paving the way for more practical and reliable automated programming assistants.
CCrepairBench: A High-Fidelity Benchmark and Reinforcement Learning Framework for C++ Compilation Repair
Paper ↗
Abstract
The automated repair of C++ compilation errors presents a significant challenge, the resolution of which is critical for developer productivity. Progress in this domain is constrained by two primary factors: the scarcity of large-scale, high-fidelity datasets and the limitations of conventional supervised methods, which often fail to generate semantically correct patches.This paper addresses these gaps by introducing a comprehensive framework with three core contributions. First, we present CCrepair, a novel, large-scale C++ compilation error dataset constructed through a sophisticated generate-and-verify pipeline. Second, we propose a Reinforcement Learning (RL) paradigm guided by a hybrid reward signal, shifting the focus from mere compilability to the semantic quality of the fix. Finally, we establish the robust, two-stage evaluation system providing this signal, centered on an LLM-as-a-Judge whose reliability has been rigorously validated against the collective judgments of a panel of human experts. This integrated approach aligns the training objective with generating high-quality, non-trivial patches that are both syntactically and semantically correct. The effectiveness of our approach was demonstrated experimentally. Our RL-trained Qwen2.5-1.5B-Instruct model achieved performance comparable to a Qwen2.5-14B-Instruct model, validating the efficiency of our training paradigm. Our work provides the research community with a valuable new dataset and a more effective paradigm for training and evaluating robust compilation repair models, paving the way for more practical and reliable automated programming assistants.
MicroRCA-Agent: Microservice Root Cause Analysis Method Based on Large Language Model Agents
Paper ↗
Abstract
This paper presents MicroRCA-Agent, an innovative solution for microservice root cause analysis based on large language model agents, which constructs an intelligent fault root cause localization system with multimodal data fusion. The technical innovations are embodied in three key aspects: First, we combine the pre-trained Drain log parsing algorithm with multi-level data filtering mechanism to efficiently compress massive logs into high-quality fault features. Second, we employ a dual anomaly detection approach that integrates Isolation Forest unsupervised learning algorithms with status code validation to achieve comprehensive trace anomaly identification. Third, we design a statistical symmetry ratio filtering mechanism coupled with a two-stage LLM analysis strategy to enable full-stack phenomenon summarization across node-service-pod hierarchies. The multimodal root cause analysis module leverages carefully designed cross-modal prompts to deeply integrate multimodal anomaly information, fully exploiting the cross-modal understanding and logical reasoning capabilities of large language models to generate structured analysis results encompassing fault components, root cause descriptions, and reasoning trace. Comprehensive ablation studies validate the complementary value of each modal data and the effectiveness of the system architecture. The proposed solution demonstrates superior performance in complex microservice fault scenarios, achieving a final score of 50.71. The code has been released at: https://github.com/tangpan360/MicroRCA-Agent.
MicroRCA-Agent: Microservice Root Cause Analysis Method Based on Large Language Model Agents
Paper ↗
Abstract
This paper presents MicroRCA-Agent, an innovative solution for microservice root cause analysis based on large language model agents, which constructs an intelligent fault root cause localization system with multimodal data fusion. The technical innovations are embodied in three key aspects: First, we combine the pre-trained Drain log parsing algorithm with multi-level data filtering mechanism to efficiently compress massive logs into high-quality fault features. Second, we employ a dual anomaly detection approach that integrates Isolation Forest unsupervised learning algorithms with status code validation to achieve comprehensive trace anomaly identification. Third, we design a statistical symmetry ratio filtering mechanism coupled with a two-stage LLM analysis strategy to enable full-stack phenomenon summarization across node-service-pod hierarchies. The multimodal root cause analysis module leverages carefully designed cross-modal prompts to deeply integrate multimodal anomaly information, fully exploiting the cross-modal understanding and logical reasoning capabilities of large language models to generate structured analysis results encompassing fault components, root cause descriptions, and reasoning trace. Comprehensive ablation studies validate the complementary value of each modal data and the effectiveness of the system architecture. The proposed solution demonstrates superior performance in complex microservice fault scenarios, achieving a final score of 50.71. The code has been released at: https://github.com/tangpan360/MicroRCA-Agent.
DeepAssert: An LLM-Aided Verification Framework with Fine-Grained Assertion Generation for Modules with Extracted Module Specifications
Paper ↗
Abstract
Assertion-Based Verification (ABV) is a crucial method for ensuring that logic designs conform to their architectural specifications. However, existing assertion generation methods primarily rely on information either from the design specification, or register-transfer level (RTL) code. The former methods are typically limited to generating assertions for the top-level design. As the top-level design is composed of different modules without module-level specifications, they are unable to generate deep assertions that target the internal functionality of modules. The latter methods often rely on a golden RTL model, which is difficult to obtain. To address the above limitations, this paper presents a novel large language model (LLM)-aided verification framework named DeepAssert. DeepAssert is capable of analyzing the invocation relationships between modules and extracting independent specifications for each module with its I/O port information. These extracted specifications are subsequently used to guide LLMs to automatically generate fine-grained deep assertions for these modules. Our evaluation demonstrates that DeepAssert significantly outperforms existing methods such as AssertLLM and Spec2Assertion in generating high-quality deep assertions for modules. Furthermore, when integrated with these methods, DeepAssert can enhance the overall quality of the assertions generated. This allows for a more comprehensive and effective verification process.
DeepAssert: An LLM-Aided Verification Framework with Fine-Grained Assertion Generation for Modules with Extracted Module Specifications
Paper ↗
Abstract
Assertion-Based Verification (ABV) is a crucial method for ensuring that logic designs conform to their architectural specifications. However, existing assertion generation methods primarily rely on information either from the design specification, or register-transfer level (RTL) code. The former methods are typically limited to generating assertions for the top-level design. As the top-level design is composed of different modules without module-level specifications, they are unable to generate deep assertions that target the internal functionality of modules. The latter methods often rely on a golden RTL model, which is difficult to obtain. To address the above limitations, this paper presents a novel large language model (LLM)-aided verification framework named DeepAssert. DeepAssert is capable of analyzing the invocation relationships between modules and extracting independent specifications for each module with its I/O port information. These extracted specifications are subsequently used to guide LLMs to automatically generate fine-grained deep assertions for these modules. Our evaluation demonstrates that DeepAssert significantly outperforms existing methods such as AssertLLM and Spec2Assertion in generating high-quality deep assertions for modules. Furthermore, when integrated with these methods, DeepAssert can enhance the overall quality of the assertions generated. This allows for a more comprehensive and effective verification process.
SALT4Decompile: Inferring Source-level Abstract Logic Tree for LLM-Based Binary Decompilation
Paper ↗
Abstract
Decompilation is widely used in reverse engineering to recover high-level language code from binary executables. While recent approaches leveraging Large Language Models (LLMs) have shown promising progress, they typically treat assembly code as a linear sequence of instructions, overlooking arbitrary jump patterns and isolated data segments inherent to binary files. This limitation significantly hinders their ability to correctly infer source code semantics from assembly code. To address this limitation, we propose \saltm, a novel binary decompilation method that abstracts stable logical features shared between binary and source code. The core idea of \saltm is to abstract selected binary-level operations, such as specific jumps, into a high-level logic framework that better guides LLMs in semantic recovery. Given a binary function, \saltm constructs a Source-level Abstract Logic Tree (\salt) from assembly code to approximate the logic structure of high-level language. It then fine-tunes an LLM using the reconstructed \salt to generate decompiled code. Finally, the output is refined through error correction and symbol recovery to improve readability and correctness. We compare \saltm to three categories of baselines (general-purpose LLMs, commercial decompilers, and decompilation methods) using three well-known datasets (Decompile-Eval, MBPP, Exebench). Our experimental results demonstrate that \saltm is highly effective in recovering the logic of the source code, significantly outperforming state-of-the-art methods (e.g., 70.4\% TCP rate on Decompile-Eval with a 10.6\% improvement). The results further validate its robustness against four commonly used obfuscation techniques. Additionally, analyses of real-world software and a user study confirm that our decompiled output offers superior assistance to human analysts in comprehending binary functions.
SALT4Decompile: Inferring Source-level Abstract Logic Tree for LLM-Based Binary Decompilation
Paper ↗
Abstract
Decompilation is widely used in reverse engineering to recover high-level language code from binary executables. While recent approaches leveraging Large Language Models (LLMs) have shown promising progress, they typically treat assembly code as a linear sequence of instructions, overlooking arbitrary jump patterns and isolated data segments inherent to binary files. This limitation significantly hinders their ability to correctly infer source code semantics from assembly code. To address this limitation, we propose \saltm, a novel binary decompilation method that abstracts stable logical features shared between binary and source code. The core idea of \saltm is to abstract selected binary-level operations, such as specific jumps, into a high-level logic framework that better guides LLMs in semantic recovery. Given a binary function, \saltm constructs a Source-level Abstract Logic Tree (\salt) from assembly code to approximate the logic structure of high-level language. It then fine-tunes an LLM using the reconstructed \salt to generate decompiled code. Finally, the output is refined through error correction and symbol recovery to improve readability and correctness. We compare \saltm to three categories of baselines (general-purpose LLMs, commercial decompilers, and decompilation methods) using three well-known datasets (Decompile-Eval, MBPP, Exebench). Our experimental results demonstrate that \saltm is highly effective in recovering the logic of the source code, significantly outperforming state-of-the-art methods (e.g., 70.4\% TCP rate on Decompile-Eval with a 10.6\% improvement). The results further validate its robustness against four commonly used obfuscation techniques. Additionally, analyses of real-world software and a user study confirm that our decompiled output offers superior assistance to human analysts in comprehending binary functions.
Automating Modelica Module Generation Using Large Language Models: A Case Study on Building Control Description Language
Paper ↗
Abstract
Dynamic energy systems and controls require advanced modeling frameworks to design and test supervisory and fault tolerant strategies. Modelica is a widely used equation based language, but developing control modules is labor intensive and requires specialized expertise. This paper examines the use of large language models (LLMs) to automate the generation of Control Description Language modules in the Building Modelica Library as a case study. We developed a structured workflow that combines standardized prompt scaffolds, library aware grounding, automated compilation with OpenModelica, and human in the loop evaluation. Experiments were carried out on four basic logic tasks (And, Or, Not, and Switch) and five control modules (chiller enable/disable, bypass valve control, cooling tower fan speed, plant requests, and relief damper control). The results showed that GPT 4o failed to produce executable Modelica code in zero shot mode, while Claude Sonnet 4 achieved up to full success for basic logic blocks with carefully engineered prompts. For control modules, success rates reached 83 percent, and failed outputs required medium level human repair (estimated one to eight hours). Retrieval augmented generation often produced mismatches in module selection (for example, And retrieved as Or), while a deterministic hard rule search strategy avoided these errors. Human evaluation also outperformed AI evaluation, since current LLMs cannot assess simulation results or validate behavioral correctness. Despite these limitations, the LLM assisted workflow reduced the average development time from 10 to 20 hours down to 4 to 6 hours per module, corresponding to 40 to 60 percent time savings. These results highlight both the potential and current limitations of LLM assisted Modelica generation, and point to future research in pre simulation validation, stronger grounding, and closed loop evaluation.
Automating Modelica Module Generation Using Large Language Models: A Case Study on Building Control Description Language
Paper ↗
Abstract
Dynamic energy systems and controls require advanced modeling frameworks to design and test supervisory and fault tolerant strategies. Modelica is a widely used equation based language, but developing control modules is labor intensive and requires specialized expertise. This paper examines the use of large language models (LLMs) to automate the generation of Control Description Language modules in the Building Modelica Library as a case study. We developed a structured workflow that combines standardized prompt scaffolds, library aware grounding, automated compilation with OpenModelica, and human in the loop evaluation. Experiments were carried out on four basic logic tasks (And, Or, Not, and Switch) and five control modules (chiller enable/disable, bypass valve control, cooling tower fan speed, plant requests, and relief damper control). The results showed that GPT 4o failed to produce executable Modelica code in zero shot mode, while Claude Sonnet 4 achieved up to full success for basic logic blocks with carefully engineered prompts. For control modules, success rates reached 83 percent, and failed outputs required medium level human repair (estimated one to eight hours). Retrieval augmented generation often produced mismatches in module selection (for example, And retrieved as Or), while a deterministic hard rule search strategy avoided these errors. Human evaluation also outperformed AI evaluation, since current LLMs cannot assess simulation results or validate behavioral correctness. Despite these limitations, the LLM assisted workflow reduced the average development time from 10 to 20 hours down to 4 to 6 hours per module, corresponding to 40 to 60 percent time savings. These results highlight both the potential and current limitations of LLM assisted Modelica generation, and point to future research in pre simulation validation, stronger grounding, and closed loop evaluation.
Shift-Left Techniques in Electronic Design Automation: A Survey
Paper ↗
Abstract
The chip design process involves numerous steps, beginning with defining product requirements and progressing through architectural planning, system-level design, and the physical layout of individual circuit blocks. As the enablers of large-scale chip development, Electronic Design Automation (EDA) tools play a vital role in helping designers achieve high-quality results. The Shift-Left methodology introduces a pathway toward creating digital twins and fusing multiple design steps, thereby transitioning traditionally sequential, physically-aware processes into virtual design environments. This shift allows designers to establish stronger correlations earlier and optimize designs more effectively. However, challenges remain, especially in accurately replicating downstream behaviors and determining the right scope and timing for adoption. These challenges, in turn, have revealed new opportunities for EDA vendors, physical designers, and logic designers alike. As the industry advances toward intelligent EDA tools and techniques, it is timely to reflect on Shift-Left progress made and the challenges that remain. The rise of AI techniques and the momentum of open-source design flows have significantly strengthened prediction and modeling capabilities, making data-driven methods increasingly relevant to the EDA community. This, in turn, enhances the ''Shift-Left'' features embedded in current tools. In this paper, we present a comprehensive survey of existing and emerging paradigms in Shift-Left research within EDA and the broader design ecosystem. Our goal is to provide a unique perspective on the state of the field and its future directions. Relevant papers mentioned are organized in https://github.com/iCAS-SJTU/Shift-Left-EDA-Papers.
Shift-Left Techniques in Electronic Design Automation: A Survey
Paper ↗
Abstract
The chip design process involves numerous steps, beginning with defining product requirements and progressing through architectural planning, system-level design, and the physical layout of individual circuit blocks. As the enablers of large-scale chip development, Electronic Design Automation (EDA) tools play a vital role in helping designers achieve high-quality results. The Shift-Left methodology introduces a pathway toward creating digital twins and fusing multiple design steps, thereby transitioning traditionally sequential, physically-aware processes into virtual design environments. This shift allows designers to establish stronger correlations earlier and optimize designs more effectively. However, challenges remain, especially in accurately replicating downstream behaviors and determining the right scope and timing for adoption. These challenges, in turn, have revealed new opportunities for EDA vendors, physical designers, and logic designers alike. As the industry advances toward intelligent EDA tools and techniques, it is timely to reflect on Shift-Left progress made and the challenges that remain. The rise of AI techniques and the momentum of open-source design flows have significantly strengthened prediction and modeling capabilities, making data-driven methods increasingly relevant to the EDA community. This, in turn, enhances the ''Shift-Left'' features embedded in current tools. In this paper, we present a comprehensive survey of existing and emerging paradigms in Shift-Left research within EDA and the broader design ecosystem. Our goal is to provide a unique perspective on the state of the field and its future directions. Relevant papers mentioned are organized in https://github.com/iCAS-SJTU/Shift-Left-EDA-Papers.
TopoSizing: An LLM-aided Framework of Topology-based Understanding and Sizing for AMS Circuits
Paper ↗
Abstract
Analog and mixed-signal circuit design remains challenging due to the shortage of high-quality data and the difficulty of embedding domain knowledge into automated flows. Traditional black-box optimization achieves sampling efficiency but lacks circuit understanding, which often causes evaluations to be wasted in low-value regions of the design space. In contrast, learning-based methods embed structural knowledge but are case-specific and costly to retrain. Recent attempts with large language models show potential, yet they often rely on manual intervention, limiting generality and transparency. We propose TopoSizing, an end-to-end framework that performs robust circuit understanding directly from raw netlists and translates this knowledge into optimization gains. Our approach first applies graph algorithms to organize circuits into a hierarchical device-module-stage representation. LLM agents then execute an iterative hypothesis-verification-refinement loop with built-in consistency checks, producing explicit annotations. Verified insights are integrated into Bayesian optimization through LLM-guided initial sampling and stagnation-triggered trust-region updates, improving efficiency while preserving feasibility.
TopoSizing: An LLM-aided Framework of Topology-based Understanding and Sizing for AMS Circuits
Paper ↗
Abstract
Analog and mixed-signal circuit design remains challenging due to the shortage of high-quality data and the difficulty of embedding domain knowledge into automated flows. Traditional black-box optimization achieves sampling efficiency but lacks circuit understanding, which often causes evaluations to be wasted in low-value regions of the design space. In contrast, learning-based methods embed structural knowledge but are case-specific and costly to retrain. Recent attempts with large language models show potential, yet they often rely on manual intervention, limiting generality and transparency. We propose TopoSizing, an end-to-end framework that performs robust circuit understanding directly from raw netlists and translates this knowledge into optimization gains. Our approach first applies graph algorithms to organize circuits into a hierarchical device-module-stage representation. LLM agents then execute an iterative hypothesis-verification-refinement loop with built-in consistency checks, producing explicit annotations. Verified insights are integrated into Bayesian optimization through LLM-guided initial sampling and stagnation-triggered trust-region updates, improving efficiency while preserving feasibility.
MALTA: An Automated CGRA Design Framework
Paper ↗
Abstract
Coarse-grained Reconfigurable Arrays (CGRAs) are a promising computing architecture that can deliver high-performance, energy-efficient acceleration across diverse domains. By supporting reconfiguration at the functional unit level, CGRAs efficiently adapt to varying computational patterns and optimize resource utilization. However, designing CGRAs is highly challenging due to the vast design space, independent architectural parameters, and the time-consuming nature of manual design. Fortunately, the rapid advancement of large language models (LLMs) presents new opportunities to automate this process. In this work, we propose MALTA-- an open-source multi-agent LLM-based framework for Hardware/Software (HW/SW) co-design of CGRAs. The framework employs LLM reasoning to generate CGRAs across four stages: HW/SW co-design, Design error correction, Best design selection, and Evaluation & Feedback. Furthermore, MALTA iteratively optimizes the generated CGRAs, leveraging agent reasoning and feedback to achieve higher PPA (that is, power, performance, and area) design points for a given domain. In addition, we introduce an LLM self-learning mechanism that employs LLM-driven decision making to select the optimal CGRA to accelerate the design process. We evaluate the framework with state-of-the-art LLM-based methods and manual CGRA design, in terms of performance, power consumption, and area. Experimental results show that MALTA efficiently generates high-quality CGRA architectures, significantly reducing manual design effort and demonstrating the potential of our framework for real-world CGRA design.
MALTA: An Automated CGRA Design Framework
Paper ↗
Abstract
Coarse-grained Reconfigurable Arrays (CGRAs) are a promising computing architecture that can deliver high-performance, energy-efficient acceleration across diverse domains. By supporting reconfiguration at the functional unit level, CGRAs efficiently adapt to varying computational patterns and optimize resource utilization. However, designing CGRAs is highly challenging due to the vast design space, independent architectural parameters, and the time-consuming nature of manual design. Fortunately, the rapid advancement of large language models (LLMs) presents new opportunities to automate this process. In this work, we propose MALTA-- an open-source multi-agent LLM-based framework for Hardware/Software (HW/SW) co-design of CGRAs. The framework employs LLM reasoning to generate CGRAs across four stages: HW/SW co-design, Design error correction, Best design selection, and Evaluation & Feedback. Furthermore, MALTA iteratively optimizes the generated CGRAs, leveraging agent reasoning and feedback to achieve higher PPA (that is, power, performance, and area) design points for a given domain. In addition, we introduce an LLM self-learning mechanism that employs LLM-driven decision making to select the optimal CGRA to accelerate the design process. We evaluate the framework with state-of-the-art LLM-based methods and manual CGRA design, in terms of performance, power consumption, and area. Experimental results show that MALTA efficiently generates high-quality CGRA architectures, significantly reducing manual design effort and demonstrating the potential of our framework for real-world CGRA design.
Automating Code Generation for Semiconductor Equipment Control from Developer Utterances with LLMs
Paper ↗
Abstract
Semiconductors form the backbone of modern electronics, with their manufacturing and testing relying on highly specialized equipment and domain-specific programming languages. Equipment languages such as the Algorithmic Pattern Generator (ALPG) are critical for precise hardware control but are challenging to program due to their low-level syntax and steep learning curve. While large language models (LLMs) have shown promise in generating high-level code from natural language, their effectiveness on low-level equipment languages remains limited. To address this, we propose Progressive Knowledge Enhancement (PKE), a novel multi-stage prompting framework that progressively extracts and activates the latent knowledge within LLMs, guiding them from simple to complex examples without extensive fine-tuning. Empirical evaluation on an industrial ALPG dataset shows that PKE significantly outperforms standard prompting and surpasses state-of-the-art methods in generating correct ALPG code, achieving 11.1\% and 15.2\% higher exact match scores compared to the second-best technique. Further analysis of individual components confirms that progressive knowledge extraction based on difficulty enhances accuracy. Our study offer a practical approach to boosting LLM capabilities for specialized low-level programming, supporting greater productivity in semiconductor software development.
Automating Code Generation for Semiconductor Equipment Control from Developer Utterances with LLMs
Paper ↗
Abstract
Semiconductors form the backbone of modern electronics, with their manufacturing and testing relying on highly specialized equipment and domain-specific programming languages. Equipment languages such as the Algorithmic Pattern Generator (ALPG) are critical for precise hardware control but are challenging to program due to their low-level syntax and steep learning curve. While large language models (LLMs) have shown promise in generating high-level code from natural language, their effectiveness on low-level equipment languages remains limited. To address this, we propose Progressive Knowledge Enhancement (PKE), a novel multi-stage prompting framework that progressively extracts and activates the latent knowledge within LLMs, guiding them from simple to complex examples without extensive fine-tuning. Empirical evaluation on an industrial ALPG dataset shows that PKE significantly outperforms standard prompting and surpasses state-of-the-art methods in generating correct ALPG code, achieving 11.1\% and 15.2\% higher exact match scores compared to the second-best technique. Further analysis of individual components confirms that progressive knowledge extraction based on difficulty enhances accuracy. Our study offer a practical approach to boosting LLM capabilities for specialized low-level programming, supporting greater productivity in semiconductor software development.
Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization
Paper ↗
Abstract
Recent advances in large language models (LLMs) demonstrate their effectiveness in scaling test-time compute for software engineering tasks. However, these approaches often focus on high-level solutions, with limited attention to optimizing low-level CUDA kernel implementations. Additionally, existing kernel generation benchmarks suffer from exploitable loopholes and insufficient diversity in testing conditions, hindering true generalization assessment. To address these limitations, we introduce robust-kbench, a new benchmark for rigorous evaluation of kernel performance and correctness across varied scenarios. Furthermore, we present a comprehensive agentic framework that automates CUDA kernel discovery, verification, and optimization. This pipeline enables frontier LLMs to translate torch code to CUDA kernels and iteratively improve their runtime within our robust evaluation setting. Our sequential workflow first translates PyTorch code into equivalent CUDA kernels. It then optimizes their runtime using a novel evolutionary meta-generation procedure tailored to the CUDA ecosystem, guided by LLM-based verifiers for correctness and efficient filtering. Evaluated on robust-kbench, our approach produces CUDA kernels outperforming torch implementations for practical applications, including forward and backward passes. It can fuse operations and deploy various runtime optimization strategies. The verifier workflow accurately classifies incorrect kernels, enhancing hardware verification efficiency.
Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization
Paper ↗
Abstract
Recent advances in large language models (LLMs) demonstrate their effectiveness in scaling test-time compute for software engineering tasks. However, these approaches often focus on high-level solutions, with limited attention to optimizing low-level CUDA kernel implementations. Additionally, existing kernel generation benchmarks suffer from exploitable loopholes and insufficient diversity in testing conditions, hindering true generalization assessment. To address these limitations, we introduce robust-kbench, a new benchmark for rigorous evaluation of kernel performance and correctness across varied scenarios. Furthermore, we present a comprehensive agentic framework that automates CUDA kernel discovery, verification, and optimization. This pipeline enables frontier LLMs to translate torch code to CUDA kernels and iteratively improve their runtime within our robust evaluation setting. Our sequential workflow first translates PyTorch code into equivalent CUDA kernels. It then optimizes their runtime using a novel evolutionary meta-generation procedure tailored to the CUDA ecosystem, guided by LLM-based verifiers for correctness and efficient filtering. Evaluated on robust-kbench, our approach produces CUDA kernels outperforming torch implementations for practical applications, including forward and backward passes. It can fuse operations and deploy various runtime optimization strategies. The verifier workflow accurately classifies incorrect kernels, enhancing hardware verification efficiency.
ASTREA: Introducing Agentic Intelligence for Orbital Thermal Autonomy
Paper ↗
Abstract
This paper presents ASTREA, the first agentic system deployed on flight-heritage hardware (TRL 9) for autonomous spacecraft operations. Using thermal control as a representative use case, we integrate a resource-constrained Large Language Model (LLM) agent with a reinforcement learning controller in an asynchronous architecture tailored for space-qualified platforms. Ground experiments show that LLM-guided supervision improves thermal stability and reduces violations, confirming the feasibility of combining semantic reasoning with adaptive control under hardware constraints. However, on-orbit validation aboard the International Space Station (ISS) reveals performance degradation caused by inference latency mismatched with the rapid thermal cycles characteristic of Low Earth Orbit (LEO) satellites. These results highlight both the opportunities and current limitations of agentic LLM-based systems in real flight environments, providing practical design guidelines for future space autonomy.
ASTREA: Introducing Agentic Intelligence for Orbital Thermal Autonomy
Paper ↗
Abstract
This paper presents ASTREA, the first agentic system deployed on flight-heritage hardware (TRL 9) for autonomous spacecraft operations. Using thermal control as a representative use case, we integrate a resource-constrained Large Language Model (LLM) agent with a reinforcement learning controller in an asynchronous architecture tailored for space-qualified platforms. Ground experiments show that LLM-guided supervision improves thermal stability and reduces violations, confirming the feasibility of combining semantic reasoning with adaptive control under hardware constraints. However, on-orbit validation aboard the International Space Station (ISS) reveals performance degradation caused by inference latency mismatched with the rapid thermal cycles characteristic of Low Earth Orbit (LEO) satellites. These results highlight both the opportunities and current limitations of agentic LLM-based systems in real flight environments, providing practical design guidelines for future space autonomy.
LLM-Based Approach for Enhancing Maintainability of Automotive Architectures
Paper ↗
Abstract
There are many bottlenecks that decrease the flexibility of automotive systems, making their long-term maintenance, as well as updates and extensions in later lifecycle phases increasingly difficult, mainly due to long re-engineering, standardization, and compliance procedures, as well as heterogeneity and numerosity of devices and underlying software components involved. In this paper, we explore the potential of Large Language Models (LLMs) when it comes to the automation of tasks and processes that aim to increase the flexibility of automotive systems. Three case studies towards achieving this goal are considered as outcomes of early-stage research: 1) updates, hardware abstraction, and compliance, 2) interface compatibility checking, and 3) architecture modification suggestions. For proof-of-concept implementation, we rely on OpenAI's GPT-4o model.
LLM-Based Approach for Enhancing Maintainability of Automotive Architectures
Paper ↗
Abstract
There are many bottlenecks that decrease the flexibility of automotive systems, making their long-term maintenance, as well as updates and extensions in later lifecycle phases increasingly difficult, mainly due to long re-engineering, standardization, and compliance procedures, as well as heterogeneity and numerosity of devices and underlying software components involved. In this paper, we explore the potential of Large Language Models (LLMs) when it comes to the automation of tasks and processes that aim to increase the flexibility of automotive systems. Three case studies towards achieving this goal are considered as outcomes of early-stage research: 1) updates, hardware abstraction, and compliance, 2) interface compatibility checking, and 3) architecture modification suggestions. For proof-of-concept implementation, we rely on OpenAI's GPT-4o model.
Converting IEC 61131-3 LD into SFC Using Large Language Model: Dataset and Testing
Paper ↗
Abstract
In the domain of Programmable Logic Controller (PLC) programming, converting a Ladder Diagram (LD) into a Sequential Function Chart (SFC) is an inherently challenging problem, primarily due to the lack of domain-specific knowledge and the issue of state explosion in existing algorithms. However, the rapid development of Artificial Intelligence (AI) - especially Large Language Model (LLM) - offers a promising new approach. Despite this potential, data-driven approaches in this field have been hindered by a lack of suitable datasets. To address this gap, we constructed several datasets consisting of paired textual representations of SFC and LD programs that conform to the IEC 61131-3 standard. Based on these datasets, we explored the feasibility of automating the LD-SFC conversion using LLM. Our preliminary experiments show that a fine-tuned LLM model achieves up to 91% accuracy on certain dataset, with the lowest observed accuracy being 79%, suggesting that with proper training and representation, LLMs can effectively support LD-SFC conversion. These early results highlight the viability and future potential of this approach.
Converting IEC 61131-3 LD into SFC Using Large Language Model: Dataset and Testing
Paper ↗
Abstract
In the domain of Programmable Logic Controller (PLC) programming, converting a Ladder Diagram (LD) into a Sequential Function Chart (SFC) is an inherently challenging problem, primarily due to the lack of domain-specific knowledge and the issue of state explosion in existing algorithms. However, the rapid development of Artificial Intelligence (AI) - especially Large Language Model (LLM) - offers a promising new approach. Despite this potential, data-driven approaches in this field have been hindered by a lack of suitable datasets. To address this gap, we constructed several datasets consisting of paired textual representations of SFC and LD programs that conform to the IEC 61131-3 standard. Based on these datasets, we explored the feasibility of automating the LD-SFC conversion using LLM. Our preliminary experiments show that a fine-tuned LLM model achieves up to 91% accuracy on certain dataset, with the lowest observed accuracy being 79%, suggesting that with proper training and representation, LLMs can effectively support LD-SFC conversion. These early results highlight the viability and future potential of this approach.
From Legacy Fortran to Portable Kokkos: An Autonomous Agentic AI Workflow
Paper ↗
Abstract
Scientific applications continue to rely on legacy Fortran codebases originally developed for homogeneous, CPU-based systems. As High-Performance Computing (HPC) shifts toward heterogeneous GPU-accelerated architectures, many accelerators lack native Fortran bindings, creating an urgent need to modernize legacy codes for portability. Frameworks like Kokkos provide performance portability and a single-source C++ abstraction, but manual Fortran-to-Kokkos porting demands significant expertise and time. Large language models (LLMs) have shown promise in source-to-source code generation, yet their use in fully autonomous workflows for translating and optimizing parallel code remains largely unexplored, especially for performance portability across diverse hardware. This paper presents an agentic AI workflow where specialized LLM "agents" collaborate to translate, validate, compile, run, test, debug, and optimize Fortran kernels into portable Kokkos C++ programs. Results show the pipeline modernizes a range of benchmark kernels, producing performance-portable Kokkos codes across hardware partitions. Paid OpenAI models such as GPT-5 and o4-mini-high executed the workflow for only a few U.S. dollars, generating optimized codes that surpassed Fortran baselines, whereas open-source models like Llama4-Maverick often failed to yield functional codes. This work demonstrates the feasibility of agentic AI for Fortran-to-Kokkos transformation and offers a pathway for autonomously modernizing legacy scientific applications to run portably and efficiently on diverse supercomputers. It further highlights the potential of LLM-driven agentic systems to perform structured, domain-specific reasoning tasks in scientific and systems-oriented applications.
From Legacy Fortran to Portable Kokkos: An Autonomous Agentic AI Workflow
Paper ↗
Abstract
Scientific applications continue to rely on legacy Fortran codebases originally developed for homogeneous, CPU-based systems. As High-Performance Computing (HPC) shifts toward heterogeneous GPU-accelerated architectures, many accelerators lack native Fortran bindings, creating an urgent need to modernize legacy codes for portability. Frameworks like Kokkos provide performance portability and a single-source C++ abstraction, but manual Fortran-to-Kokkos porting demands significant expertise and time. Large language models (LLMs) have shown promise in source-to-source code generation, yet their use in fully autonomous workflows for translating and optimizing parallel code remains largely unexplored, especially for performance portability across diverse hardware. This paper presents an agentic AI workflow where specialized LLM "agents" collaborate to translate, validate, compile, run, test, debug, and optimize Fortran kernels into portable Kokkos C++ programs. Results show the pipeline modernizes a range of benchmark kernels, producing performance-portable Kokkos codes across hardware partitions. Paid OpenAI models such as GPT-5 and o4-mini-high executed the workflow for only a few U.S. dollars, generating optimized codes that surpassed Fortran baselines, whereas open-source models like Llama4-Maverick often failed to yield functional codes. This work demonstrates the feasibility of agentic AI for Fortran-to-Kokkos transformation and offers a pathway for autonomously modernizing legacy scientific applications to run portably and efficiently on diverse supercomputers. It further highlights the potential of LLM-driven agentic systems to perform structured, domain-specific reasoning tasks in scientific and systems-oriented applications.
UniPar: A Unified LLM-Based Framework for Parallel and Accelerated Code Translation in HPC
Paper ↗
Abstract
Translating programs between various parallel programming languages is an important problem in the high-performance computing (HPC) community. Existing tools for this problem are either too narrow in scope and/or outdated. Recent explosive growth in the popularity of large language models (LLMs) and their ability to generate and translate code offers a potential alternative approach. Toward that end, we first need to systematically evaluate the ability of LLMs to translate between parallel languages. In this work, we introduce UniPar, a systematic evaluation framework for LLM-based parallel code translation. Specifically, in this work, we target translations between serial code, CUDA, and OpenMP. Our goal is to assess how well current instruction-tuned LLMs -- specifically GPT-4o-mini and LLaMA-3.3-70B-Instruct -- can be used out of the box or enhanced through known strategies. We evaluated four major usage modes: hyperparameter optimization for decoding, zero- and few-shot prompting, supervised fine-tuning, and iterative feedback through compiler-based repair. As a part of the evaluation, we construct a new dataset called PARATRANS, covering both serial-to-parallel translation and cross-paradigm transformations. Our findings reveal that while off-the-shelf models struggle under the default settings (e.g., GPT-4o-mini achieves only 46% compilation and 15% functional correctness), our UniPar methodology -- combining fine-tuning, hyperparameter tuning, and compiler-guided repair -- improves performance by up to 2X (69% compilation and 33% correctness). We believe that our findings will provide useful insights for researchers to further improve LLMs for the parallel language translation problem. UniPar source code and PARATRANS dataset are available at our GitHub repository https://github.com/Scientific-Computing-Lab/UniPar_AI.
UniPar: A Unified LLM-Based Framework for Parallel and Accelerated Code Translation in HPC
Paper ↗
Abstract
Translating programs between various parallel programming languages is an important problem in the high-performance computing (HPC) community. Existing tools for this problem are either too narrow in scope and/or outdated. Recent explosive growth in the popularity of large language models (LLMs) and their ability to generate and translate code offers a potential alternative approach. Toward that end, we first need to systematically evaluate the ability of LLMs to translate between parallel languages. In this work, we introduce UniPar, a systematic evaluation framework for LLM-based parallel code translation. Specifically, in this work, we target translations between serial code, CUDA, and OpenMP. Our goal is to assess how well current instruction-tuned LLMs -- specifically GPT-4o-mini and LLaMA-3.3-70B-Instruct -- can be used out of the box or enhanced through known strategies. We evaluated four major usage modes: hyperparameter optimization for decoding, zero- and few-shot prompting, supervised fine-tuning, and iterative feedback through compiler-based repair. As a part of the evaluation, we construct a new dataset called PARATRANS, covering both serial-to-parallel translation and cross-paradigm transformations. Our findings reveal that while off-the-shelf models struggle under the default settings (e.g., GPT-4o-mini achieves only 46% compilation and 15% functional correctness), our UniPar methodology -- combining fine-tuning, hyperparameter tuning, and compiler-guided repair -- improves performance by up to 2X (69% compilation and 33% correctness). We believe that our findings will provide useful insights for researchers to further improve LLMs for the parallel language translation problem. UniPar source code and PARATRANS dataset are available at our GitHub repository https://github.com/Scientific-Computing-Lab/UniPar_AI.
Large language model-empowered next-generation computer-aided engineering
Paper ↗
Abstract
Software development has entered a new era where large language models (LLMs) now serve as general-purpose reasoning engines, enabling natural language interaction and transformative applications across diverse domains. This paradigm is now extending into computer-aided engineering (CAE). Recent applications of LLMs in CAE have successfully automated routine tasks, including CAD model generation and FEM simulations. Nevertheless, these contributions, which primarily serve to reduce manual labor, are often insufficient for addressing the significant computational challenges posed by large-scale, high-dimensional systems. To this aim, we first introduce the concept of LLM-empowered CAE agent, where LLMs act as autonomous collaborators that plan, execute, and adapt CAE workflows. Then, we propose an LLM-empowered CAE agent for data-free model order reduction (MOR), a powerful yet underused approach for ultra-fast large-scale parametric analysis due to the intrusive nature and labor-intensive redevelopment of solvers. LLMs can alleviate this barrier by automating derivations, code restructuring, and implementation, making intrusive MOR both practical and broadly accessible. To demonstrate feasibility, we present an LLM-empowered CAE agent for solving ultra-large-scale space-parameter-time (S-P-T) physical problems using Tensor-decomposition-based A Priori Surrogates (TAPS). Our results show that natural language prompts describing parametric partial differential equations (PDEs) can be translated into efficient solver implementations, substantially reducing human effort while producing high-fidelity reduced-order models. Moreover, LLMs can synthesize novel MOR solvers for unseen cases such as nonlinear and high-dimensional parametric problems based on their internal knowledge base. This highlights the potential of LLMs to establish the foundation for next-generation CAE systems.
Large language model-empowered next-generation computer-aided engineering
Paper ↗
Abstract
Software development has entered a new era where large language models (LLMs) now serve as general-purpose reasoning engines, enabling natural language interaction and transformative applications across diverse domains. This paradigm is now extending into computer-aided engineering (CAE). Recent applications of LLMs in CAE have successfully automated routine tasks, including CAD model generation and FEM simulations. Nevertheless, these contributions, which primarily serve to reduce manual labor, are often insufficient for addressing the significant computational challenges posed by large-scale, high-dimensional systems. To this aim, we first introduce the concept of LLM-empowered CAE agent, where LLMs act as autonomous collaborators that plan, execute, and adapt CAE workflows. Then, we propose an LLM-empowered CAE agent for data-free model order reduction (MOR), a powerful yet underused approach for ultra-fast large-scale parametric analysis due to the intrusive nature and labor-intensive redevelopment of solvers. LLMs can alleviate this barrier by automating derivations, code restructuring, and implementation, making intrusive MOR both practical and broadly accessible. To demonstrate feasibility, we present an LLM-empowered CAE agent for solving ultra-large-scale space-parameter-time (S-P-T) physical problems using Tensor-decomposition-based A Priori Surrogates (TAPS). Our results show that natural language prompts describing parametric partial differential equations (PDEs) can be translated into efficient solver implementations, substantially reducing human effort while producing high-fidelity reduced-order models. Moreover, LLMs can synthesize novel MOR solvers for unseen cases such as nonlinear and high-dimensional parametric problems based on their internal knowledge base. This highlights the potential of LLMs to establish the foundation for next-generation CAE systems.
Evolution of Kernels: Automated RISC-V Kernel Optimization with Large Language Models
Paper ↗
Abstract
Automated kernel design is critical for overcoming software ecosystem barriers in emerging hardware platforms like RISC-V. While large language models (LLMs) have shown promise for automated kernel optimization, demonstrating success in CUDA domains with comprehensive technical documents and mature codebases, their effectiveness remains unproven for reference-scarce domains like RISC-V. We present Evolution of Kernels (EoK), a novel LLM-based evolutionary program search framework that automates kernel design for domains with limited reference material. EoK mitigates reference scarcity by mining and formalizing reusable optimization ideas (general design principles + actionable thoughts) from established kernel libraries' development histories; it then guides parallel LLM explorations using these ideas, enriched via Retrieval-Augmented Generation (RAG) with RISC-V-specific context, prioritizing historically effective techniques. Empirically, EoK achieves a median 1.27x speedup, surpassing human experts on all 80 evaluated kernel design tasks and improving upon prior LLM-based automated kernel design methods by 20%. These results underscore the viability of incorporating human experience into emerging domains and highlight the immense potential of LLM-based automated kernel optimization.
Evolution of Kernels: Automated RISC-V Kernel Optimization with Large Language Models
Paper ↗
Abstract
Automated kernel design is critical for overcoming software ecosystem barriers in emerging hardware platforms like RISC-V. While large language models (LLMs) have shown promise for automated kernel optimization, demonstrating success in CUDA domains with comprehensive technical documents and mature codebases, their effectiveness remains unproven for reference-scarce domains like RISC-V. We present Evolution of Kernels (EoK), a novel LLM-based evolutionary program search framework that automates kernel design for domains with limited reference material. EoK mitigates reference scarcity by mining and formalizing reusable optimization ideas (general design principles + actionable thoughts) from established kernel libraries' development histories; it then guides parallel LLM explorations using these ideas, enriched via Retrieval-Augmented Generation (RAG) with RISC-V-specific context, prioritizing historically effective techniques. Empirically, EoK achieves a median 1.27x speedup, surpassing human experts on all 80 evaluated kernel design tasks and improving upon prior LLM-based automated kernel design methods by 20%. These results underscore the viability of incorporating human experience into emerging domains and highlight the immense potential of LLM-based automated kernel optimization.
Application of Machine Learning for Correcting Defect-induced Neuromorphic Circuit Inference Errors
Paper ↗
Abstract
This paper presents a machine learning-based approach to correct inference errors caused by stuck-at faults in fully analog ReRAM-based neuromorphic circuits. Using a Design-Technology Co-Optimization (DTCO) simulation framework, we model and analyze six spatial defect types-circular, circular-complement, ring, row, column, and checkerboard-across multiple layers of a multi-array neuromorphic architecture. We demonstrate that the proposed correction method, which employs a lightweight neural network trained on the circuit's output voltages, can recover up to 35% (from 55% to 90%) inference accuracy loss in defective scenarios. Our results, based on handwritten digit recognition tasks, show that even small corrective networks can significantly improve circuit robustness. This method offers a scalable and energy-efficient path toward enhanced yield and reliability for neuromorphic systems in edge and internet-of-things (IoTs) applications. In addition to correcting the specific defect types used during training, our method also demonstrates the ability to generalize-achieving reasonable accuracy when tested on different types of defects not seen during training. The framework can be readily extended to support real-time adaptive learning, enabling on-chip correction for dynamic or aging-induced fault profiles.
Application of Machine Learning for Correcting Defect-induced Neuromorphic Circuit Inference Errors
Paper ↗
Abstract
This paper presents a machine learning-based approach to correct inference errors caused by stuck-at faults in fully analog ReRAM-based neuromorphic circuits. Using a Design-Technology Co-Optimization (DTCO) simulation framework, we model and analyze six spatial defect types-circular, circular-complement, ring, row, column, and checkerboard-across multiple layers of a multi-array neuromorphic architecture. We demonstrate that the proposed correction method, which employs a lightweight neural network trained on the circuit's output voltages, can recover up to 35% (from 55% to 90%) inference accuracy loss in defective scenarios. Our results, based on handwritten digit recognition tasks, show that even small corrective networks can significantly improve circuit robustness. This method offers a scalable and energy-efficient path toward enhanced yield and reliability for neuromorphic systems in edge and internet-of-things (IoTs) applications. In addition to correcting the specific defect types used during training, our method also demonstrates the ability to generalize-achieving reasonable accuracy when tested on different types of defects not seen during training. The framework can be readily extended to support real-time adaptive learning, enabling on-chip correction for dynamic or aging-induced fault profiles.
BERT4beam: Large AI Model Enabled Generalized Beamforming Optimization
Paper ↗
Abstract
Artificial intelligence (AI) is anticipated to emerge as a pivotal enabler for the forthcoming sixth-generation (6G) wireless communication systems. However, current research efforts regarding large AI models for wireless communications primarily focus on fine-tuning pre-trained large language models (LLMs) for specific tasks. This paper investigates the large-scale AI model designed for beamforming optimization to adapt and generalize to diverse tasks defined by system utilities and scales. We propose a novel framework based on bidirectional encoder representations from transformers (BERT), termed BERT4beam. We aim to formulate the beamforming optimization problem as a token-level sequence learning task, perform tokenization of the channel state information, construct the BERT model, and conduct task-specific pre-training and fine-tuning strategies. Based on the framework, we propose two BERT-based approaches for single-task and multi-task beamforming optimization, respectively. Both approaches are generalizable for varying user scales. Moreover, the former can adapt to varying system utilities and antenna configurations by re-configuring the input and output module of the BERT model, while the latter, termed UBERT, can directly generalize to diverse tasks, due to a finer-grained tokenization strategy. Extensive simulation results demonstrate that the two proposed approaches can achieve near-optimal performance and outperform existing AI models across various beamforming optimization tasks, showcasing strong adaptability and generalizability.
BERT4beam: Large AI Model Enabled Generalized Beamforming Optimization
Paper ↗
Abstract
Artificial intelligence (AI) is anticipated to emerge as a pivotal enabler for the forthcoming sixth-generation (6G) wireless communication systems. However, current research efforts regarding large AI models for wireless communications primarily focus on fine-tuning pre-trained large language models (LLMs) for specific tasks. This paper investigates the large-scale AI model designed for beamforming optimization to adapt and generalize to diverse tasks defined by system utilities and scales. We propose a novel framework based on bidirectional encoder representations from transformers (BERT), termed BERT4beam. We aim to formulate the beamforming optimization problem as a token-level sequence learning task, perform tokenization of the channel state information, construct the BERT model, and conduct task-specific pre-training and fine-tuning strategies. Based on the framework, we propose two BERT-based approaches for single-task and multi-task beamforming optimization, respectively. Both approaches are generalizable for varying user scales. Moreover, the former can adapt to varying system utilities and antenna configurations by re-configuring the input and output module of the BERT model, while the latter, termed UBERT, can directly generalize to diverse tasks, due to a finer-grained tokenization strategy. Extensive simulation results demonstrate that the two proposed approaches can achieve near-optimal performance and outperform existing AI models across various beamforming optimization tasks, showcasing strong adaptability and generalizability.
Securing LLM-Generated Embedded Firmware through AI Agent-Driven Validation and Patching
Paper ↗
Abstract
Large Language Models (LLMs) show promise in generating firmware for embedded systems, but often introduce security flaws and fail to meet real-time performance constraints. This paper proposes a three-phase methodology that combines LLM-based firmware generation with automated security validation and iterative refinement in a virtualized environment. Using structured prompts, models like GPT-4 generate firmware for networking and control tasks, deployed on FreeRTOS via QEMU. These implementations are tested using fuzzing, static analysis, and runtime monitoring to detect vulnerabilities such as buffer overflows (CWE-120), race conditions (CWE-362), and denial-of-service threats (CWE-400). Specialized AI agents for Threat Detection, Performance Optimization, and Compliance Verification collaborate to improve detection and remediation. Identified issues are categorized using CWE, then used to prompt targeted LLM-generated patches in an iterative loop. Experiments show a 92.4\% Vulnerability Remediation Rate (37.3\% improvement), 95.8\% Threat Model Compliance, and 0.87 Security Coverage Index. Real-time metrics include 8.6ms worst-case execution time and 195{\mu}s jitter. This process enhances firmware security and performance while contributing an open-source dataset for future research.
Securing LLM-Generated Embedded Firmware through AI Agent-Driven Validation and Patching
Paper ↗
Abstract
Large Language Models (LLMs) show promise in generating firmware for embedded systems, but often introduce security flaws and fail to meet real-time performance constraints. This paper proposes a three-phase methodology that combines LLM-based firmware generation with automated security validation and iterative refinement in a virtualized environment. Using structured prompts, models like GPT-4 generate firmware for networking and control tasks, deployed on FreeRTOS via QEMU. These implementations are tested using fuzzing, static analysis, and runtime monitoring to detect vulnerabilities such as buffer overflows (CWE-120), race conditions (CWE-362), and denial-of-service threats (CWE-400). Specialized AI agents for Threat Detection, Performance Optimization, and Compliance Verification collaborate to improve detection and remediation. Identified issues are categorized using CWE, then used to prompt targeted LLM-generated patches in an iterative loop. Experiments show a 92.4\% Vulnerability Remediation Rate (37.3\% improvement), 95.8\% Threat Model Compliance, and 0.87 Security Coverage Index. Real-time metrics include 8.6ms worst-case execution time and 195{\mu}s jitter. This process enhances firmware security and performance while contributing an open-source dataset for future research.
AutoVeriFix: Automatically Correcting Errors and Enhancing Functional Correctness in LLM-Generated Verilog Code
Paper ↗
Abstract
Large language models (LLMs) have demonstrated impressive capabilities in generating software code for high-level programming languages such as Python and C++. However, their application to hardware description languages, such as Verilog, is challenging due to the scarcity of high-quality training data. Current approaches to Verilog code generation using LLMs often focus on syntactic correctness, resulting in code with functional errors. To address these challenges, we present AutoVeriFix, a novel Python-assisted two-stage framework designed to enhance the functional correctness of LLM-generated Verilog code. In the first stage, LLMs are employed to generate high-level Python reference models that define the intended circuit behavior. In the second stage, these Python models facilitate the creation of automated tests that guide the generation of Verilog RTL implementations. Simulation discrepancies between the reference model and the Verilog code are iteratively used to identify and correct errors, thereby improving the functional accuracy and reliability of the LLM-generated Verilog code. Experimental results demonstrate that our approach significantly outperforms existing state-of-the-art methods in improving the functional correctness of generated Verilog code.
AutoVeriFix: Automatically Correcting Errors and Enhancing Functional Correctness in LLM-Generated Verilog Code
Paper ↗
Abstract
Large language models (LLMs) have demonstrated impressive capabilities in generating software code for high-level programming languages such as Python and C++. However, their application to hardware description languages, such as Verilog, is challenging due to the scarcity of high-quality training data. Current approaches to Verilog code generation using LLMs often focus on syntactic correctness, resulting in code with functional errors. To address these challenges, we present AutoVeriFix, a novel Python-assisted two-stage framework designed to enhance the functional correctness of LLM-generated Verilog code. In the first stage, LLMs are employed to generate high-level Python reference models that define the intended circuit behavior. In the second stage, these Python models facilitate the creation of automated tests that guide the generation of Verilog RTL implementations. Simulation discrepancies between the reference model and the Verilog code are iteratively used to identify and correct errors, thereby improving the functional accuracy and reliability of the LLM-generated Verilog code. Experimental results demonstrate that our approach significantly outperforms existing state-of-the-art methods in improving the functional correctness of generated Verilog code.
LLM-Guided Ansätze Design for Quantum Circuit Born Machines in Financial Generative Modeling
Paper ↗
Abstract
Quantum generative modeling using quantum circuit Born machines (QCBMs) shows promising potential for practical quantum advantage. However, discovering ans\"atze that are both expressive and hardware-efficient remains a key challenge, particularly on noisy intermediate-scale quantum (NISQ) devices. In this work, we introduce a prompt-based framework that leverages large language models (LLMs) to generate hardware-aware QCBM architectures. Prompts are conditioned on qubit connectivity, gate error rates, and hardware topology, while iterative feedback, including Kullback-Leibler (KL) divergence, circuit depth, and validity, is used to refine the circuits. We evaluate our method on a financial modeling task involving daily changes in Japanese government bond (JGB) interest rates. Our results show that the LLM-generated ans\"atze are significantly shallower and achieve superior generative performance compared to the standard baseline when executed on real IBM quantum hardware using 12 qubits. These findings demonstrate the practical utility of LLM-driven quantum architecture search and highlight a promising path toward robust, deployable generative models for near-term quantum devices.
LLM-Guided Ansätze Design for Quantum Circuit Born Machines in Financial Generative Modeling
Paper ↗
Abstract
Quantum generative modeling using quantum circuit Born machines (QCBMs) shows promising potential for practical quantum advantage. However, discovering ans\"atze that are both expressive and hardware-efficient remains a key challenge, particularly on noisy intermediate-scale quantum (NISQ) devices. In this work, we introduce a prompt-based framework that leverages large language models (LLMs) to generate hardware-aware QCBM architectures. Prompts are conditioned on qubit connectivity, gate error rates, and hardware topology, while iterative feedback, including Kullback-Leibler (KL) divergence, circuit depth, and validity, is used to refine the circuits. We evaluate our method on a financial modeling task involving daily changes in Japanese government bond (JGB) interest rates. Our results show that the LLM-generated ans\"atze are significantly shallower and achieve superior generative performance compared to the standard baseline when executed on real IBM quantum hardware using 12 qubits. These findings demonstrate the practical utility of LLM-driven quantum architecture search and highlight a promising path toward robust, deployable generative models for near-term quantum devices.
Astra: A Multi-Agent System for GPU Kernel Performance Optimization
Paper ↗
Abstract
GPU kernel optimization has long been a central challenge at the intersection of high-performance computing and machine learning. Efficient kernels are crucial for accelerating large language model (LLM) training and serving, yet attaining high performance typically requires extensive manual tuning. Compiler-based systems reduce some of this burden, but still demand substantial manual design and engineering effort. Recently, researchers have explored using LLMs for GPU kernel generation, though prior work has largely focused on translating high-level PyTorch modules into CUDA code. In this work, we introduce Astra, the first LLM-based multi-agent system for GPU kernel optimization. Unlike previous approaches, Astra starts from existing CUDA implementations extracted from SGLang, a widely deployed framework for serving LLMs, rather than treating PyTorch modules as the specification. Within Astra, specialized LLM agents collaborate through iterative code generation, testing, profiling, and planning to produce kernels that are both correct and high-performance. On kernels from SGLang, Astra achieves an average speedup of 1.32x using zero-shot prompting with OpenAI o4-mini. A detailed case study further demonstrates that LLMs can autonomously apply loop transformations, optimize memory access patterns, exploit CUDA intrinsics, and leverage fast math operations to yield substantial performance gains. Our work highlights multi-agent LLM systems as a promising new paradigm for GPU kernel optimization.
Astra: A Multi-Agent System for GPU Kernel Performance Optimization
Paper ↗
Abstract
GPU kernel optimization has long been a central challenge at the intersection of high-performance computing and machine learning. Efficient kernels are crucial for accelerating large language model (LLM) training and serving, yet attaining high performance typically requires extensive manual tuning. Compiler-based systems reduce some of this burden, but still demand substantial manual design and engineering effort. Recently, researchers have explored using LLMs for GPU kernel generation, though prior work has largely focused on translating high-level PyTorch modules into CUDA code. In this work, we introduce Astra, the first LLM-based multi-agent system for GPU kernel optimization. Unlike previous approaches, Astra starts from existing CUDA implementations extracted from SGLang, a widely deployed framework for serving LLMs, rather than treating PyTorch modules as the specification. Within Astra, specialized LLM agents collaborate through iterative code generation, testing, profiling, and planning to produce kernels that are both correct and high-performance. On kernels from SGLang, Astra achieves an average speedup of 1.32x using zero-shot prompting with OpenAI o4-mini. A detailed case study further demonstrates that LLMs can autonomously apply loop transformations, optimize memory access patterns, exploit CUDA intrinsics, and leverage fast math operations to yield substantial performance gains. Our work highlights multi-agent LLM systems as a promising new paradigm for GPU kernel optimization.
Constraint-Compliant Network Optimization through Large Language Models
Paper ↗
Abstract
This work develops an LLM-based optimization framework ensuring strict constraint satisfaction in network optimization. While LLMs possess contextual reasoning capabilities, existing approaches often fail to enforce constraints, causing infeasible solutions. Unlike conventional methods that address average constraints, the proposed framework integrates a natural language-based input encoding strategy to restrict the solution space and guarantee feasibility. For multi-access edge computing networks, task allocation is optimized while minimizing worst-case latency. Numerical evaluations demonstrate LLMs as a promising tool for constraint-aware network optimization, offering insights into their inference capabilities.
Constraint-Compliant Network Optimization through Large Language Models
Paper ↗
Abstract
This work develops an LLM-based optimization framework ensuring strict constraint satisfaction in network optimization. While LLMs possess contextual reasoning capabilities, existing approaches often fail to enforce constraints, causing infeasible solutions. Unlike conventional methods that address average constraints, the proposed framework integrates a natural language-based input encoding strategy to restrict the solution space and guarantee feasibility. For multi-access edge computing networks, task allocation is optimized while minimizing worst-case latency. Numerical evaluations demonstrate LLMs as a promising tool for constraint-aware network optimization, offering insights into their inference capabilities.
MCTuner: Spatial Decomposition-Enhanced Database Tuning via LLM-Guided Exploration
Paper ↗
Abstract
Database knob tuning is essential for optimizing the performance of modern database management systems, which often expose hundreds of knobs with continuous or categorical values. However, the large number of knobs and the vast configuration space make it difficult to identify optimal settings efficiently. Although learning-based tuning has shown promise, existing approaches either ignore domain knowledge by relying solely on benchmark feedback or struggle to explore the high-dimensional knob space, resulting in high tuning costs and suboptimal performance. To address these challenges, we propose MCTuner, an adaptive knob tuning framework that minimizes exploration in ineffective regions of the configuration space. MCTuner employs a Mixture-of-Experts (MoE) mechanism with specialized LLMs to identify performance-critical knobs. In further, MCTuner introduces the first spatial decomposition algorithm that recursively partitions the space into hierarchical subspaces, on which Bayesian Optimization is performed to efficiently search for near-optimal configurations. Evaluated on different benchmarks (OLAP, OLTP, and HTAP), MCTuner achieves up to 19.2% performance gains and 1.4x faster configuration discovery per iteration compared to state-of-the-art methods.
MCTuner: Spatial Decomposition-Enhanced Database Tuning via LLM-Guided Exploration
Paper ↗
Abstract
Database knob tuning is essential for optimizing the performance of modern database management systems, which often expose hundreds of knobs with continuous or categorical values. However, the large number of knobs and the vast configuration space make it difficult to identify optimal settings efficiently. Although learning-based tuning has shown promise, existing approaches either ignore domain knowledge by relying solely on benchmark feedback or struggle to explore the high-dimensional knob space, resulting in high tuning costs and suboptimal performance. To address these challenges, we propose MCTuner, an adaptive knob tuning framework that minimizes exploration in ineffective regions of the configuration space. MCTuner employs a Mixture-of-Experts (MoE) mechanism with specialized LLMs to identify performance-critical knobs. In further, MCTuner introduces the first spatial decomposition algorithm that recursively partitions the space into hierarchical subspaces, on which Bayesian Optimization is performed to efficiently search for near-optimal configurations. Evaluated on different benchmarks (OLAP, OLTP, and HTAP), MCTuner achieves up to 19.2% performance gains and 1.4x faster configuration discovery per iteration compared to state-of-the-art methods.
A Spatio-Temporal Graph Neural Networks Approach for Predicting Silent Data Corruption inducing Circuit-Level Faults
Paper ↗
Abstract
Silent Data Errors (SDEs) from time-zero defects and aging degrade safety-critical systems. Functional testing detects SDE-related faults but is expensive to simulate. We present a unified spatio-temporal graph convolutional network (ST-GCN) for fast, accurate prediction of long-cycle fault impact probabilities (FIPs) in large sequential circuits, supporting quantitative risk assessment. Gate-level netlists are modeled as spatio-temporal graphs to capture topology and signal timing; dedicated spatial and temporal encoders predict multi-cycle FIPs efficiently. On ISCAS-89 benchmarks, the method reduces simulation time by more than 10x while maintaining high accuracy (mean absolute error 0.024 for 5-cycle predictions). The framework accepts features from testability metrics or fault simulation, allowing efficiency-accuracy trade-offs. A test-point selection study shows that choosing observation points by predicted FIPs improves detection of long-cycle, hard-to-detect faults. The approach scales to SoC-level test strategy optimization and fits downstream electronic design automation flows.
A Spatio-Temporal Graph Neural Networks Approach for Predicting Silent Data Corruption inducing Circuit-Level Faults
Paper ↗
Abstract
Silent Data Errors (SDEs) from time-zero defects and aging degrade safety-critical systems. Functional testing detects SDE-related faults but is expensive to simulate. We present a unified spatio-temporal graph convolutional network (ST-GCN) for fast, accurate prediction of long-cycle fault impact probabilities (FIPs) in large sequential circuits, supporting quantitative risk assessment. Gate-level netlists are modeled as spatio-temporal graphs to capture topology and signal timing; dedicated spatial and temporal encoders predict multi-cycle FIPs efficiently. On ISCAS-89 benchmarks, the method reduces simulation time by more than 10x while maintaining high accuracy (mean absolute error 0.024 for 5-cycle predictions). The framework accepts features from testability metrics or fault simulation, allowing efficiency-accuracy trade-offs. A test-point selection study shows that choosing observation points by predicted FIPs improves detection of long-cycle, hard-to-detect faults. The approach scales to SoC-level test strategy optimization and fits downstream electronic design automation flows.
Proof2Silicon: Prompt Repair for Verified Code and Hardware Generation via Reinforcement Learning
Paper ↗
Abstract
Large Language Models (LLMs) have demonstrated impressive capabilities in automated code generation but frequently produce code that fails formal verification, an essential requirement for hardware and safety-critical domains. To overcome this fundamental limitation, we previously proposed PREFACE, a model-agnostic framework based on reinforcement learning (RL) that iteratively repairs the prompts provided to frozen LLMs, systematically steering them toward generating formally verifiable Dafny code without costly fine-tuning. This work presents Proof2Silicon, a novel end-to-end synthesis framework that embeds the previously proposed PREFACE flow to enable the generation of correctness-by-construction hardware directly from natural language specifications. Proof2Silicon operates by: (1) leveraging PREFACE's verifier-driven RL agent to optimize prompt generation iteratively, ensuring Dafny code correctness; (2) automatically translating verified Dafny programs into synthesizable high-level C using Dafny's Python backend and PyLog; and (3) employing Vivado HLS to produce RTL implementations. Evaluated rigorously on a challenging 100-task benchmark, PREFACE's RL-guided prompt optimization consistently improved Dafny verification success rates across diverse LLMs by up to 21%. Crucially, Proof2Silicon achieved an end-to-end hardware synthesis success rate of up to 72%, generating RTL designs through Vivado HLS synthesis flows. These results demonstrate a robust, scalable, and automated pipeline for LLM-driven, formally verified hardware synthesis, bridging natural-language specification and silicon realization.
Proof2Silicon: Prompt Repair for Verified Code and Hardware Generation via Reinforcement Learning
Paper ↗
Abstract
Large Language Models (LLMs) have demonstrated impressive capabilities in automated code generation but frequently produce code that fails formal verification, an essential requirement for hardware and safety-critical domains. To overcome this fundamental limitation, we previously proposed PREFACE, a model-agnostic framework based on reinforcement learning (RL) that iteratively repairs the prompts provided to frozen LLMs, systematically steering them toward generating formally verifiable Dafny code without costly fine-tuning. This work presents Proof2Silicon, a novel end-to-end synthesis framework that embeds the previously proposed PREFACE flow to enable the generation of correctness-by-construction hardware directly from natural language specifications. Proof2Silicon operates by: (1) leveraging PREFACE's verifier-driven RL agent to optimize prompt generation iteratively, ensuring Dafny code correctness; (2) automatically translating verified Dafny programs into synthesizable high-level C using Dafny's Python backend and PyLog; and (3) employing Vivado HLS to produce RTL implementations. Evaluated rigorously on a challenging 100-task benchmark, PREFACE's RL-guided prompt optimization consistently improved Dafny verification success rates across diverse LLMs by up to 21%. Crucially, Proof2Silicon achieved an end-to-end hardware synthesis success rate of up to 72%, generating RTL designs through Vivado HLS synthesis flows. These results demonstrate a robust, scalable, and automated pipeline for LLM-driven, formally verified hardware synthesis, bridging natural-language specification and silicon realization.
Large Language Models for Next-Generation Wireless Network Management: A Survey and Tutorial
Paper ↗
Abstract
The rapid advancement toward sixth-generation (6G) wireless networks has significantly intensified the complexity and scale of optimization problems, including resource allocation and trajectory design, often formulated as combinatorial problems in large discrete decision spaces. However, traditional optimization methods, such as heuristics and deep reinforcement learning (DRL), struggle to meet the demanding requirements of real-time adaptability, scalability, and dynamic handling of user intents in increasingly heterogeneous and resource-constrained network environments. Large language models (LLMs) present a transformative paradigm by enabling natural language-driven problem formulation, context-aware reasoning, and adaptive solution refinement through advanced semantic understanding and structured reasoning capabilities. This paper provides a systematic and comprehensive survey of LLM-enabled optimization frameworks tailored for wireless networks. We first introduce foundational design concepts and distinguish LLM-enabled methods from conventional optimization paradigms. Subsequently, we critically analyze key enabling methodologies, including natural language modeling, solver collaboration, and solution verification processes. Moreover, we explore representative case studies to demonstrate LLMs' transformative potential in practical scenarios such as optimization formulation, low-altitude economy networking, and intent networking. Finally, we discuss current research challenges, examine prominent open-source frameworks and datasets, and identify promising future directions to facilitate robust, scalable, and trustworthy LLM-enabled optimization solutions for next-generation wireless networks.
Large Language Models for Next-Generation Wireless Network Management: A Survey and Tutorial
Paper ↗
Abstract
The rapid advancement toward sixth-generation (6G) wireless networks has significantly intensified the complexity and scale of optimization problems, including resource allocation and trajectory design, often formulated as combinatorial problems in large discrete decision spaces. However, traditional optimization methods, such as heuristics and deep reinforcement learning (DRL), struggle to meet the demanding requirements of real-time adaptability, scalability, and dynamic handling of user intents in increasingly heterogeneous and resource-constrained network environments. Large language models (LLMs) present a transformative paradigm by enabling natural language-driven problem formulation, context-aware reasoning, and adaptive solution refinement through advanced semantic understanding and structured reasoning capabilities. This paper provides a systematic and comprehensive survey of LLM-enabled optimization frameworks tailored for wireless networks. We first introduce foundational design concepts and distinguish LLM-enabled methods from conventional optimization paradigms. Subsequently, we critically analyze key enabling methodologies, including natural language modeling, solver collaboration, and solution verification processes. Moreover, we explore representative case studies to demonstrate LLMs' transformative potential in practical scenarios such as optimization formulation, low-altitude economy networking, and intent networking. Finally, we discuss current research challenges, examine prominent open-source frameworks and datasets, and identify promising future directions to facilitate robust, scalable, and trustworthy LLM-enabled optimization solutions for next-generation wireless networks.
Revolution or Hype? Seeking the Limits of Large Models in Hardware Design
Paper ↗
Abstract
Recent breakthroughs in Large Language Models (LLMs) and Large Circuit Models (LCMs) have sparked excitement across the electronic design automation (EDA) community, promising a revolution in circuit design and optimization. Yet, this excitement is met with significant skepticism: Are these AI models a genuine revolution in circuit design, or a temporary wave of inflated expectations? This paper serves as a foundational text for the corresponding ICCAD 2025 panel, bringing together perspectives from leading experts in academia and industry. It critically examines the practical capabilities, fundamental limitations, and future prospects of large AI models in hardware design. The paper synthesizes the core arguments surrounding reliability, scalability, and interpretability, framing the debate on whether these models can meaningfully outperform or complement traditional EDA methods. The result is an authoritative overview offering fresh insights into one of today's most contentious and impactful technology trends.
Revolution or Hype? Seeking the Limits of Large Models in Hardware Design
Paper ↗
Abstract
Recent breakthroughs in Large Language Models (LLMs) and Large Circuit Models (LCMs) have sparked excitement across the electronic design automation (EDA) community, promising a revolution in circuit design and optimization. Yet, this excitement is met with significant skepticism: Are these AI models a genuine revolution in circuit design, or a temporary wave of inflated expectations? This paper serves as a foundational text for the corresponding ICCAD 2025 panel, bringing together perspectives from leading experts in academia and industry. It critically examines the practical capabilities, fundamental limitations, and future prospects of large AI models in hardware design. The paper synthesizes the core arguments surrounding reliability, scalability, and interpretability, framing the debate on whether these models can meaningfully outperform or complement traditional EDA methods. The result is an authoritative overview offering fresh insights into one of today's most contentious and impactful technology trends.
KubeGuard: LLM-Assisted Kubernetes Hardening via Configuration Files and Runtime Logs Analysis
Paper ↗
Abstract
The widespread adoption of Kubernetes (K8s) for orchestrating cloud-native applications has introduced significant security challenges, such as misconfigured resources and overly permissive configurations. Failing to address these issues can result in unauthorized access, privilege escalation, and lateral movement within clusters. Most existing K8s security solutions focus on detecting misconfigurations, typically through static analysis or anomaly detection. In contrast, this paper presents KubeGuard, a novel runtime log-driven recommender framework aimed at mitigating risks by addressing overly permissive configurations. KubeGuard is designed to harden K8s environments through two complementary tasks: Resource Creation and Resource Refinement. It leverages large language models (LLMs) to analyze manifests and runtime logs reflecting actual system behavior, using modular prompt-chaining workflows. This approach enables KubeGuard to create least-privilege configurations for new resources and refine existing manifests to reduce the attack surface. KubeGuard's output manifests are presented as recommendations that users (e.g., developers and operators) can review and adopt to enhance cluster security. Our evaluation demonstrates that KubeGuard effectively generates and refines K8s manifests for Roles, NetworkPolicies, and Deployments, leveraging both proprietary and open-source LLMs. The high precision, recall, and F1-scores affirm KubeGuard's practicality as a framework that translates runtime observability into actionable, least-privilege configuration guidance.
KubeGuard: LLM-Assisted Kubernetes Hardening via Configuration Files and Runtime Logs Analysis
Paper ↗
Abstract
The widespread adoption of Kubernetes (K8s) for orchestrating cloud-native applications has introduced significant security challenges, such as misconfigured resources and overly permissive configurations. Failing to address these issues can result in unauthorized access, privilege escalation, and lateral movement within clusters. Most existing K8s security solutions focus on detecting misconfigurations, typically through static analysis or anomaly detection. In contrast, this paper presents KubeGuard, a novel runtime log-driven recommender framework aimed at mitigating risks by addressing overly permissive configurations. KubeGuard is designed to harden K8s environments through two complementary tasks: Resource Creation and Resource Refinement. It leverages large language models (LLMs) to analyze manifests and runtime logs reflecting actual system behavior, using modular prompt-chaining workflows. This approach enables KubeGuard to create least-privilege configurations for new resources and refine existing manifests to reduce the attack surface. KubeGuard's output manifests are presented as recommendations that users (e.g., developers and operators) can review and adopt to enhance cluster security. Our evaluation demonstrates that KubeGuard effectively generates and refines K8s manifests for Roles, NetworkPolicies, and Deployments, leveraging both proprietary and open-source LLMs. The high precision, recall, and F1-scores affirm KubeGuard's practicality as a framework that translates runtime observability into actionable, least-privilege configuration guidance.
AutoPBO: LLM-powered Optimization for Local Search PBO Solvers
Paper ↗
Abstract
Pseudo-Boolean Optimization (PBO) provides a powerful framework for modeling combinatorial problems through pseudo-Boolean (PB) constraints. Local search solvers have shown excellent performance in PBO solving, and their efficiency is highly dependent on their internal heuristics to guide the search. Still, their design often requires significant expert effort and manual tuning in practice. While Large Language Models (LLMs) have demonstrated potential in automating algorithm design, their application to optimizing PBO solvers remains unexplored. In this work, we introduce AutoPBO, a novel LLM-powered framework to automatically enhance PBO local search solvers. We conduct experiments on a broad range of four public benchmarks, including one real-world benchmark, a benchmark from PB competition, an integer linear programming optimization benchmark, and a crafted combinatorial benchmark, to evaluate the performance improvement achieved by AutoPBO and compare it with six state-of-the-art competitors, including two local search PBO solvers NuPBO and OraSLS, two complete PB solvers PBO-IHS and RoundingSat, and two mixed integer programming (MIP) solvers Gurobi and SCIP. AutoPBO demonstrates significant improvements over previous local search approaches, while maintaining competitive performance compared to state-of-the-art competitors. The results suggest that AutoPBO offers a promising approach to automating local search solver design.
AutoPBO: LLM-powered Optimization for Local Search PBO Solvers
Paper ↗
Abstract
Pseudo-Boolean Optimization (PBO) provides a powerful framework for modeling combinatorial problems through pseudo-Boolean (PB) constraints. Local search solvers have shown excellent performance in PBO solving, and their efficiency is highly dependent on their internal heuristics to guide the search. Still, their design often requires significant expert effort and manual tuning in practice. While Large Language Models (LLMs) have demonstrated potential in automating algorithm design, their application to optimizing PBO solvers remains unexplored. In this work, we introduce AutoPBO, a novel LLM-powered framework to automatically enhance PBO local search solvers. We conduct experiments on a broad range of four public benchmarks, including one real-world benchmark, a benchmark from PB competition, an integer linear programming optimization benchmark, and a crafted combinatorial benchmark, to evaluate the performance improvement achieved by AutoPBO and compare it with six state-of-the-art competitors, including two local search PBO solvers NuPBO and OraSLS, two complete PB solvers PBO-IHS and RoundingSat, and two mixed integer programming (MIP) solvers Gurobi and SCIP. AutoPBO demonstrates significant improvements over previous local search approaches, while maintaining competitive performance compared to state-of-the-art competitors. The results suggest that AutoPBO offers a promising approach to automating local search solver design.
INGRID: Intelligent Generative Robotic Design Using Large Language Models
Paper ↗
Abstract
The integration of large language models (LLMs) into robotic systems has accelerated progress in embodied artificial intelligence, yet current approaches remain constrained by existing robotic architectures, particularly serial mechanisms. This hardware dependency fundamentally limits the scope of robotic intelligence. Here, we present INGRID (Intelligent Generative Robotic Design), a framework that enables the automated design of parallel robotic mechanisms through deep integration with reciprocal screw theory and kinematic synthesis methods. We decompose the design challenge into four progressive tasks: constraint analysis, kinematic joint generation, chain construction, and complete mechanism design. INGRID demonstrates the ability to generate novel parallel mechanisms with both fixed and variable mobility, discovering kinematic configurations not previously documented in the literature. We validate our approach through three case studies demonstrating how INGRID assists users in designing task-specific parallel robots based on desired mobility requirements. By bridging the gap between mechanism theory and machine learning, INGRID enables researchers without specialized robotics training to create custom parallel mechanisms, thereby decoupling advances in robotic intelligence from hardware constraints. This work establishes a foundation for mechanism intelligence, where AI systems actively design robotic hardware, potentially transforming the development of embodied AI systems.
INGRID: Intelligent Generative Robotic Design Using Large Language Models
Paper ↗
Abstract
The integration of large language models (LLMs) into robotic systems has accelerated progress in embodied artificial intelligence, yet current approaches remain constrained by existing robotic architectures, particularly serial mechanisms. This hardware dependency fundamentally limits the scope of robotic intelligence. Here, we present INGRID (Intelligent Generative Robotic Design), a framework that enables the automated design of parallel robotic mechanisms through deep integration with reciprocal screw theory and kinematic synthesis methods. We decompose the design challenge into four progressive tasks: constraint analysis, kinematic joint generation, chain construction, and complete mechanism design. INGRID demonstrates the ability to generate novel parallel mechanisms with both fixed and variable mobility, discovering kinematic configurations not previously documented in the literature. We validate our approach through three case studies demonstrating how INGRID assists users in designing task-specific parallel robots based on desired mobility requirements. By bridging the gap between mechanism theory and machine learning, INGRID enables researchers without specialized robotics training to create custom parallel mechanisms, thereby decoupling advances in robotic intelligence from hardware constraints. This work establishes a foundation for mechanism intelligence, where AI systems actively design robotic hardware, potentially transforming the development of embodied AI systems.
Human-LLM Synergy in Context-Aware Adaptive Architecture for Scalable Drone Swarm Operation
Paper ↗
Abstract
The deployment of autonomous drone swarms in disaster response missions necessitates the development of flexible, scalable, and robust coordination systems. Traditional fixed architectures struggle to cope with dynamic and unpredictable environments, leading to inefficiencies in energy consumption and connectivity. This paper addresses this gap by proposing an adaptive architecture for drone swarms, leveraging a Large Language Model to dynamically select the optimal architecture as centralized, hierarchical, or holonic based on real time mission parameters such as task complexity, swarm size, and communication stability. Our system addresses the challenges of scalability, adaptability, and robustness,ensuring efficient energy consumption and maintaining connectivity under varying conditions. Extensive simulations demonstrate that our adaptive architecture outperforms traditional static models in terms of scalability, energy efficiency, and connectivity. These results highlight the potential of our approach to provide a scalable, adaptable, and resilient solution for real world disaster response scenarios.
Human-LLM Synergy in Context-Aware Adaptive Architecture for Scalable Drone Swarm Operation
Paper ↗
Abstract
The deployment of autonomous drone swarms in disaster response missions necessitates the development of flexible, scalable, and robust coordination systems. Traditional fixed architectures struggle to cope with dynamic and unpredictable environments, leading to inefficiencies in energy consumption and connectivity. This paper addresses this gap by proposing an adaptive architecture for drone swarms, leveraging a Large Language Model to dynamically select the optimal architecture as centralized, hierarchical, or holonic based on real time mission parameters such as task complexity, swarm size, and communication stability. Our system addresses the challenges of scalability, adaptability, and robustness,ensuring efficient energy consumption and maintaining connectivity under varying conditions. Extensive simulations demonstrate that our adaptive architecture outperforms traditional static models in terms of scalability, energy efficiency, and connectivity. These results highlight the potential of our approach to provide a scalable, adaptable, and resilient solution for real world disaster response scenarios.
A Multi-stage Error Diagnosis for APB Transaction
Paper ↗
Abstract
Functional verification and debugging are critical bottlenecks in modern System-on-Chip (SoC) design, with manual detection of Advanced Peripheral Bus (APB) transaction errors in large Value Change Dump (VCD) files being inefficient and error-prone. Addressing the 2025 ICCAD Contest Problem D, this study proposes an automated error diagnosis framework using a hierarchical Random Forest-based architecture. The multi-stage error diagnosis employs four pre-trained binary classifiers to sequentially detect Out-of-Range Access, Address Corruption, and Data Corruption errors, prioritizing high-certainty address-related faults before tackling complex data errors to enhance efficiency. Experimental results show an overall accuracy of 91.36%, with near-perfect precision and recall for address errors and robust performance for data errors. Although the final results of the ICCAD 2025 CAD Contest are yet to be announced as of the submission date, our team achieved first place in the beta stage, highlighting the method's competitive strength. This research validates the potential of hierarchical machine learning as a powerful automated tool for hardware debugging in Electronic Design Automation (EDA).
A Multi-stage Error Diagnosis for APB Transaction
Paper ↗
Abstract
Functional verification and debugging are critical bottlenecks in modern System-on-Chip (SoC) design, with manual detection of Advanced Peripheral Bus (APB) transaction errors in large Value Change Dump (VCD) files being inefficient and error-prone. Addressing the 2025 ICCAD Contest Problem D, this study proposes an automated error diagnosis framework using a hierarchical Random Forest-based architecture. The multi-stage error diagnosis employs four pre-trained binary classifiers to sequentially detect Out-of-Range Access, Address Corruption, and Data Corruption errors, prioritizing high-certainty address-related faults before tackling complex data errors to enhance efficiency. Experimental results show an overall accuracy of 91.36%, with near-perfect precision and recall for address errors and robust performance for data errors. Although the final results of the ICCAD 2025 CAD Contest are yet to be announced as of the submission date, our team achieved first place in the beta stage, highlighting the method's competitive strength. This research validates the potential of hierarchical machine learning as a powerful automated tool for hardware debugging in Electronic Design Automation (EDA).
GridMind: LLMs-Powered Agents for Power System Analysis and Operations
Paper ↗
Abstract
The complexity of traditional power system analysis workflows presents significant barriers to efficient decision-making in modern electric grids. This paper presents GridMind, a multi-agent AI system that integrates Large Language Models (LLMs) with deterministic engineering solvers to enable conversational scientific computing for power system analysis. The system employs specialized agents coordinating AC Optimal Power Flow and N-1 contingency analysis through natural language interfaces while maintaining numerical precision via function calls. GridMind addresses workflow integration, knowledge accessibility, context preservation, and expert decision-support augmentation. Experimental evaluation on IEEE test cases demonstrates that the proposed agentic framework consistently delivers correct solutions across all tested language models, with smaller LLMs achieving comparable analytical accuracy with reduced computational latency. This work establishes agentic AI as a viable paradigm for scientific computing, demonstrating how conversational interfaces can enhance accessibility while preserving numerical rigor essential for critical engineering applications.
GridMind: LLMs-Powered Agents for Power System Analysis and Operations
Paper ↗
Abstract
The complexity of traditional power system analysis workflows presents significant barriers to efficient decision-making in modern electric grids. This paper presents GridMind, a multi-agent AI system that integrates Large Language Models (LLMs) with deterministic engineering solvers to enable conversational scientific computing for power system analysis. The system employs specialized agents coordinating AC Optimal Power Flow and N-1 contingency analysis through natural language interfaces while maintaining numerical precision via function calls. GridMind addresses workflow integration, knowledge accessibility, context preservation, and expert decision-support augmentation. Experimental evaluation on IEEE test cases demonstrates that the proposed agentic framework consistently delivers correct solutions across all tested language models, with smaller LLMs achieving comparable analytical accuracy with reduced computational latency. This work establishes agentic AI as a viable paradigm for scientific computing, demonstrating how conversational interfaces can enhance accessibility while preserving numerical rigor essential for critical engineering applications.
Real-time ML-based Defense Against Malicious Payload in Reconfigurable Embedded Systems
Paper ↗
Abstract
The growing use of FPGAs in reconfigurable systems introducessecurity risks through malicious bitstreams that could cause denial-of-service (DoS), data leakage, or covert attacks. We investigated chip-level hardware malicious payload in embedded systems and proposed a supervised machine learning method to detect malicious bitstreams via static byte-level features. Our approach diverges from existing methods by analyzing bitstreams directly at the binary level, enabling real-time detection without requiring access to source code or netlists. Bitstreams were sourced from state-of-the-art (SOTA) benchmarks and re-engineered to target the Xilinx PYNQ-Z1 FPGA Development Board. Our dataset included 122 samples of benign and malicious configurations. The data were vectorized using byte frequency analysis, compressed using TSVD, and balanced using SMOTE to address class imbalance. The evaluated classifiers demonstrated that Random Forest achieved a macro F1-score of 0.97, underscoring the viability of real-time Trojan detection on resource-constrained systems. The final model was serialized and successfully deployed via PYNQ to enable integrated bitstream analysis.
Real-time ML-based Defense Against Malicious Payload in Reconfigurable Embedded Systems
Paper ↗
Abstract
The growing use of FPGAs in reconfigurable systems introducessecurity risks through malicious bitstreams that could cause denial-of-service (DoS), data leakage, or covert attacks. We investigated chip-level hardware malicious payload in embedded systems and proposed a supervised machine learning method to detect malicious bitstreams via static byte-level features. Our approach diverges from existing methods by analyzing bitstreams directly at the binary level, enabling real-time detection without requiring access to source code or netlists. Bitstreams were sourced from state-of-the-art (SOTA) benchmarks and re-engineered to target the Xilinx PYNQ-Z1 FPGA Development Board. Our dataset included 122 samples of benign and malicious configurations. The data were vectorized using byte frequency analysis, compressed using TSVD, and balanced using SMOTE to address class imbalance. The evaluated classifiers demonstrated that Random Forest achieved a macro F1-score of 0.97, underscoring the viability of real-time Trojan detection on resource-constrained systems. The final model was serialized and successfully deployed via PYNQ to enable integrated bitstream analysis.
Nano Machine Intelligence: From a Communication Perspective
Paper ↗
Abstract
We present an AI-integrated molecular communication link validated on a benchtop nanomachine testbed representative of subdermal implants. The system employs an indium-gallium-zinc-oxide electrolyte-gated FET (IGZO-EGFET) functionalized with glucose oxidase as a biocompatible receiver, a microfluidic channel with a syringe-pump transmitter using on-off keying (OOK), and a machine-intelligence pipeline that addresses model mismatch and hardware non-idealities. The pipeline integrates: (i) a modular universal decoder robust to vibration-induced noise, chemical delay, and single-tap intersymbol interference; (ii) a lightweight pilot-only synchronizer that estimates symbol intervals; and (iii) a virtual-response generator that augments data and scales symbol duration. Experiments across multiple chips and sessions demonstrate end-to-end chemical text transmission with consistent error-rate reductions compared to naive thresholding and standard neural baselines. By coupling biocompatible hardware with learning-based detection and generative augmentation, this work establishes a practical route toward AI-native nanomachine networks and higher rate molecular links, while providing a system blueprint adaptable to other biochemical modalities.
Nano Machine Intelligence: From a Communication Perspective
Paper ↗
Abstract
We present an AI-integrated molecular communication link validated on a benchtop nanomachine testbed representative of subdermal implants. The system employs an indium-gallium-zinc-oxide electrolyte-gated FET (IGZO-EGFET) functionalized with glucose oxidase as a biocompatible receiver, a microfluidic channel with a syringe-pump transmitter using on-off keying (OOK), and a machine-intelligence pipeline that addresses model mismatch and hardware non-idealities. The pipeline integrates: (i) a modular universal decoder robust to vibration-induced noise, chemical delay, and single-tap intersymbol interference; (ii) a lightweight pilot-only synchronizer that estimates symbol intervals; and (iii) a virtual-response generator that augments data and scales symbol duration. Experiments across multiple chips and sessions demonstrate end-to-end chemical text transmission with consistent error-rate reductions compared to naive thresholding and standard neural baselines. By coupling biocompatible hardware with learning-based detection and generative augmentation, this work establishes a practical route toward AI-native nanomachine networks and higher rate molecular links, while providing a system blueprint adaptable to other biochemical modalities.
FlexNGIA 2.0: Redesigning the Internet with Agentic AI -- Protocols, Services, and Traffic Engineering Designed, Deployed, and Managed by AI
Paper ↗
Abstract
The escalating demands of immersive communications, alongside advances in network softwarization and AI-driven cognition and generative reasoning, create a pivotal opportunity to rethink and reshape the future Internet. In this context, we introduce in this paper, FlexNGIA 2.0, an Agentic AI-driven Internet architecture that leverages LLM-based AI agents to autonomously orchestrate, configure, and evolve the network. These agents can, at runtime, perceive, reason, coordinate among themselves to dynamically design, implement, deploy, and adapt communication protocols, Service Function Chains (SFCs), network functions, resource allocation strategies, congestion control, and traffic engineering schemes, thereby ensuring optimal performance, reliability, and efficiency under evolving conditions. The paper first outlines the overall architecture of FlexNGIA 2.0 and its constituent LLM-Based AI agents. For each agent, we detail its design, implementation, inputs and outputs, prompt structures, interactions with tools and other agents, followed by preliminary proof-of-concept experiments demonstrating its operation and potential. The results clearly highlight the ability of these LLM-based AI agents to automate the design, the implementation, the deployment, and the performance evaluation of transport protocols, service function chains, network functions, congestion control schemes, and resource allocation strategies. FlexNGIA 2.0 paves the way for a new class of Agentic AI-Driven networks, where fully cognitive, self-evolving AI agents can autonomously design, implement, adapt and optimize the network's protocols, algorithms, and behaviors to efficiently operate across complex, dynamic, and heterogeneous environments. To bring this vision to reality, we also identify key research challenges toward achieving fully autonomous, adaptive, and agentic AI-driven networks.
FlexNGIA 2.0: Redesigning the Internet with Agentic AI -- Protocols, Services, and Traffic Engineering Designed, Deployed, and Managed by AI
Paper ↗
Abstract
The escalating demands of immersive communications, alongside advances in network softwarization and AI-driven cognition and generative reasoning, create a pivotal opportunity to rethink and reshape the future Internet. In this context, we introduce in this paper, FlexNGIA 2.0, an Agentic AI-driven Internet architecture that leverages LLM-based AI agents to autonomously orchestrate, configure, and evolve the network. These agents can, at runtime, perceive, reason, coordinate among themselves to dynamically design, implement, deploy, and adapt communication protocols, Service Function Chains (SFCs), network functions, resource allocation strategies, congestion control, and traffic engineering schemes, thereby ensuring optimal performance, reliability, and efficiency under evolving conditions. The paper first outlines the overall architecture of FlexNGIA 2.0 and its constituent LLM-Based AI agents. For each agent, we detail its design, implementation, inputs and outputs, prompt structures, interactions with tools and other agents, followed by preliminary proof-of-concept experiments demonstrating its operation and potential. The results clearly highlight the ability of these LLM-based AI agents to automate the design, the implementation, the deployment, and the performance evaluation of transport protocols, service function chains, network functions, congestion control schemes, and resource allocation strategies. FlexNGIA 2.0 paves the way for a new class of Agentic AI-Driven networks, where fully cognitive, self-evolving AI agents can autonomously design, implement, adapt and optimize the network's protocols, algorithms, and behaviors to efficiently operate across complex, dynamic, and heterogeneous environments. To bring this vision to reality, we also identify key research challenges toward achieving fully autonomous, adaptive, and agentic AI-driven networks.
Error Notebook-Guided, Training-Free Part Retrieval in 3D CAD Assemblies via Vision-Language Models
Paper ↗
Abstract
Effective specification-aware part retrieval within complex CAD assemblies is essential for automated design verification and downstream engineering tasks. However, directly using LLMs/VLMs to this task presents some challenges: the input sequences may exceed model token limits, and even after processing, performance remains unsatisfactory. Moreover, fine-tuning LLMs/VLMs requires significant computational resources, and for many high-performing general-use proprietary models (e.g., GPT or Gemini), fine-tuning access is not available. In this paper, we propose a novel part retrieval framework that requires no extra training, but using Error Notebooks + RAG for refined prompt engineering to help improve the existing general model's retrieval performance. The construction of Error Notebooks consists of two steps: (1) collecting historical erroneous CoTs and their incorrect answers, and (2) connecting these CoTs through reflective corrections until the correct solutions are obtained. As a result, the Error Notebooks serve as a repository of tasks along with their corrected CoTs and final answers. RAG is then employed to retrieve specification-relevant records from the Error Notebooks and incorporate them into the inference process. Another major contribution of our work is a human-in-the-loop CAD dataset, which is used to evaluate our method. In addition, the engineering value of our novel framework lies in its ability to effectively handle 3D models with lengthy, non-natural language metadata. Experiments with proprietary models, including GPT-4o and the Gemini series, show substantial gains, with GPT-4o (Omni) achieving up to a 23.4% absolute accuracy improvement on the human preference dataset. Moreover, ablation studies confirm that CoT reasoning provides benefits especially in challenging cases with higher part counts (>10).
Error Notebook-Guided, Training-Free Part Retrieval in 3D CAD Assemblies via Vision-Language Models
Paper ↗
Abstract
Effective specification-aware part retrieval within complex CAD assemblies is essential for automated design verification and downstream engineering tasks. However, directly using LLMs/VLMs to this task presents some challenges: the input sequences may exceed model token limits, and even after processing, performance remains unsatisfactory. Moreover, fine-tuning LLMs/VLMs requires significant computational resources, and for many high-performing general-use proprietary models (e.g., GPT or Gemini), fine-tuning access is not available. In this paper, we propose a novel part retrieval framework that requires no extra training, but using Error Notebooks + RAG for refined prompt engineering to help improve the existing general model's retrieval performance. The construction of Error Notebooks consists of two steps: (1) collecting historical erroneous CoTs and their incorrect answers, and (2) connecting these CoTs through reflective corrections until the correct solutions are obtained. As a result, the Error Notebooks serve as a repository of tasks along with their corrected CoTs and final answers. RAG is then employed to retrieve specification-relevant records from the Error Notebooks and incorporate them into the inference process. Another major contribution of our work is a human-in-the-loop CAD dataset, which is used to evaluate our method. In addition, the engineering value of our novel framework lies in its ability to effectively handle 3D models with lengthy, non-natural language metadata. Experiments with proprietary models, including GPT-4o and the Gemini series, show substantial gains, with GPT-4o (Omni) achieving up to a 23.4% absolute accuracy improvement on the human preference dataset. Moreover, ablation studies confirm that CoT reasoning provides benefits especially in challenging cases with higher part counts (>10).
Towards Agentic OS: An LLM Agent Framework for Linux Schedulers
Paper ↗
Abstract
Operating system schedulers suffer from a fundamental semantic gap, where kernel policies fail to understand application-specific needs, leading to suboptimal performance. We introduce SchedCP, the first framework that enables fully autonomous Large Language Model (LLM) agents to safely and efficiently optimize Linux schedulers without human involvement. Our core insight is that the challenge is not merely to apply a better LLM, but to architect a decoupled control plane that separates the AI's role of semantic reasoning ("what to optimize") from the system's role of execution ("how to observe and act"). Implemented as Model Context Protocol(MCP) server, SchedCP provides a stable interface with three key services: a Workload Analysis Engine, an evolving Scheduler Policy Repository, and an Execution Verifier that validates all AI-generated code and configure before deployment with static and dynamic analysis. We demonstrate this architecture's power with sched-agent, a multi-agent system that autonomously analyzes workloads, synthesizes custom eBPF scheduling policies, and deploys them via the sched\_ext infrastructure. Our evaluation shows that SchedCP achieves up to an 1.79x performance improvement, and a 13x cost reduction compared to naive agentic approaches, all while maintaining high success rate. By bridging the semantic gap, SchedCP democratizes expert-level system optimization and represents a step towards creating truly self-optimizing, application-aware operating systems. The code is open-sourced in https://github.com/eunomia-bpf/schedcp
Towards Agentic OS: An LLM Agent Framework for Linux Schedulers
Paper ↗
Abstract
Operating system schedulers suffer from a fundamental semantic gap, where kernel policies fail to understand application-specific needs, leading to suboptimal performance. We introduce SchedCP, the first framework that enables fully autonomous Large Language Model (LLM) agents to safely and efficiently optimize Linux schedulers without human involvement. Our core insight is that the challenge is not merely to apply a better LLM, but to architect a decoupled control plane that separates the AI's role of semantic reasoning ("what to optimize") from the system's role of execution ("how to observe and act"). Implemented as Model Context Protocol(MCP) server, SchedCP provides a stable interface with three key services: a Workload Analysis Engine, an evolving Scheduler Policy Repository, and an Execution Verifier that validates all AI-generated code and configure before deployment with static and dynamic analysis. We demonstrate this architecture's power with sched-agent, a multi-agent system that autonomously analyzes workloads, synthesizes custom eBPF scheduling policies, and deploys them via the sched\_ext infrastructure. Our evaluation shows that SchedCP achieves up to an 1.79x performance improvement, and a 13x cost reduction compared to naive agentic approaches, all while maintaining high success rate. By bridging the semantic gap, SchedCP democratizes expert-level system optimization and represents a step towards creating truly self-optimizing, application-aware operating systems. The code is open-sourced in https://github.com/eunomia-bpf/schedcp
Fluid Antenna Port Prediction based on Large Language Models
Paper ↗
Abstract
This study seeks to utilize large language models (LLMs) to forecast the moving ports of fluid antenna (FA). By repositioning the antenna to the locations identified by our proposed model, we intend to address the mobility challenges faced by user equipment (UE). To the best of our knowledge, this paper introduces, for the first time, the application of LLMs in the prediction of FA ports, presenting a novel model termed Port-LLM. The architecture of our model is based on the pre-trained GPT-2 framework. We designed specialized data preprocessing, input embedding, and output projection modules to effectively bridge the disparities between the wireless communication data and the data format utilized by the pre-trained LLM. Simulation results demonstrate that our model exhibits superior predictive performance under different numbers of base station (BS) antennas and varying UE speeds, indicating strong generalization and robustness ability. Furthermore, the spectral efficiency (SE) attained by our model surpasses that achieved by traditional methods in both medium and high-speed mobile environments.
Fluid Antenna Port Prediction based on Large Language Models
Paper ↗
Abstract
This study seeks to utilize large language models (LLMs) to forecast the moving ports of fluid antenna (FA). By repositioning the antenna to the locations identified by our proposed model, we intend to address the mobility challenges faced by user equipment (UE). To the best of our knowledge, this paper introduces, for the first time, the application of LLMs in the prediction of FA ports, presenting a novel model termed Port-LLM. The architecture of our model is based on the pre-trained GPT-2 framework. We designed specialized data preprocessing, input embedding, and output projection modules to effectively bridge the disparities between the wireless communication data and the data format utilized by the pre-trained LLM. Simulation results demonstrate that our model exhibits superior predictive performance under different numbers of base station (BS) antennas and varying UE speeds, indicating strong generalization and robustness ability. Furthermore, the spectral efficiency (SE) attained by our model surpasses that achieved by traditional methods in both medium and high-speed mobile environments.
Accelerating Latency-Critical Applications with AI-Powered Semi-Automatic Fine-Grained Parallelization on SMT Processors
Paper ↗
Abstract
Latency-critical applications tend to show low utilization of functional units due to frequent cache misses and mispredictions during speculative execution in high-performance superscalar processors. However, due to significant impact on single-thread performance, Simultaneous Multithreading (SMT) technology is rarely used with heavy threads of latency-critical applications. In this paper, we explore utilization of SMT technology to support fine-grained parallelization of latency-critical applications. Following the advancements in the development of Large Language Models (LLMs), we introduce Aira, an AI-powered Parallelization Adviser. To implement Aira, we extend AI Coding Agent in Cursor IDE with additional tools connected through Model Context Protocol, enabling end-to-end AI Agent for parallelization. Additional connected tools enable LLM-guided hotspot detection, collection of dynamic dependencies with Dynamic Binary Instrumentation, SMT-aware performance simulation to estimate performance gains. We apply Aira with Relic parallel framework for fine-grained task parallelism on SMT cores to parallelize latency-critical benchmarks representing real-world applications used in industry. We show 17% geomean performance gain from parallelization of latency-critical benchmarks using Aira with Relic framework.
Accelerating Latency-Critical Applications with AI-Powered Semi-Automatic Fine-Grained Parallelization on SMT Processors
Paper ↗
Abstract
Latency-critical applications tend to show low utilization of functional units due to frequent cache misses and mispredictions during speculative execution in high-performance superscalar processors. However, due to significant impact on single-thread performance, Simultaneous Multithreading (SMT) technology is rarely used with heavy threads of latency-critical applications. In this paper, we explore utilization of SMT technology to support fine-grained parallelization of latency-critical applications. Following the advancements in the development of Large Language Models (LLMs), we introduce Aira, an AI-powered Parallelization Adviser. To implement Aira, we extend AI Coding Agent in Cursor IDE with additional tools connected through Model Context Protocol, enabling end-to-end AI Agent for parallelization. Additional connected tools enable LLM-guided hotspot detection, collection of dynamic dependencies with Dynamic Binary Instrumentation, SMT-aware performance simulation to estimate performance gains. We apply Aira with Relic parallel framework for fine-grained task parallelism on SMT cores to parallelize latency-critical benchmarks representing real-world applications used in industry. We show 17% geomean performance gain from parallelization of latency-critical benchmarks using Aira with Relic framework.
LLM-HyPZ: Hardware Vulnerability Discovery using an LLM-Assisted Hybrid Platform for Zero-Shot Knowledge Extraction and Refinement
Paper ↗
Abstract
The rapid growth of hardware vulnerabilities has created an urgent need for systematic and scalable analysis methods. Unlike software flaws, which are often patchable post-deployment, hardware weaknesses remain embedded across product lifecycles, posing persistent risks to processors, embedded devices, and IoT platforms. Existing efforts such as the MITRE CWE Hardware List (2021) relied on expert-driven Delphi surveys, which lack statistical rigor and introduce subjective bias, while large-scale data-driven foundations for hardware weaknesses have been largely absent. In this work, we propose LLM-HyPZ, an LLM-assisted hybrid framework for zero-shot knowledge extraction and refinement from vulnerability corpora. Our approach integrates zero-shot LLM classification, contextualized embeddings, unsupervised clustering, and prompt-driven summarization to mine hardware-related CVEs at scale. Applying LLM-HyPZ to the 2021-2024 CVE corpus (114,836 entries), we identified 1,742 hardware-related vulnerabilities. We distilled them into five recurring themes, including privilege escalation via firmware and BIOS, memory corruption in mobile and IoT systems, and physical access exploits. Benchmarking across seven LLMs shows that LLaMA 3.3 70B achieves near-perfect classification accuracy (99.5%) on a curated validation set. Beyond methodological contributions, our framework directly supported the MITRE CWE Most Important Hardware Weaknesses (MIHW) 2025 update by narrowing the candidate search space. Specifically, our pipeline surfaced 411 of the 1,026 CVEs used for downstream MIHW analysis, thereby reducing expert workload and accelerating evidence gathering. These results establish LLM-HyPZ as the first data-driven, scalable approach for systematically discovering hardware vulnerabilities, thereby bridging the gap between expert knowledge and real-world vulnerability evidence.
LLM-HyPZ: Hardware Vulnerability Discovery using an LLM-Assisted Hybrid Platform for Zero-Shot Knowledge Extraction and Refinement
Paper ↗
Abstract
The rapid growth of hardware vulnerabilities has created an urgent need for systematic and scalable analysis methods. Unlike software flaws, which are often patchable post-deployment, hardware weaknesses remain embedded across product lifecycles, posing persistent risks to processors, embedded devices, and IoT platforms. Existing efforts such as the MITRE CWE Hardware List (2021) relied on expert-driven Delphi surveys, which lack statistical rigor and introduce subjective bias, while large-scale data-driven foundations for hardware weaknesses have been largely absent. In this work, we propose LLM-HyPZ, an LLM-assisted hybrid framework for zero-shot knowledge extraction and refinement from vulnerability corpora. Our approach integrates zero-shot LLM classification, contextualized embeddings, unsupervised clustering, and prompt-driven summarization to mine hardware-related CVEs at scale. Applying LLM-HyPZ to the 2021-2024 CVE corpus (114,836 entries), we identified 1,742 hardware-related vulnerabilities. We distilled them into five recurring themes, including privilege escalation via firmware and BIOS, memory corruption in mobile and IoT systems, and physical access exploits. Benchmarking across seven LLMs shows that LLaMA 3.3 70B achieves near-perfect classification accuracy (99.5%) on a curated validation set. Beyond methodological contributions, our framework directly supported the MITRE CWE Most Important Hardware Weaknesses (MIHW) 2025 update by narrowing the candidate search space. Specifically, our pipeline surfaced 411 of the 1,026 CVEs used for downstream MIHW analysis, thereby reducing expert workload and accelerating evidence gathering. These results establish LLM-HyPZ as the first data-driven, scalable approach for systematically discovering hardware vulnerabilities, thereby bridging the gap between expert knowledge and real-world vulnerability evidence.
SpliDT: Partitioned Decision Trees for Scalable Stateful Inference at Line Rate
Paper ↗
Abstract
Machine learning (ML) is increasingly being deployed in programmable data planes (switches and SmartNICs) to enable real-time traffic analysis, security monitoring, and in-network decision-making. Decision trees (DTs) are particularly well-suited for these tasks due to their interpretability and compatibility with data-plane architectures, i.e., match-action tables (MATs). However, existing in-network DT implementations are constrained by the need to compute all input features upfront, forcing models to rely on a small, fixed set of features per flow. This significantly limits model accuracy and scalability under stringent hardware resource constraints. We present SPLIDT, a system that rethinks DT deployment in the data plane by enabling partitioned inference over sliding windows of packets. SPLIDT introduces two key innovations: (1) it assigns distinct, variable feature sets to individual sub-trees of a DT, grouped into partitions, and (2) it leverages an in-band control channel (via recirculation) to reuse data-plane resources (both stateful registers and match keys) across partitions at line rate. These insights allow SPLIDT to scale the number of stateful features a model can use without exceeding hardware limits. To support this architecture, SPLIDT incorporates a custom training and design-space exploration (DSE) framework that jointly optimizes feature allocation, tree partitioning, and DT model depth. Evaluation across multiple real-world datasets shows that SPLIDT achieves higher accuracy while supporting up to 5x more stateful features than prior approaches (e.g., NetBeacon and Leo). It maintains the same low time-to-detection (TTD) as these systems, while scaling to millions of flows with minimal recirculation overhead (<0.05%).
SpliDT: Partitioned Decision Trees for Scalable Stateful Inference at Line Rate
Paper ↗
Abstract
Machine learning (ML) is increasingly being deployed in programmable data planes (switches and SmartNICs) to enable real-time traffic analysis, security monitoring, and in-network decision-making. Decision trees (DTs) are particularly well-suited for these tasks due to their interpretability and compatibility with data-plane architectures, i.e., match-action tables (MATs). However, existing in-network DT implementations are constrained by the need to compute all input features upfront, forcing models to rely on a small, fixed set of features per flow. This significantly limits model accuracy and scalability under stringent hardware resource constraints. We present SPLIDT, a system that rethinks DT deployment in the data plane by enabling partitioned inference over sliding windows of packets. SPLIDT introduces two key innovations: (1) it assigns distinct, variable feature sets to individual sub-trees of a DT, grouped into partitions, and (2) it leverages an in-band control channel (via recirculation) to reuse data-plane resources (both stateful registers and match keys) across partitions at line rate. These insights allow SPLIDT to scale the number of stateful features a model can use without exceeding hardware limits. To support this architecture, SPLIDT incorporates a custom training and design-space exploration (DSE) framework that jointly optimizes feature allocation, tree partitioning, and DT model depth. Evaluation across multiple real-world datasets shows that SPLIDT achieves higher accuracy while supporting up to 5x more stateful features than prior approaches (e.g., NetBeacon and Leo). It maintains the same low time-to-detection (TTD) as these systems, while scaling to millions of flows with minimal recirculation overhead (<0.05%).
LLM-Based Program Generation for Triggering Numerical Inconsistencies Across Compilers
Paper ↗
Abstract
Floating-point inconsistencies across compilers can undermine the reliability of numerical software. We present LLM4FP, the first framework that uses Large Language Models (LLMs) to generate floating-point programs specifically designed to trigger such inconsistencies. LLM4FP combines Grammar-Based Generation and Feedback-Based Mutation to produce diverse and valid programs. We evaluate LLM4FP across multiple compilers and optimization levels, measuring inconsistency rate, time cost, and program diversity. LLM4FP detects over twice as many inconsistencies compared to the state-of-the-art tool, Varity. Notably, most of the inconsistencies involve real-valued differences, rather than extreme values like NaN or infinities. LLM4FP also uncovers inconsistencies across a wider range of optimization levels, and finds the most mismatches between host and device compilers. These results show that LLM-guided program generation improves the detection of numerical inconsistencies.
LLM-Based Program Generation for Triggering Numerical Inconsistencies Across Compilers
Paper ↗
Abstract
Floating-point inconsistencies across compilers can undermine the reliability of numerical software. We present LLM4FP, the first framework that uses Large Language Models (LLMs) to generate floating-point programs specifically designed to trigger such inconsistencies. LLM4FP combines Grammar-Based Generation and Feedback-Based Mutation to produce diverse and valid programs. We evaluate LLM4FP across multiple compilers and optimization levels, measuring inconsistency rate, time cost, and program diversity. LLM4FP detects over twice as many inconsistencies compared to the state-of-the-art tool, Varity. Notably, most of the inconsistencies involve real-valued differences, rather than extreme values like NaN or infinities. LLM4FP also uncovers inconsistencies across a wider range of optimization levels, and finds the most mismatches between host and device compilers. These results show that LLM-guided program generation improves the detection of numerical inconsistencies.
Enhancing Semantic Understanding in Pointer Analysis using Large Language Models
Paper ↗
Abstract
Pointer analysis has been studied for over four decades. However, existing frameworks continue to suffer from the propagation of incorrect facts. A major limitation stems from their insufficient semantic understanding of code, resulting in overly conservative treatment of user-defined functions. Recent advances in large language models (LLMs) present new opportunities to bridge this gap. In this paper, we propose LMPA (LLM-enhanced Pointer Analysis), a vision that integrates LLMs into pointer analysis to enhance both precision and scalability. LMPA identifies user-defined functions that resemble system APIs and models them accordingly, thereby mitigating erroneous cross-calling-context propagation. Furthermore, it enhances summary-based analysis by inferring initial points-to sets and introducing a novel summary strategy augmented with natural language. Finally, we discuss the key challenges involved in realizing this vision.
Data Driven Programming of Photonic Integrated Circuits
Paper ↗
Abstract
Programming photonic integrated hardware often reveals as a challenging task because of the presence of non-idealities in the photonic chip. These include fabrication imper- fections and parasitic effects such as thermal crosstalk, which cause unwanted coupling between control signals. Traditional control methods based on idealized models often fail to account for these phenomana, leading to significant discrepancies between the desired and actual circuit behaviour. In this work, we propose a data-driven approach for control- ling meshes of thermally tuneable Mach Zehnder interferometers (MZIs), which exploits a machine learning (ML) model trained to compensate for these non-idealities by pre- adjusting the electrical power given to integrated phase shifters. The proposed ML system is assessed using synthetic datasets and experimentally validated on a 3 x 3 triangular MZI mesh. Results demonstrate that the data-driven controller significantly improves program- ming accuracy, offering a robust solution for accurate programming of photonic integrated circuits.
Adaptive Root Cause Localization for Microservice Systems with Multi-Agent Recursion-of-Thought
Paper ↗
Abstract
As contemporary microservice systems become increasingly popular and complex-often comprising hundreds or even thousands of fine-grained, interdependent subsystems-they are facing more frequent failures. Ensuring system reliability thus demands accurate root cause localization. While traces and metrics have proven to be effective data sources for this task, existing methods either heavily rely on pre-defined schemas, which struggle to adapt to evolving operational contexts, or lack interpretability in their reasoning process, thereby leaving Site Reliability Engineers (SREs) confused. In this paper, we conduct a comprehensive study on how SREs localize the root cause of failures, drawing insights from multiple professional SREs across different organizations. Our investigation reveals that human root cause analysis exhibits three key characteristics: recursiveness, multi-dimensional expansion, and cross-modal reasoning. Motivated by these findings, we introduce RCLAgent, an adaptive root cause localization method for microservice systems that leverages a multi-agent recursion-of-thought framework. RCLAgent employs a novel recursion-of-thought strategy to guide the LLM's reasoning process, effectively integrating data from multiple agents and tool-assisted analysis to accurately pinpoint the root cause. Experimental evaluations on various public datasets demonstrate that RCLAgent achieves superior performance by localizing the root cause using only a single request-outperforming state-of-the-art methods that depend on aggregating multiple requests. These results underscore the effectiveness of RCLAgent in enhancing the efficiency and precision of root cause localization in complex microservice environments.
Boosting Skeleton-Driven SMT Solver Fuzzing by Leveraging LLM to Produce Formula Generators
Paper ↗
Abstract
Satisfiability Modulo Theory (SMT) solvers are foundational to modern systems and programming languages research, providing the foundation for tasks like symbolic execution and automated verification. Because these solvers sit on the critical path, their correctness is essential, and high-quality test formulas are key to uncovering bugs. However, while prior testing techniques performed well on earlier solver versions, they struggle to keep pace with rapidly evolving features. Recent approaches based on Large Language Models (LLMs) show promise in exploring advanced solver capabilities, but two obstacles remain: nearly half of the generated formulas are syntactically invalid, and iterative interactions with the LLMs introduce substantial computational overhead. In this study, we present Chimera, a novel LLM-assisted fuzzing framework that addresses both issues by shifting from direct formula generation to the synthesis of reusable term (i.e., logical expression) generators. Particularly, Chimera uses LLMs to (1) automatically extract context-free grammars (CFGs) for SMT theories, including solver-specific extensions, from documentation, and (2) synthesize composable Boolean term generators that adhere to these grammars. During fuzzing, Chimera populates structural skeletons derived from existing formulas with the terms iteratively produced by the LLM-synthesized generators. This design ensures syntactic validity while promoting semantic diversity. Notably, Chimera requires only one-time LLM interaction investment, dramatically reducing runtime cost. We evaluated Chimera on two leading SMT solvers: Z3 and cvc5. Our experiments show that Chimera has identified 43 confirmed bugs, 40 of which have already been fixed by developers.
SwizzlePerf: Hardware-Aware LLMs for GPU Kernel Performance Optimization
Paper ↗
Abstract
Large language models (LLMs) have shown progress in GPU kernel performance engineering using inefficient search-based methods that optimize around runtime. Any existing approach lacks a key characteristic that human performance engineers rely on for near-optimal utilization -- hardware-awareness. By leveraging the workload's specific memory access patterns, architecture specifications, filtered profiling logs, and reflections on historical performance, we can make software-level optimizations that are tailored to the underlying hardware. SwizzlePerf automatically generates spatial optimizations for GPU kernels on disaggregated architectures by giving LLMs explicit hardware-awareness. For a GEMM kernel, SwizzlePerf takes less than 5 minutes to generate the same hardware-specific optimal swizzling pattern that took expert performance engineers 2 weeks to find. On a suite of 10 diverse ML and Science kernels, SwizzlePerf can generate swizzling patterns for 9 of the kernels that achieve up to a 2.06x speedup and 70% improvement in L2 hit rate. This work is the first of many steps toward systematically creating hardware-aware LLM performance engineering agents.
Large Language Models (LLMs) for Electronic Design Automation (EDA)
Paper ↗
Abstract
With the growing complexity of modern integrated circuits, hardware engineers are required to devote more effort to the full design-to-manufacturing workflow. This workflow involves numerous iterations, making it both labor-intensive and error-prone. Therefore, there is an urgent demand for more efficient Electronic Design Automation (EDA) solutions to accelerate hardware development. Recently, large language models (LLMs) have shown remarkable advancements in contextual comprehension, logical reasoning, and generative capabilities. Since hardware designs and intermediate scripts can be represented as text, integrating LLM for EDA offers a promising opportunity to simplify and even automate the entire workflow. Accordingly, this paper provides a comprehensive overview of incorporating LLMs into EDA, with emphasis on their capabilities, limitations, and future opportunities. Three case studies, along with their outlook, are introduced to demonstrate the capabilities of LLMs in hardware design, testing, and optimization. Finally, future directions and challenges are highlighted to further explore the potential of LLMs in shaping the next-generation EDA, providing valuable insights for researchers interested in leveraging advanced AI technologies for EDA.
Leveraging LLMs for Automated Translation of Legacy Code: A Case Study on PL/SQL to Java Transformation
Paper ↗
Abstract
The VT legacy system, comprising approximately 2.5 million lines of PL/SQL code, lacks consistent documentation and automated tests, posing significant challenges for refactoring and modernisation. This study investigates the feasibility of leveraging large language models (LLMs) to assist in translating PL/SQL code into Java for the modernised "VTF3" system. By leveraging a dataset comprising 10 PL/SQL-to-Java code pairs and 15 Java classes, which collectively established a domain model for the translated files, multiple LLMs were evaluated. Furthermore, we propose a customized prompting strategy that integrates chain-of-guidance reasoning with $n$-shot prompting. Our findings indicate that this methodology effectively guides LLMs in generating syntactically accurate translations while also achieving functional correctness. However, the findings are limited by the small sample size of available code files and the restricted access to test cases used for validating the correctness of the generated code. Nevertheless, these findings lay the groundwork for scalable, automated solutions in modernising large legacy systems.
GENIE-ASI: Generative Instruction and Executable Code for Analog Subcircuit Identification
Paper ↗
Abstract
Analog subcircuit identification is a core task in analog design, essential for simulation, sizing, and layout. Traditional methods often require extensive human expertise, rule-based encoding, or large labeled datasets. To address these challenges, we propose GENIE-ASI, the first training-free, large language model (LLM)-based methodology for analog subcircuit identification. GENIE-ASI operates in two phases: it first uses in-context learning to derive natural language instructions from a few demonstration examples, then translates these into executable Python code to identify subcircuits in unseen SPICE netlists. In addition, to evaluate LLM-based approaches systematically, we introduce a new benchmark composed of operational amplifier netlists (op-amps) that cover a wide range of subcircuit variants. Experimental results on the proposed benchmark show that GENIE-ASI matches rule-based performance on simple structures (F1-score = 1.0), remains competitive on moderate abstractions (F1-score = 0.81), and shows potential even on complex subcircuits (F1-score = 0.31). These findings demonstrate that LLMs can serve as adaptable, general-purpose tools in analog design automation, opening new research directions for foundation model applications in analog design automation.
SynCircuit: Automated Generation of New Synthetic RTL Circuits Can Enable Big Data in Circuits
Paper ↗
Abstract
In recent years, AI-assisted IC design methods have demonstrated great potential, but the availability of circuit design data is extremely limited, especially in the public domain. The lack of circuit data has become the primary bottleneck in developing AI-assisted IC design methods. In this work, we make the first attempt, SynCircuit, to generate new synthetic circuits with valid functionalities in the HDL format. SynCircuit automatically generates synthetic data using a framework with three innovative steps: 1) We propose a customized diffusion-based generative model to resolve the Directed Cyclic Graph (DCG) generation task, which has not been well explored in the AI community. 2) To ensure our circuit is valid, we enforce the circuit constraints by refining the initial graph generation outputs. 3) The Monte Carlo tree search (MCTS) method further optimizes the logic redundancy in the generated graph. Experimental results demonstrate that our proposed SynCircuit can generate more realistic synthetic circuits and enhance ML model performance in downstream circuit design tasks.
SynCircuit: Automated Generation of New Synthetic RTL Circuits Can Enable Big Data in Circuits
Paper ↗
Abstract
In recent years, AI-assisted IC design methods have demonstrated great potential, but the availability of circuit design data is extremely limited, especially in the public domain. The lack of circuit data has become the primary bottleneck in developing AI-assisted IC design methods. In this work, we make the first attempt, SynCircuit, to generate new synthetic circuits with valid functionalities in the HDL format. SynCircuit automatically generates synthetic data using a framework with three innovative steps: 1) We propose a customized diffusion-based generative model to resolve the Directed Cyclic Graph (DCG) generation task, which has not been well explored in the AI community. 2) To ensure our circuit is valid, we enforce the circuit constraints by refining the initial graph generation outputs. 3) The Monte Carlo tree search (MCTS) method further optimizes the logic redundancy in the generated graph. Experimental results demonstrate that our proposed SynCircuit can generate more realistic synthetic circuits and enhance ML model performance in downstream circuit design tasks.
Interleaving Large Language Models for Compiler Testing
Paper ↗
Abstract
Testing compilers with AI models, especially large language models (LLMs), has shown great promise. However, current approaches struggle with two key problems: The generated programs for testing compilers are often too simple, and extensive testing with the LLMs is computationally expensive. In this paper, we propose a novel compiler testing framework that decouples the testing process into two distinct phases: an offline phase and an online phase. In the offline phase, we use LLMs to generate a collection of small but feature-rich code pieces. In the online phase, we reuse these code pieces by strategically combining them to build high-quality and valid test programs, which are then used to test compilers. We implement this idea in a tool, LegoFuzz, for testing C compilers. The results are striking: we found 66 bugs in GCC and LLVM, the most widely used C compilers. Almost half of the bugs are miscompilation bugs, which are serious and hard-to-find bugs that none of the existing LLM-based tools could find. We believe this efficient design opens up new possibilities for using AI models in software testing beyond just C compilers.
Beyond Tokens: Enhancing RTL Quality Estimation via Structural Graph Learning
Paper ↗
Abstract
Estimating the quality of register transfer level (RTL) designs is crucial in the electronic design automation (EDA) workflow, as it enables instant feedback on key metrics like area and delay without the need for time-consuming logic synthesis. While recent approaches have leveraged large language models (LLMs) to derive embeddings from RTL code and achieved promising results, they overlook the structural semantics essential for accurate quality estimation. In contrast, the control data flow graph (CDFG) view exposes the design's structural characteristics more explicitly, offering richer cues for representation learning. In this work, we introduce a novel structure-aware graph self-supervised learning framework, StructRTL, for improved RTL design quality estimation. By learning structure-informed representations from CDFGs, our method significantly outperforms prior art on various quality estimation tasks. To further boost performance, we incorporate a knowledge distillation strategy that transfers low-level insights from post-mapping netlists into the CDFG predictor. Experiments show that our approach establishes new state-of-the-art results, demonstrating the effectiveness of combining structural learning with cross-stage supervision.
LLM as an Execution Estimator: Recovering Missing Dependency for Practical Time-travelling Debugging
Paper ↗
Abstract
Dynamic data dependency, answering "why a variable has this value?", is critical for debugging. Given a program step `s` reading a variable `v`, finding the dynamic definition of `v` is challenging. Traditional methods require either (1) exhaustive instrumentation of all possible definitions of `v` in one run or (2) replicating the run to re-examine reads/writes - both costly. If `v` is defined in a library, instrumentation becomes expensive; for non-deterministic programs, replication is infeasible. We propose RecovSlicing, which computes dynamic data dependency in a single run with partial instrumentation. We leverage LLMs to infer program behavior from a partially recorded trace and code context. Given a trace and a slicing criterion (step `s` and variable `v`), RecovSlicing estimates the runtime definition of `v` by recovering the missing execution.It also supports implicit variables, such as those in `list.get(i)`. Technically, RecovSlicing tackles: (1) recovering runtime values and structures, and (2) aligning recovered variables with recorded memory to analyze definitions. We evaluate RecovSlicing on 8,300 data dependencies across three slicing benchmarks, comparing it with Slicer4J, ND-Slicer, LLM Slicer, and re-execution Slicer. RecovSlicing achieves accuracy of 80.3%, 91.1%, and 98.3%, outperforming the best baseline (39.0%, 82.0%, 59.9%), and also leads in recall (91.1%, 91.1%, 98.3% vs. 53.4%, 79.1%, 87.1%). Integrated into a regression bug localizer, it enables finding 16% more regressions.
LLM as an Execution Estimator: Recovering Missing Dependency for Practical Time-travelling Debugging
Paper ↗
Abstract
In this work, we propose RecovSlicing for computing dynamic data dependency in a single run, with only partial instrumentation. We explore the intuition that LLM can potentially infer program dynamics based on a partially recorded trace and relevant code as its context. Given (1) a partially recorded trace of a program $P$ and (2) the slicing criteria consisting of a query step $s$ and a query variable $v$ read by $s$, RecovSlicing computes the runtime definition of $v$ on the trace by estimating the miss-recorded execution of $P$. In this work, we allow the user to specify implicit query variable, for example, the implicit library variable used in list{\ttfamily .}get(i). Technically, built upon non-deterministic LLM, we address the challenges of (1) precise recovery of runtime variable value and structure from the recorded execution and (2) aligning the memory address of recovered variables and the recorded variables for definition analysis. We extensively evaluate RecovSlicing against the state-of-the-art slicers such as Slicer4J, ND-Slicer, LLM Slicer, and re-execution Slicer on a total number of 8300 data-dependencies over 3 slicing benchmarks. The results show that RecovSlicing can significantly outperform the baselines. The accuracy and recall, achieving 80.3%, 91.1%, and 98.3% on the three benchmarks, whereas the best baseline reaches 39.0%, 82.0%, and 59.9% (accuracy), and 53.4%, 79.1%, and 87.1% (recall), respectively. In addition, we integrate RecovSlicing in a dual-slicing based regression bug localizer, significantly improving its performance by locating 16% more regressions.
LLM as an Execution Estimator: Recovering Missing Dependency for Practical Time-travelling Debugging
Paper ↗
Abstract
Determining the dynamic data dependency of a step that reads a variable $v$ is challenging. It typically requires either exhaustive instrumentation, which becomes prohibitively expensive when $v$ is defined within library calls, or repeated executions, which are impractical for non-deterministic programs. In this work, we propose RecovSlicing for computing dynamic data dependency in a single run, with only partial instrumentation. We explore the intuition that LLM can potentially infer program dynamics based on a partially recorded trace and relevant code as its context. Given (1) a partially recorded trace of a program $P$ and (2) the slicing criteria consisting of a query step $s$ and a query variable $v$ read by $s$, RecovSlicing computes the runtime definition of $v$ on the trace by estimating the miss-recorded execution of $P$. In this work, we allow the user to specify implicit query variable. Technically, built upon non-deterministic LLM, we address the challenges of (1) precise recovery of runtime variable value and structure from the recorded execution and (2) aligning the memory address of recovered variables and the recorded variables for definition analysis. We evaluate RecovSlicing on 8300 data dependencies across three slicing benchmarks, comparing it with Slicer4J, ND-Slicer, LLM Slicer, and re-execution Slicer. RecovSlicing achieves significantly higher accuracy (80.3%, 91.1%, 98.3%) and recall (up to 98.3%) than the best baseline (accuracy: 39.0%, 82.0%, 59.9%; recall: 53.4%, 79.1%, 87.1%). Integrated into a dual-slicing regression bug localizer, it identifies 16% more regressions.
LLM as an Execution Estimator: Recovering Missing Dependency for Practical Time-travelling Debugging
Paper ↗
Abstract
Determining the dynamic data dependency of a step that reads a variable $v$ is challenging. It typically requires either exhaustive instrumentation, which becomes prohibitively expensive when $v$ is defined within library calls, or repeated executions, which are impractical for non-deterministic programs. In this work, we propose RecovSlicing for computing dynamic data dependency in a single run, with only partial instrumentation. We explore the intuition that LLM can potentially infer program dynamics based on a partially recorded trace and relevant code as its context. Given (1) a partially recorded trace of a program $P$ and (2) the slicing criteria consisting of a query step $s$ and a query variable $v$ read by $s$, RecovSlicing computes the runtime definition of $v$ on the trace by estimating the miss-recorded execution of $P$. In this work, we allow the user to specify implicit query variable. Technically, built upon non-deterministic LLM, we address the challenges of (1) precise recovery of runtime variable value and structure from the recorded execution and (2) aligning the memory address of recovered variables and the recorded variables for definition analysis. We evaluate RecovSlicing on 8300 data dependencies across three slicing benchmarks, comparing it with Slicer4J, ND-Slicer, LLM Slicer, and re-execution Slicer. RecovSlicing achieves significantly higher accuracy (80.3%, 91.1%, 98.3%) and recall (up to 98.3%) than the best baseline (accuracy: 39.0%, 82.0%, 59.9%; recall: 53.4%, 79.1%, 87.1%). Integrated into a dual-slicing regression bug localizer, it identifies 16% more regressions.
VERIRL: Boosting the LLM-based Verilog Code Generation via Reinforcement Learning
Paper ↗
Abstract
Recent advancements in code generation have shown remarkable success across software domains, yet hardware description languages (HDLs) such as Verilog remain underexplored due to their concurrency semantics, syntactic rigidity, and simulation complexity. In this work, we address these challenges by introducing a reinforcement learning (RL) framework tailored for Verilog code generation. We first construct Veribench-53K, a high-quality dataset curated from over 700K Verilog problems, enriched with structured prompts, complexity labels, and diverse testbenches. To tackle the problem of sparse and noisy reward signals, we propose a Trace-back based Rescore mechanism that leverages reasoning paths and iterative refinement to enhance feedback reliability and support reward model training. Furthermore, to mitigate catastrophic forgetting and overfitting during RL fine-tuning, we introduce a sample-balanced weighting strategy that adaptively balances learning dynamics based on reward-probability distributions. These innovations are integrated into an iterative RL pipeline that co-evolves the policy and reward models. In contrast to recent work such as CraftRTL, which relies on large-scale closed-source model distillation, and DeepSeek-style approaches that struggle with sparse feedback, our method demonstrates superior performance using a smaller but high-quality dataset combined with RL optimization. Experiments on Verilog generation tasks demonstrate state-of-the-art performance, with substantial gains in test pass rate, functional correctness, and compilation robustness. Our findings highlight the potential of RL-driven approaches for structured code generation in hardware-centric domains. VERIRL is publicly available at https://github.com/omniAI-Lab/VeriRL.
Automating Conflict-Aware ACL Configurations with Natural Language Intents
Paper ↗
Abstract
ACL configuration is essential for managing network flow reachability, yet its complexity grows significantly with topologies and pre-existing rules. To carry out ACL configuration, the operator needs to (1) understand the new configuration policies or intents and translate them into concrete ACL rules, (2) check and resolve any conflicts between the new and existing rules, and (3) deploy them across the network. Existing systems rely heavily on manual efforts for these tasks, especially for the first two, which are tedious, error-prone, and impractical to scale. We propose Xumi to tackle this problem. Leveraging LLMs with domain knowledge of the target network, Xumi automatically and accurately translates the natural language intents into complete ACL rules to reduce operators' manual efforts. Xumi then detects all potential conflicts between new and existing rules and generates resolved intents for deployment with operators' guidance, and finally identifies the best deployment plan that minimizes the rule additions while satisfying all intents. Evaluation shows that Xumi accelerates the entire configuration pipeline by over 10x compared to current practices, addresses O(100) conflicting ACLs and reduces rule additions by ~40% in modern cloud network.
LLMulator: Generalizable Cost Modeling for Dataflow Accelerators with Input-Adaptive Control Flow
Paper ↗
Abstract
Accurate and fast performance prediction for dataflow-based accelerators is vital for efficient hardware design and design space exploration, yet existing methods struggle to generalize across architectures, applications, and input-dependent control flows. We present LLMulator, a progressive numeric modeling framework leveraging the program semantic knowledge of pre-trained large language models (LLMs) for robust, hardware- and application-aware prediction. Our numeric model treats performance values as categorical token sequences, enabling range-agnostic estimates and confidence-aware predictions for unseen applications. To handle input-dependent control flows, we introduce a reinforcement learning-based dynamic calibration method, reducing cycle prediction error by 9.7% over static models and converging to 11.2% error after a few iterations. For cross-hardware generalization, we develop a progressive data augmentation strategy that generates diverse datasets covering multi-level dataflow structures, memory parameters, and loop mapping primitives, significantly boosting prediction accuracy across architectures and configurations.
AgentRAN: An Agentic AI Architecture for Autonomous Control of Open 6G Networks
Paper ↗
Abstract
The Open RAN movement has catalyzed a transformation toward programmable, interoperable cellular infrastructures. Yet, today's deployments still rely heavily on static control and manual operations. To move beyond this limitation, we introduce AgenRAN, an AI-native, Open RAN-aligned agentic framework that generates and orchestrates a fabric of distributed AI agents based on Natural Language (NL) intents. Unlike traditional approaches that require explicit programming, AgentRAN's LLM-powered agents interpret natural language intents, negotiate strategies through structured conversations, and orchestrate control loops across the network. AgentRAN instantiates a self-organizing hierarchy of agents that decompose complex intents across time scales (from sub-millisecond to minutes), spatial domains (cell to network-wide), and protocol layers (PHY/MAC to RRC). A central innovation is the AI-RAN Factory, an automated synthesis pipeline that observes agent interactions and continuously generates new agents embedding improved control algorithms, effectively transforming the network from a static collection of functions into an adaptive system capable of evolving its own intelligence. We demonstrate AgentRAN through live experiments on 5G testbeds where competing user demands are dynamically balanced through cascading intents. By replacing rigid APIs with NL coordination, AgentRAN fundamentally redefines how future 6G networks autonomously interpret, adapt, and optimize their behavior to meet operator goals.
SEFRQO: A Self-Evolving Fine-Tuned RAG-Based Query Optimizer
Paper ↗
Abstract
Query optimization is a crucial problem in database systems that has been studied for decades. Learned query optimizers (LQOs) can improve performance over time by incorporating feedback; however, they suffer from cold-start issues and often require retraining when workloads shift or schemas change. Recent LLM-based query optimizers leverage pre-trained and fine-tuned LLMs to mitigate these challenges. Nevertheless, they neglect LLMs' in-context learning and execution records as feedback for continuous evolution. In this paper, we present SEFRQO, a Self-Evolving Fine-tuned RAG-based Query Optimizer. SEFRQO mitigates the cold-start problem of LQOs by continuously learning from execution feedback via a Retrieval-Augmented Generation (RAG) framework. We employ both supervised fine-tuning and reinforcement fine-tuning to prepare the LLM to produce syntactically correct and performance-efficient query hints. Moreover, SEFRQO leverages the LLM's in-context learning capabilities by dynamically constructing prompts with references to similar queries and the historical execution record of the same query. This self-evolving paradigm iteratively optimizes the prompt to minimize query execution latency. Evaluations show that SEFRQO outperforms state-of-the-art LQOs, achieving up to 65.05% and 93.57% reductions in query latency on the CEB and Stack workloads, respectively, compared to PostgreSQL.
ARSP: Automated Repair of Verilog Designs via Semantic Partitioning
Paper ↗
Abstract
Debugging functional Verilog bugs consumes a significant portion of front-end design time. While Large Language Models (LLMs) have demonstrated great potential in mitigating this effort, existing LLM-based automated debugging methods underperform on industrial-scale modules. A major reason for this is bug signal dilution in long contexts, where a few bug-relevant tokens are overwhelmed by hundreds of unrelated lines, diffusing the model's attention. To address this issue, we introduce ARSP, a two-stage system that mitigates dilution via semantics-guided fragmentation. A Partition LLM splits a module into semantically tight fragments; a Repair LLM patches each fragment; edits are merged without altering unrelated logic. A synthetic data framework generates fragment-level training pairs spanning bug types, design styles, and scales to supervise both models. Experiments show that ARSP achieves 77.92% pass@1 and 83.88% pass@5, outperforming mainstream commercial LLMs including Claude-3.7 and SOTA automated Verilog debugging tools Strider and MEIC. Also, semantic partitioning improves pass@1 by 11.6% and pass@5 by 10.2% over whole-module debugging, validating the effectiveness of fragment-level scope reduction in LLM-based Verilog debugging.
Fast and Accurate RFIC Performance Prediction via Pin Level Graph Neural Networks and Probabilistic Flow
Paper ↗
Abstract
Accurately predicting the performance of active radio frequency (RF) circuits is essential for modern wireless systems but remains challenging due to highly nonlinear, layout-sensitive behavior and the high computational cost of traditional simulation tools. Existing machine learning (ML) surrogates often require large datasets to generalize across various topologies or to accurately model skewed and multi-modal performance metrics. In this work, a lightweight, data-efficient, and topology-aware graph neural network (GNN) model is proposed for predicting key performance metrics of multiple topologies of active RF circuits such as low noise amplifiers (LNAs), mixers, voltage-controlled oscillators (VCOs), and PAs. To capture transistor-level symmetry and preserve fine-grained connectivity details, circuits are modeled at the device-terminal level, enabling scalable message passing while reducing data requirements. Masked autoregressive flow (MAF) output heads are incorporated to improve robustness in modeling complex target distributions. Experiments on datasets demonstrate high prediction accuracy, with symmetric mean absolute percentage error (sMAPE) and mean relative error (MRE) averaging 2.40% and 2.91%, respectively. Owing to the pin-level conversion of circuit to graph and ML architecture robust to modeling complex densities of RF metrics, the MRE is improved by 3.14x while using 2.24x fewer training samples compared to prior work, demonstrating the method's effectiveness for rapid and accurate RF circuit design automation.
Agentic AI Empowered Multi-UAV Trajectory Optimization in Low-Altitude Economy Networks
Paper ↗
Abstract
This paper proposes a novel Agentic Retrieval-augmented generation with Mamba-Attention Integrated Transformer (ARMAIT) framework for multi-Unmanned Aerial Vehicle (UAV) trajectory optimization. The framework is built upon Large Language Models (LLMs), incorporating Retrieval-Augmented Generation (RAG) empowered by Agentic AI and integrated with a UAV-specific knowledge base. Through the Agentic RAG, the LLM autonomously interprets high-level task requirements and identifies the key components necessary for trajectory optimization, including model inputs and outputs, network architecture, reward functions, and task constraints. To support efficient modeling across different system scales, we introduce the Mamba-Attention Integrated Transformer (MAIT), a hybrid neural architecture that combines the long-range dependency modeling capability of attention mechanisms with the efficient temporal dynamic representation of Mamba. Furthermore, a Trajectory-Group Relative Policy Optimization (T-GRPO) method is proposed to achieve unified policy gradient optimization in both discrete and continuous trajectory spaces for MAIT training. Extensive experimental results validate the feasibility and effectiveness of the proposed ARMAIT framework.
LLM-Assisted Semantic Alignment and Integration in Collaborative Model-Based Systems Engineering Using SysML v2
Paper ↗
Abstract
Cross-organizational collaboration in Model-Based Systems Engineering (MBSE) faces many challenges in achieving semantic alignment across independently developed system models. SysML v2 introduces enhanced structural modularity and formal semantics, offering a stronger foundation for interoperable modeling. Meanwhile, GPT-based Large Language Models (LLMs) provide new capabilities for assisting model understanding and integration. This paper proposes a structured, prompt-driven approach for LLM-assisted semantic alignment of SysML v2 models. The core contribution lies in the iterative development of an alignment approach and interaction prompts, incorporating model extraction, semantic matching, and verification. The approach leverages SysML v2 constructs such as alias, import, and metadata extensions to support traceable, soft alignment integration. It is demonstrated with a GPT-based LLM through an example of a measurement system. Benefits and limitations are discussed.
Leveraging Large Language Models to Detect Missed Peephole Optimizations
Paper ↗
Abstract
By replacing small, suboptimal instruction sequences within programs with a more efficient equivalent, peephole optimization can not only directly optimize code size and performance, but also potentially enables further transformations in the subsequent optimization pipeline. Although peephole optimization is a critical class of compiler optimizations, discovering new and effective peephole optimizations is challenging as the instruction sets can be extremely complex and diverse. Previous methods either do not scale well or can only capture a limited subset of peephole optimizations. In this work, we leverage Large Language Models (LLMs) to detect missed peephole optimizations. We propose Lampo, a novel automated framework that synergistically combines the creative but unreliable code optimization ability of LLMs with rigorous correctness verification performed by translation validation tools, integrated in a feedback-driven iterative process. Through a comprehensive evaluation within LLVM ecosystems, we show that Lampo can successfully detect up to 17 out of 25 previously reported missed optimizations in LLVM on average, and that 22 out of 25 can potentially be found by Lampo with different LLMs. For comparison, the state-of-the-art superoptimizer for LLVM, Souper, identified 15 of them. Moreover, within seven months of development and intermittent experiments, Lampo found 26 missed peephole optimizations, 15 of which have been confirmed and 6 already fixed. These results demonstrate Lampo's strong potential in continuously detecting missed peephole optimizations.
Congestion Control System Optimization with Large Language Models
Paper ↗
Abstract
Congestion control is a fundamental component of Internet infrastructure, and researchers have dedicated considerable effort to developing improved congestion control algorithms. However, despite extensive study, existing algorithms continue to exhibit suboptimal performance across diverse network environments. In this paper, we introduce a novel approach that automatically optimizes congestion control algorithms using large language models (LLMs). Our framework consists of a structured algorithm generation process, an emulation-based evaluation pipeline covering a broad range of network conditions, and a statistically guided method to substantially reduce evaluation time. Empirical results from four distinct LLMs validate the effectiveness of our approach. We successfully identify algorithms that achieve up to 27% performance improvements over the original BBR algorithm in a production QUIC implementation. Our work demonstrates the potential of LLMs to accelerate the design of high-performance network algorithms and paves the way for broader applications in networking systems.
MAAdvisor: Zero-Shot Index Advisor using Multi-Agent LLMs
Paper ↗
Abstract
Index recommendation is one of the most important problems in database management system (DBMS) optimization. Given queries and certain index-related constraints, traditional methods rely on heuristic optimization or learning-based models to select effective indexes and improve query performance. However, heuristic optimization suffers from high computation time, and learning-based models lose generalisability due to training for different workloads and database schemas. With the recent rapid development of large language models (LLMs), methods using prompt tuning have been proposed to enhance the efficiency of index selection. However, such methods still can not achieve the state-of-the-art (SOTA) results, and preparing the index selection demonstrations is also resource-intensive. To address these issues, we propose MAAdvisor, a zero-shot LLM-based index advisor with a multi-agent framework. We decompose the index recommendation problem into sub-steps, including planning, selection, combination, revision, and reflection. A set of LLM-embedded agents is designed to handle each one of the different sub-steps. Our method utilizes global agents to control the index selection process and local agents to select and revise indexes. Through extensive experiments, we show that our proposed MAAdvisor not only achieves the SOTA performance compared to the heuristic methods, but also outperforms learning-based and prompt-based methods with higher efficiency and better zero-shot inference ability.
Transfer Learning for Minimum Operating Voltage Prediction in Advanced Technology Nodes: Leveraging Legacy Data and Silicon Odometer Sensing
Paper ↗
Abstract
Accurate prediction of chip performance is critical for ensuring energy efficiency and reliability in semiconductor manufacturing. However, developing minimum operating voltage ($V_{min}$) prediction models at advanced technology nodes is challenging due to limited training data and the complex relationship between process variations and $V_{min}$. To address these issues, we propose a novel transfer learning framework that leverages abundant legacy data from the 16nm technology node to enable accurate $V_{min}$ prediction at the advanced 5nm node. A key innovation of our approach is the integration of input features derived from on-chip silicon odometer sensor data, which provide fine-grained characterization of localized process variations -- an essential factor at the 5nm node -- resulting in significantly improved prediction accuracy.
Transfer Learning for Minimum Operating Voltage Prediction in Advanced Technology Nodes: Leveraging Legacy Data and Silicon Odometer Sensing
Paper ↗
Abstract
Accurate prediction of chip performance is critical for ensuring energy efficiency and reliability in semiconductor manufacturing. However, developing minimum operating voltage ($V_{min}$) prediction models at advanced technology nodes is challenging due to limited training data and the complex relationship between process variations and $V_{min}$. To address these issues, we propose a novel transfer learning framework that leverages abundant legacy data from the 16nm technology node to enable accurate $V_{min}$ prediction at the advanced 5nm node. A key innovation of our approach is the integration of input features derived from on-chip silicon odometer sensor data, which provide fine-grained characterization of localized process variations -- an essential factor at the 5nm node -- resulting in significantly improved prediction accuracy.
ASIC-Agent: An Autonomous Multi-Agent System for ASIC Design with Benchmark Evaluation
Paper ↗
Abstract
Large Language Models (LLMs) have demonstrated remarkable capabilities in Register Transfer Level (RTL) design, enabling high-quality code generation from natural language descriptions. However, LLMs alone face significant limitations in real-world hardware design workflows, including the inability to execute code, lack of debugging capabilities, and absence of long-term memory. To address these challenges, we present ASIC-Agent, an autonomous system designed specifically for digital ASIC design tasks. ASIC-Agent enhances base LLMs with a multi-agent architecture incorporating specialized sub-agents for RTL generation, verification, OpenLane hardening, and Caravel chip integration, all operating within a comprehensive sandbox environment with access to essential hardware design tools. The system leverages a vector database containing documentation, API references, error knowledge, and curated insights from the open-source silicon community. To evaluate ASIC-Agent's performance, we introduce ASIC-Agent-Bench, the first benchmark specifically designed to assess agentic systems in hardware design tasks. We evaluate ASIC-Agent with various base LLMs, providing quantitative comparisons and qualitative insights into agent behavior across different design scenarios. Our results demonstrate that ASIC-Agent, when powered by Claude 4 Sonnet, successfully automates a broad range of ASIC design tasks spanning varying levels of complexity, showing the potential of significantly accelerating the ASIC design workflow.
Interface on demand: Towards AI native Control interfaces for 6G
Paper ↗
Abstract
Traditional standardized network interfaces face significant limitations, including vendor-specific incompatibilities, rigid design assumptions, and lack of adaptability for new functionalities. We propose a multi-agent framework leveraging large language models (LLMs) to generate control interfaces on demand between network functions (NFs). This includes a matching agent, which aligns required control functionalities with NF capabilities, and a code-generation agent, which generates the necessary API server for interface realization. We validate our approach using simulated multi-vendor gNB and WLAN AP environments. The performance evaluations highlight the trade-offs between cost and latency across LLMs for interface generation tasks. Our work sets the foundation for AI-native dynamic control interface generation, paving the way for enhanced interoperability and adaptability in future mobile networks.
Preguss: It Analyzes, It Specifies, It Verifies
Paper ↗
Abstract
Fully automated verification of large-scale software and hardware systems is arguably the holy grail of formal methods. Large language models (LLMs) have recently demonstrated their potential for enhancing the degree of automation in formal verification by, e.g., generating formal specifications as essential to deductive verification, yet exhibit poor scalability due to context-length limitations and, more importantly, the difficulty of inferring complex, interprocedural specifications. This paper outlines Preguss - a modular, fine-grained framework for automating the generation and refinement of formal specifications. Preguss synergizes between static analysis and deductive verification by orchestrating two components: (i) potential runtime error (RTE)-guided construction and prioritization of verification units, and (ii) LLM-aided synthesis of interprocedural specifications at the unit level. We envisage that Preguss paves a compelling path towards the automated verification of large-scale programs.
A Distributed Learned Hash Table
Paper ↗
Abstract
Distributed Hash Tables (DHTs) are pivotal in numerous high-impact key-value applications built on distributed networked systems, offering a decentralized architecture that avoids single points of failure and improves data availability. Despite their widespread utility, DHTs face substantial challenges in handling range queries, which are crucial for applications such as LLM serving, distributed storage, databases, content delivery networks, and blockchains. To address this limitation, we present LEAD, a novel system incorporating learned models within DHT structures to significantly optimize range query performance. LEAD utilizes a recursive machine learning model to map and retrieve data across a distributed system while preserving the inherent order of data. LEAD includes the designs to minimize range query latency and message cost while maintaining high scalability and resilience to network churn. Our comprehensive evaluations, conducted in both testbed implementation and simulations, demonstrate that LEAD achieves tremendous advantages in system efficiency compared to existing range query methods in large-scale distributed systems, reducing query latency and message cost by 80% to 90%+. Furthermore, LEAD exhibits remarkable scalability and robustness against system churn, providing a robust, scalable solution for efficient data retrieval in distributed key-value systems.
AI Agents for Photonic Integrated Circuit Design Automation
Paper ↗
Abstract
We present Photonics Intelligent Design and Optimization (PhIDO), a multi-agent framework that converts natural-language photonic integrated circuit (PIC) design requests into layout mask files. We compare 7 reasoning large language models for PhIDO using a testbench of 102 design descriptions that ranged from single devices to 112-component PICs. The success rate for single-device designs was up to 91%. For design queries with less than or equal to 15 components, o1, Gemini-2.5-pro, and Claude Opus 4 achieved the highest end-to-end pass@5 success rates of approximately 57%, with Gemini-2.5-pro requiring the fewest output tokens and lowest cost. The next steps toward autonomous PIC development include standardized knowledge representations, expanded datasets, extended verification, and robotic automation.
VerilogLAVD: LLM-Aided Rule Generation for Vulnerability Detection in Verilog
Paper ↗
Abstract
Timely detection of hardware vulnerabilities during the early design stage is critical for reducing remediation costs. Existing early detection techniques often require specialized security expertise, limiting their usability. Recent efforts have explored the use of large language models (LLMs) for Verilog vulnerability detection. However, LLMs struggle to capture the structure in Verilog code, resulting in inconsistent detection results. To this end, we propose VerilogLAVD, the first LLM-aided graph traversal rule generation approach for Verilog vulnerability detection. Our approach introduces the Verilog Property Graph (VeriPG), a unified representation of Verilog code. It combines syntactic features extracted from the abstract syntax tree (AST) with semantic information derived from control flow and data dependency graphs. We leverage LLMs to generate VeriPG-based detection rules from Common Weakness Enumeration (CWE) descriptions. These rules guide the rule executor that traversal VeriPG for potential vulnerabilities. To evaluate VerilogLAVD, we build a dataset collected from open-source repositories and synthesized data. In our empirical evaluation on 77 Verilog designs encompassing 12 CWE types, VerilogLAVD achieves an F1-score of 0.54. Compared to the LLM-only and LLM with external knowledge baselines, VerilogLAVD improves F1-score by 0.31 and 0.27, respectively.
ViTAD: Timing Violation-Aware Debugging of RTL Code using Large Language Models
Paper ↗
Abstract
In modern Very Large Scale Integrated (VLSI) circuit design flow, the Register-Transfer Level (RTL) stage presents a critical opportunity for timing optimization. Addressing timing violations at this early stage is essential, as modern systems demand higher speeds, where even minor timing violations can lead to functional failures or system crashes. However, traditional timing optimization heavily relies on manual expertise, requiring engineers to iteratively analyze timing reports and debug. To automate this process, this paper proposes ViTAD, a method that efficiently analyzes the root causes of timing violations and dynamically generates targeted repair strategies. Specifically, we first parse Verilog code and timing reports to construct a Signal Timing Dependency Graph (STDG). Based on the STDG, we perform violation path analysis and use large language models (LLMs) to infer the root causes of violations. Finally, by analyzing the causes of violations, we selectively retrieve relevant debugging knowledge from a domain-specific knowledge base to generate customized repair solutions. To evaluate the effectiveness of our method, we construct a timing violation dataset based on real-world open-source projects. This dataset contains 54 cases of violations. Experimental results show that our method achieves a 73.68% success rate in repairing timing violations, while the baseline using only LLM is 54.38%. Our method improves the success rate by 19.30%.
SecFSM: Knowledge Graph-Guided Verilog Code Generation for Secure Finite State Machines in Systems-on-Chip
Paper ↗
Abstract
Finite State Machines (FSMs) play a critical role in implementing control logic for Systems-on-Chip (SoC). Traditionally, FSMs are implemented by hardware engineers through Verilog coding, which is often tedious and time-consuming. Recently, with the remarkable progress of Large Language Models (LLMs) in code generation, LLMs have been increasingly explored for automating Verilog code generation. However, LLM-generated Verilog code often suffers from security vulnerabilities, which is particularly concerning for security-sensitive FSM implementations. To address this issue, we propose SecFSM, a novel method that leverages a security-oriented knowledge graph to guide LLMs in generating more secure Verilog code. Specifically, we first construct a FSM Security Knowledge Graph (FSKG) as an external aid to LLMs. Subsequently, we analyze users' requirements to identify vulnerabilities and get a list of vulnerabilities in the requirements. Then, we retrieve knowledge from FSKG based on the vulnerabilities list. Finally, we construct security prompts based on the security knowledge for Verilog code generation. To evaluate SecFSM, we build a dedicated dataset collected from academic datasets, artificial datasets, papers, and industrial cases. Extensive experiments demonstrate that SecFSM outperforms state-of-the-art baselines. In particular, on a benchmark of 25 security test cases evaluated by DeepSeek-R1, SecFSM achieves an outstanding pass rate of 21/25.
OS-R1: Agentic Operating System Kernel Tuning with Reinforcement Learning
Paper ↗
Abstract
Linux kernel tuning is essential for optimizing operating system (OS) performance. However, existing methods often face challenges in terms of efficiency, scalability, and generalization. This paper introduces OS-R1, an agentic Linux kernel tuning framework powered by rule-based reinforcement learning (RL). By abstracting the kernel configuration space as an RL environment, OS-R1 facilitates efficient exploration by large language models (LLMs) and ensures accurate configuration modifications. Additionally, custom reward functions are designed to enhance reasoning standardization, configuration modification accuracy, and system performance awareness of the LLMs. Furthermore, we propose a two-phase training process that accelerates convergence and minimizes retraining across diverse tuning scenarios. Experimental results show that OS-R1 significantly outperforms existing baseline methods, achieving up to 5.6% performance improvement over heuristic tuning and maintaining high data efficiency. Notably, OS-R1 is adaptable across various real-world applications, demonstrating its potential for practical deployment in diverse environments. Our dataset and code are publicly available at https://github.com/LHY-24/OS-R1.
GALA: Can Graph-Augmented Large Language Model Agentic Workflows Elevate Root Cause Analysis?
Paper ↗
Abstract
Root cause analysis (RCA) in microservice systems is challenging, requiring on-call engineers to rapidly diagnose failures across heterogeneous telemetry such as metrics, logs, and traces. Traditional RCA methods often focus on single modalities or merely rank suspect services, falling short of providing actionable diagnostic insights with remediation guidance. This paper introduces GALA, a novel multi-modal framework that combines statistical causal inference with LLM-driven iterative reasoning for enhanced RCA. Evaluated on an open-source benchmark, GALA achieves substantial improvements over state-of-the-art methods of up to 42.22% accuracy. Our novel human-guided LLM evaluation score shows GALA generates significantly more causally sound and actionable diagnostic outputs than existing methods. Through comprehensive experiments and a case study, we show that GALA bridges the gap between automated failure diagnosis and practical incident resolution by providing both accurate root cause identification and human-interpretable remediation guidance.
Modeling Relational Logic Circuits for And-Inverter Graph Convolutional Network
Paper ↗
Abstract
The automation of logic circuit design enhances chip performance, energy efficiency, and reliability, and is widely applied in the field of Electronic Design Automation (EDA).And-Inverter Graphs (AIGs) efficiently represent, optimize, and verify the functional characteristics of digital circuits, enhancing the efficiency of EDA development.Due to the complex structure and large scale of nodes in real-world AIGs, accurate modeling is challenging, leading to existing work lacking the ability to jointly model functional and structural characteristics, as well as insufficient dynamic information propagation capability.To address the aforementioned challenges, we propose AIGer.Specifically, AIGer consists of two components: 1) Node logic feature initialization embedding component and 2) AIGs feature learning network component.The node logic feature initialization embedding component projects logic nodes, such as AND and NOT, into independent semantic spaces, to enable effective node embedding for subsequent processing.Building upon this, the AIGs feature learning network component employs a heterogeneous graph convolutional network, designing dynamic relationship weight matrices and differentiated information aggregation approaches to better represent the original structure and information of AIGs.The combination of these two components enhances AIGer's ability to jointly model functional and structural characteristics and improves its message passing capability. Experimental results indicate that AIGer outperforms the current best models in the Signal Probability Prediction (SSP) task, improving MAE and MSE by 18.95\% and 44.44\%, respectively. In the Truth Table Distance Prediction (TTDP) task, AIGer achieves improvements of 33.57\% and 14.79\% in MAE and MSE, respectively, compared to the best-performing models.
From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation
Paper ↗
Abstract
Computer-Aided Design (CAD) plays a vital role in engineering and manufacturing, yet current CAD workflows require extensive domain expertise and manual modeling effort. Recent advances in large language models (LLMs) have made it possible to generate code from natural language, opening new opportunities for automating parametric 3D modeling. However, directly translating human design intent into executable CAD code remains highly challenging, due to the need for logical reasoning, syntactic correctness, and numerical precision. In this work, we propose CAD-RL, a multimodal Chain-of-Thought (CoT) guided reinforcement learning post training framework for CAD modeling code generation. Our method combines CoT-based Cold Start with goal-driven reinforcement learning post training using three task-specific rewards: executability reward, geometric accuracy reward, and external evaluation reward. To ensure stable policy learning under sparse and high-variance reward conditions, we introduce three targeted optimization strategies: Trust Region Stretch for improved exploration, Precision Token Loss for enhanced dimensions parameter accuracy, and Overlong Filtering to reduce noisy supervision. To support training and benchmarking, we release ExeCAD, a noval dataset comprising 16,540 real-world CAD examples with paired natural language and structured design language descriptions, executable CADQuery scripts, and rendered 3D models. Experiments demonstrate that CAD-RL achieves significant improvements in reasoning quality, output precision, and code executability over existing VLMs.
From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation
Paper ↗
Abstract
Computer-Aided Design (CAD) plays a vital role in engineering and manufacturing, yet current CAD workflows require extensive domain expertise and manual modeling effort. Recent advances in large language models (LLMs) have made it possible to generate code from natural language, opening new opportunities for automating parametric 3D modeling. However, directly translating human design intent into executable CAD code remains highly challenging, due to the need for logical reasoning, syntactic correctness, and numerical precision. In this work, we propose CAD-RL, a multimodal Chain-of-Thought (CoT) guided reinforcement learning post training framework for CAD modeling code generation. Our method combines CoT-based Cold Start with goal-driven reinforcement learning post training using three task-specific rewards: executability reward, geometric accuracy reward, and external evaluation reward. To ensure stable policy learning under sparse and high-variance reward conditions, we introduce three targeted optimization strategies: Trust Region Stretch for improved exploration, Precision Token Loss for enhanced dimensions parameter accuracy, and Overlong Filtering to reduce noisy supervision. To support training and benchmarking, we release ExeCAD, a noval dataset comprising 16,540 real-world CAD examples with paired natural language and structured design language descriptions, executable CADQuery scripts, and rendered 3D models. Experiments demonstrate that CAD-RL achieves significant improvements in reasoning quality, output precision, and code executability over existing VLMs.
LLMLog: Advanced Log Template Generation via LLM-driven Multi-Round Annotation
Paper ↗
Abstract
Modern computing systems, such as HDFS and Spark, produce vast quantities of logs that developers use for tasks like anomaly detection and error analysis. To simplify log analysis, template generation methods have been proposed to standardize log formats, transforming unstructured data into structured templates. Existing heuristic-based methods and neural network-based methods suffer from low accuracy problems due to the reliance on handcrafted heuristics or specific log patterns in training sets. Recently, large language models (LLMs) have shown great potential in log template generation. However, they often struggle with ambiguous, complex, or highly specific log content, which can lead to errors in generating accurate templates. To address these challenges, we propose LLMLog, a multi-round annotation framework with adaptive in-context learning. We first propose an edit-distance-based similarity metric to evaluate log similarity. Then, we introduce a method to select the most informative $k$ unlabeled logs for annotation by considering both the representativeness of the logs and the confidence of LLM predictions. Additionally, we design an adaptive context selection strategy that adaptively selects labeled logs to ensure comprehensive keyword coverage for unlabeled logs. These labeled logs serve as the context for LLMs to better understand the unlabeled logs, thereby enhancing the accuracy of template generation. Extensive experiments on sixteen datasets demonstrate that LLMLog outperforms the state-of-the-art approaches.
E3-Rewrite: Learning to Rewrite SQL for Executability, Equivalence,and Efficiency
Paper ↗
Abstract
SQL query rewriting aims to reformulate a query into a more efficient form while preserving equivalence. Most existing methods rely on predefined rewrite rules. However, such rule-based approaches face fundamental limitations: (1) fixed rule sets generalize poorly to novel query patterns and struggle with complex queries; (2) a wide range of effective rewriting strategies cannot be fully captured by declarative rules. To overcome these issues, we propose using large language models (LLMs) to generate rewrites. LLMs can capture complex strategies, such as evaluation reordering and CTE rewriting. Despite this potential, directly applying LLMs often results in suboptimal or non-equivalent rewrites due to a lack of execution awareness and semantic grounding. To address these challenges, We present E3-Rewrite, an LLM-based SQL rewriting framework that produces executable, equivalent, and efficient queries. It integrates two core components: a context construction module and a reinforcement learning framework. First, the context module leverages execution plans and retrieved demonstrations to build bottleneck-aware prompts that guide inference-time rewriting. Second, we design a reward function targeting executability, equivalence, and efficiency, evaluated via syntax checks, equivalence verification, and cost estimation. Third, to ensure stable multi-objective learning, we adopt a staged curriculum that first emphasizes executability and equivalence, then gradually incorporates efficiency. Extensive experiments show that E3-Rewrite achieves up to a 25.6\% reduction in query execution time compared to state-of-the-art methods across multiple SQL benchmarks. Moreover, it delivers up to 24.4\% more successful rewrites, expanding coverage to complex queries that previous systems failed to handle.
CRADLE: Conversational RTL Design Space Exploration with LLM-based Multi-Agent Systems
Paper ↗
Abstract
This paper presents CRADLE, a conversational framework for design space exploration of RTL designs using LLM-based multi-agent systems. Unlike existing rigid approaches, CRADLE enables user-guided flows with internal self-verification, correction, and optimization. We demonstrate the framework with a generator-critic agent system targeting FPGA resource minimization using state-of-the-art LLMs. Experimental results on the RTLLM benchmark show that CRADLE achieves significant reductions in resource usage with averages of 48% and 40% in LUTs and FFs across all benchmark designs.
LLM-Driven Adaptive 6G-Ready Wireless Body Area Networks: Survey and Framework
Paper ↗
Abstract
Wireless Body Area Networks (WBANs) enable continuous monitoring of physiological signals for applications ranging from chronic disease management to emergency response. Recent advances in 6G communications, post-quantum cryptography, and energy harvesting have the potential to enhance WBAN performance. However, integrating these technologies into a unified, adaptive system remains a challenge. This paper surveys some of the most well-known Wireless Body Area Network (WBAN) architectures, routing strategies, and security mechanisms, identifying key gaps in adaptability, energy efficiency, and quantum-resistant security. We propose a novel Large Language Model-driven adaptive WBAN framework in which a Large Language Model acts as a cognitive control plane, coordinating routing, physical layer selection, micro-energy harvesting, and post-quantum security in real time. Our review highlights the limitations of current heuristic-based designs and outlines a research agenda for resource-constrained, 6G-ready medical systems. This approach aims to enable ultra-reliable, secure, and self-optimizing WBANs for next-generation mobile health applications.
MuaLLM: A Multimodal Large Language Model Agent for Circuit Design Assistance with Hybrid Contextual Retrieval-Augmented Generation
Paper ↗
Abstract
Conducting a comprehensive literature review is crucial for advancing circuit design methodologies. However, the rapid influx of state-of-the-art research, inconsistent data representation, and the complexity of optimizing circuit design objectives make this task significantly challenging. In this paper, we propose MuaLLM, an open-source multimodal Large Language Model (LLM) agent for circuit design assistance that integrates a hybrid Retrieval-Augmented Generation (RAG) framework with an adaptive vector database of circuit design research papers. Unlike conventional LLMs, the MuaLLM agent employs a Reason + Act (ReAct) workflow for iterative reasoning, goal-setting, and multi-step information retrieval. It functions as a question-answering design assistant, capable of interpreting complex queries and providing reasoned responses grounded in circuit literature. Its multimodal capabilities enable processing of both textual and visual data, facilitating more efficient and comprehensive analysis. The system dynamically adapts using intelligent search tools, automated document retrieval from the internet, and real-time database updates. Unlike conventional approaches constrained by model context limits, MuaLLM decouples retrieval from inference, enabling scalable reasoning over arbitrarily large corpora. At the maximum context length supported by standard LLMs, MuaLLM remains up to 10x less costly and 1.6x faster while maintaining the same accuracy. This allows rapid, no-human-in-the-loop database generation, overcoming the bottleneck of simulation-based dataset creation for circuits. To evaluate MuaLLM, we introduce two custom datasets: RAG-250, targeting retrieval and citation performance, and Reasoning-100 (Reas-100), focused on multistep reasoning in circuit design. MuaLLM achieves 90.1% recall on RAG-250, and 86.8% accuracy on Reas-100.
ELF: Efficient Logic Synthesis by Pruning Redundancy in Refactoring
Paper ↗
Abstract
In electronic design automation, logic optimization operators play a crucial role in minimizing the gate count of logic circuits. However, their computation demands are high. Operators such as refactor conventionally form iterative cuts for each node, striving for a more compact representation - a task which often fails 98% on average. Prior research has sought to mitigate computational cost through parallelization. In contrast, our approach leverages a classifier to prune unsuccessful cuts preemptively, thus eliminating unnecessary resynthesis operations. Experiments on the refactor operator using the EPFL benchmark suite and 10 large industrial designs demonstrate that this technique can speedup logic optimization by 3.9x on average compared with the state-of-the-art ABC implementation.
Maximizing GPU Efficiency via Optimal Adapter Caching: An Analytical Approach for Multi-Tenant LLM Serving
Paper ↗
Abstract
Serving LLM adapters has gained significant attention as an effective approach to adapt general-purpose language models to diverse, task-specific use cases. However, serving a wide range of adapters introduces several and substantial overheads, leading to performance degradation and challenges in optimal placement. To address these challenges, we present an analytical, AI-driven pipeline that accurately determines the optimal allocation of adapters in single-node setups. This allocation maximizes performance, effectively using GPU resources, while preventing request starvation. Crucially, the proposed allocation is given based on current workload patterns. These insights in single-node setups can be leveraged in multi-replica deployments for overall placement, load balancing and server configuration, ultimately enhancing overall performance and improving resource efficiency. Our approach builds on an in-depth analysis of LLM adapter serving, accounting for overheads and performance variability, and includes the development of the first Digital Twin capable of replicating online LLM-adapter serving systems with matching key performance metrics. The experimental results demonstrate that the Digital Twin achieves a SMAPE difference of no more than 5.5% in throughput compared to real results, and the proposed pipeline accurately predicts the optimal placement with minimal latency.
AutoAssert 1: A LoRA Fine-Tuned LLM Model for Efficient Automated Assertion Generation
Paper ↗
Abstract
As the complexity of software systems continues to increase, the demand for automated testing and maintenance tools is growing exponentially. To meet this urgent need, we propose a new assertion generation method based on Hardware Description Language (HDL). This method combines a lightweight, parameter-adjustable large language model (LLM) with the Unsloth platform to automatically generate test cases, thereby significantly reducing training costs without sacrificing accuracy or generalization performance. Empirical evaluation shows that our method can efficiently generate assertions that strictly conform to the hardware logic. This framework provides a robust and flexible solution to modern software testing and maintenance challenges. https://github.com/liusu-orange/AutoAssert-1 and https://gitee.com/OpenBPU/auto-assert1 are the locations of the source code.
Integrating Rules and Semantics for LLM-Based C-to-Rust Translation
Paper ↗
Abstract
Automated translation of legacy C code into Rust aims to ensure memory safety while reducing the burden of manual migration. Early approaches in code translation rely on static rule-based methods, but they suffer from limited coverage due to dependence on predefined rule patterns. Recent works regard the task as a sequence-to-sequence problem by leveraging large language models (LLMs). Although these LLM-based methods are capable of reducing unsafe code blocks, the translated code often exhibits issues in following Rust rules and maintaining semantic consistency. On one hand, existing methods adopt a direct prompting strategy to translate the C code, which struggles to accommodate the syntactic rules between C and Rust. On the other hand, this strategy makes it difficult for LLMs to accurately capture the semantics of complex code. To address these challenges, we propose IRENE, an LLM-based framework that Integrates RulEs aNd sEmantics to enhance translation. IRENE consists of three modules: 1) a rule-augmented retrieval module that selects relevant translation examples based on rules generated from a static analyzer developed by us, thereby improving the handling of Rust rules; 2) a structured summarization module that produces a structured summary for guiding LLMs to enhance the semantic understanding of C code; 3) an error-driven translation module that leverages compiler diagnostics to iteratively refine translations. We evaluate IRENE on two datasets (xCodeEval, a public dataset, and HW-Bench, an industrial dataset provided by Huawei) and eight LLMs, focusing on translation accuracy and safety.
White-Box Reasoning: Synergizing LLM Strategy and gm/Id Data for Automated Analog Circuit Design
Paper ↗
Abstract
Analog IC design is a bottleneck due to its reliance on experience and inefficient simulations, as traditional formulas fail in advanced nodes. Applying Large Language Models (LLMs) directly to this problem risks mere "guessing" without engineering principles. We present a "synergistic reasoning" framework that integrates an LLM's strategic reasoning with the physical precision of the gm/Id methodology. By empowering the LLM with gm/Id lookup tables, it becomes a quantitative, data-driven design partner. We validated this on a two-stage op-amp, where our framework enabled the Gemini model to meet all TT corner specs in 5 iterations and extended optimization to all PVT corners. A crucial ablation study proved gm/Id data is key for this efficiency and precision; without it, the LLM is slower and deviates. Compared to a senior engineer's design, our framework achieves quasi-expert quality with an order-of-magnitude improvement in efficiency. This work validates a path for true analog design automation by combining LLM reasoning with scientific circuit design methodologies.
Generative AI for Intent-Driven Network Management in 6G: A Case Study on Hierarchical Learning Approach
Paper ↗
Abstract
With the emergence of 6G, mobile networks are becoming increasingly heterogeneous and dynamic, necessitating advanced automation for efficient management. Intent-Driven Networks (IDNs) address this by translating high-level intents into optimization policies. Large Language Models (LLMs) can enhance this process by understanding complex human instructions to enable adaptive, intelligent automation. Given the rapid advancements in Generative AI (GenAI), a comprehensive survey of LLM-based IDN architectures in disaggregated Radio Access Network (RAN) environments is both timely and critical. This article provides such a survey, along with a case study on a hierarchical learning-enabled IDN architecture that integrates GenAI across three key stages: intent processing, intent validation, and intent execution. Unlike most existing approaches that apply GenAI in the form of LLMs for intent processing only, we propose a hierarchical framework that introduces GenAI across all three stages of IDN. To demonstrate the effectiveness of the proposed IDN management architecture, we present a case study based on the latest GenAI architecture named Mamba. The case study shows how the proposed GenAI-driven architecture enhances network performance through intelligent automation, surpassing the performance of the conventional IDN architectures.
MX-AI: Agentic Observability and Control Platform for Open and AI-RAN
Paper ↗
Abstract
Future 6G radio access networks (RANs) will be artificial intelligence (AI)-native: observed, reasoned about, and re-configured by autonomous agents cooperating across the cloud-edge continuum. We introduce MX-AI, the first end-to-end agentic system that (i) instruments a live 5G Open RAN testbed based on OpenAirInterface (OAI) and FlexRIC, (ii) deploys a graph of Large-Language-Model (LLM)-powered agents inside the Service Management and Orchestration (SMO) layer, and (iii) exposes both observability and control functions for 6G RAN resources through natural-language intents. On 50 realistic operational queries, MX-AI attains a mean answer quality of 4.1/5.0 and 100 % decision-action accuracy, while incurring only 8.8 seconds end-to-end latency when backed by GPT-4.1. Thus, it matches human-expert performance, validating its practicality in real settings. We publicly release the agent graph, prompts, and evaluation harness to accelerate open research on AI-native RANs. A live demo is presented here: https://www.youtube.com/watch?v=CEIya7988Ug&t=285s&ab_channel=BubbleRAN
Meta-Learning for Speeding Up Large Model Inference in Decentralized Environments
Paper ↗
Abstract
The deployment of large-scale models, such as large language models (LLMs), incurs substantial costs due to their computational demands. To mitigate these costs and address challenges related to scalability and data security, there is a growing shift towards decentralized systems for model deployment, where choosing efficient inference acceleration schemes become crucial to manage computational resources effectively and enhance system responsiveness. In this work, we address the challenge of selecting optimal acceleration methods in decentralized systems by introducing a meta-learning-based framework. This framework automates the selection process by learning from historical performance data of various acceleration techniques across different tasks. Unlike traditional methods that rely on random selection or expert intuition, our approach systematically identifies the best acceleration strategies based on the specific characteristics of each task. We demonstrate that our meta-learning framework not only streamlines the decision-making process but also consistently outperforms conventional methods in terms of efficiency and performance. Our results highlight the potential of inference acceleration in decentralized AI systems, offering a path towards more democratic and economically feasible artificial intelligence solutions.
ArchXBench: A Complex Digital Systems Benchmark Suite for LLM Driven RTL Synthesis
Paper ↗
Abstract
Modern SoC datapaths include deeply pipelined, domain-specific accelerators, but their RTL implementation and verification are still mostly done by hand. While large language models (LLMs) exhibit advanced code-generation abilities for programming languages like Python, their application to Verilog-like RTL remains in its nascent stage. This is reflected in the simple arithmetic and control circuits currently used to evaluate generative capabilities in existing benchmarks. In this paper, we introduce ArchXBench, a six-level benchmark suite that encompasses complex arithmetic circuits and other advanced digital subsystems drawn from domains such as cryptography, image processing, machine learning, and signal processing. Architecturally, some of these designs are purely combinational, others are multi-cycle or pipelined, and many require hierarchical composition of modules. For each benchmark, we provide a problem description, design specification, and testbench, enabling rapid research in the area of LLM-driven agentic approaches for complex digital systems design. Using zero-shot prompting with Claude Sonnet 4, GPT 4.1, o4-mini-high, and DeepSeek R1 under a pass@5 criterion, we observed that o4-mini-high successfully solves the largest number of benchmarks, 16 out of 30, spanning Levels 1, 2, and 3. From Level 4 onward, however, all models consistently fail, highlighting a clear gap in the capabilities of current state-of-the-art LLMs and prompting/agentic approaches.
MAHL: Multi-Agent LLM-Guided Hierarchical Chiplet Design with Adaptive Debugging
Paper ↗
Abstract
As program workloads (e.g., AI) increase in size and algorithmic complexity, the primary challenge lies in their high dimensionality, encompassing computing cores, array sizes, and memory hierarchies. To overcome these obstacles, innovative approaches are required. Agile chip design has already benefited from machine learning integration at various stages, including logic synthesis, placement, and routing. With Large Language Models (LLMs) recently demonstrating impressive proficiency in Hardware Description Language (HDL) generation, it is promising to extend their abilities to 2.5D integration, an advanced technique that saves area overhead and development costs. However, LLM-driven chiplet design faces challenges such as flatten design, high validation cost and imprecise parameter optimization, which limit its chiplet design capability. To address this, we propose MAHL, a hierarchical LLM-based chiplet design generation framework that features six agents which collaboratively enable AI algorithm-hardware mapping, including hierarchical description generation, retrieval-augmented code generation, diverseflow-based validation, and multi-granularity design space exploration. These components together enhance the efficient generation of chiplet design with optimized Power, Performance and Area (PPA). Experiments show that MAHL not only significantly improves the generation accuracy of simple RTL design, but also increases the generation accuracy of real-world chiplet design, evaluated by Pass@5, from 0 to 0.72 compared to conventional LLMs under the best-case scenario. Compared to state-of-the-art CLARIE (expert-based), MAHL achieves comparable or even superior PPA results under certain optimization objectives.
Optimizing Prompt Sequences using Monte Carlo Tree Search for LLM-Based Optimization
Paper ↗
Abstract
Large language models (LLMs) have demonstrated remarkable capabilities in code generation and structured reasoning; however, their performance often degrades on complex tasks that require consistent multi-step planning. Recent work has explored combining LLMs with Monte Carlo Tree Search (MCTS), yet existing approaches primarily focus on generating heuristic-based code for optimization or target simpler tasks where correctness alone is sufficient. In this work, we propose MCTS-OPS, a novel neural-symbolic framework that formulates prompt selection as a sequential decision process guided by MCTS. Our method explores and refines multi-step prompt sequences for the goal of improving code generation quality and enhancing the problem-solving capabilities of LLMs in general optimization. Experiments on network optimization show significant improvement over the baselines, both in the success rate of executing the generated code and in the optimization results with the specified objective and constraints (2$\sim$4$\times$ higher reward and 3$\times$ lower standard deviation). Moreover, it improves the chance of attaining the optimal solution by about 10\% of cases, compared to baseline methods in hard problems. These results highlight the promise of combining symbolic planning with LLMs for robust, high-quality code generation in complex domains.
Understanding and Mitigating Errors of LLM-Generated RTL Code
Paper ↗
Abstract
Despite the promising potential of large language model (LLM) based register-transfer-level (RTL) code generation, the overall success rate remains unsatisfactory. Errors arise from various factors, with limited understanding of specific failure causes hindering improvement. To address this, we conduct a comprehensive error analysis and manual categorization. Our findings reveal that most errors stem not from LLM reasoning limitations, but from insufficient RTL programming knowledge, poor understanding of circuit concepts, ambiguous design descriptions, or misinterpretation of complex multimodal inputs. Leveraging in-context learning, we propose targeted error correction techniques. Specifically, we construct a domain-specific knowledge base and employ retrieval-augmented generation (RAG) to supply necessary RTL knowledge. To mitigate ambiguity errors, we introduce design description rules and implement a rule-checking mechanism. For multimodal misinterpretation, we integrate external tools to convert inputs into LLM-compatible meta-formats. For remaining errors, we adopt an iterative debugging loop (simulation-error localization-correction). Integrating these techniques into an LLM-based framework significantly improves performance. We incorporate these error correction techniques into a foundational LLM-based RTL code generation framework, resulting in significantly improved performance. Experimental results show that our enhanced framework achieves 91.0\% accuracy on the VerilogEval benchmark, surpassing the baseline code generation approach by 32.7\%, demonstrating the effectiveness of our methods.
EasySize: Elastic Analog Circuit Sizing via LLM-Guided Heuristic Search
Paper ↗
Abstract
Analog circuit design is a time-consuming, experience-driven task in chip development. Despite advances in AI, developing universal, fast, and stable gate sizing methods for analog circuits remains a significant challenge. Recent approaches combine Large Language Models (LLMs) with heuristic search techniques to enhance generalizability, but they often depend on large model sizes and lack portability across different technology nodes. To overcome these limitations, we propose EasySize, the first lightweight gate sizing framework based on a finetuned Qwen3-8B model, designed for universal applicability across process nodes, design specifications, and circuit topologies. EasySize exploits the varying Ease of Attainability (EOA) of performance metrics to dynamically construct task-specific loss functions, enabling efficient heuristic search through global Differential Evolution (DE) and local Particle Swarm Optimization (PSO) within a feedback-enhanced flow. Although finetuned solely on 350nm node data, EasySize achieves strong performance on 5 operational amplifier (Op-Amp) netlists across 180nm, 45nm, and 22nm technology nodes without additional targeted training, and outperforms AutoCkt, a widely-used Reinforcement Learning based sizing framework, on 86.67\% of tasks with more than 96.67\% of simulation resources reduction. We argue that EasySize can significantly reduce the reliance on human expertise and computational resources in gate sizing, thereby accelerating and simplifying the analog circuit design process. EasySize will be open-sourced at a later date.
Semantic Reasoning Meets Numerical Precision: An LLM-Powered Multi-Agent System for Power Grid Control
Paper ↗
Abstract
The increasing penetration of Distributed Energy Resources (DERs), widespread adoption of Electric Vehicles (EVs), and the growing frequency of extreme weather events have significantly increased the complexity of power grid planning, operation, and management. Traditional rule-based systems and numerical optimization approaches often struggle with the scale, dynamics, and adaptability required by modern power networks. This paper introduces Grid-Agent, an autonomous, AI-driven framework that combines Large Language Models (LLMs) with multi-agent reinforcement learning to detect and remediate grid violations in real time. Grid-Agent integrates semantic reasoning with numerical precision through a modular agent architecture: a planning agent generates coordinated action sequences using numerical power flow solvers, while a validation agent evaluates system stability and action effectiveness via sandboxed execution with safety rollbacks. To ensure scalability, Grid-Agent incorporates an adaptive multiscale network representation that dynamically selects optimal encoding schemes based on network size and complexity. The framework enables coordinated violation resolution through optimizing switch configurations, battery deployment, and load curtailment strategies. Experimental results in standard IEEE and CIGRE test systems (IEEE 69-bus, CIGRE MV, and IEEE 30-bus) demonstrate superior violation mitigation performance. Additionally, the framework's built-in data collection and learning capabilities enable continuous learning and adaptation to diverse network topologies. The autonomous nature of the framework makes it particularly suitable for modern smart grid applications requiring rapid response to dynamic operating conditions.
Circuit-Aware SAT Solving: Guiding CDCL via Conditional Probabilities
Paper ↗
Abstract
Circuit Satisfiability (CSAT) plays a pivotal role in Electronic Design Automation. The standard workflow for solving CSAT problems converts circuits into Conjunctive Normal Form (CNF) and employs generic SAT solvers powered by Conflict-Driven Clause Learning (CDCL). However, this process inherently discards rich structural and functional information, leading to suboptimal solver performance. To address this limitation, we introduce CASCAD, a novel circuit-aware SAT solving framework that directly leverages circuit-level conditional probabilities computed via Graph Neural Networks (GNNs). By explicitly modeling gate-level conditional probabilities, CASCAD dynamically guides two critical CDCL heuristics -- variable phase selection and clause managementto significantly enhance solver efficiency. Extensive evaluations on challenging real-world Logical Equivalence Checking (LEC) benchmarks demonstrate that CASCAD reduces solving times by up to 10x compared to state-of-the-art CNF-based approaches, achieving an additional 23.5% runtime reduction via our probability-guided clause filtering strategy. Our results underscore the importance of preserving circuit-level structural insights within SAT solvers, providing a robust foundation for future improvements in SAT-solving efficiency and EDA tool design.
ReFuzzer: Feedback-Driven Approach to Enhance Validity of LLM-Generated Test Programs
Paper ↗
Abstract
Existing LLM-based compiler fuzzers often produce syntactically or semantically invalid test programs, limiting their effectiveness in exercising compiler optimizations and backend components. We introduce ReFuzzer, a framework for refining LLM-generated test programs by systematically detecting and correcting compilation and runtime violations (e.g. division by zero or array out-of-bounds accesses). ReFuzzer employs a feedback loop with a local LLM to validate and filter erroneous programs before execution, improving fuzzing effectiveness beyond crash detection and enabling the generation of diverse yet valid test programs. We evaluated ReFuzzer's effectiveness across black-, grey- and white-box fuzzing approaches targeting LLVM/Clang. ReFuzzer improved test programs' validity from 47.0-49.4% to 96.6-97.3%, with an average processing time of 2.9-3.5 s per test program on a dual-GPU machine. Further, refuzzing significantly increased code coverage in critical optimization and IR generation components. For example, vectorization coverage had an absolute improvement of 9.2%, 2.3%, and 7.1% in black-, grey-, and white-box fuzzing, enhancing testing effectiveness.
SAGE-HLS: Syntax-Aware AST-Guided LLM for High-Level Synthesis Code Generation
Paper ↗
Abstract
In today's rapidly evolving field of electronic design automation (EDA), the complexity of hardware designs is increasing, necessitating more sophisticated automation solutions. High-level synthesis (HLS), as a pivotal solution, automates hardware designs from high-level abstractions (e.g., C/C++). However, it faces significant challenges, particularly in design space exploration and optimization. While large language models (LLMs) have shown notable capabilities in code generation, their application to HLS has been limited due to the scarcity of (publicly) available HLS code datasets. Hence, research in this domain has primarily focused on techniques such as prompt engineering and retrieval-augmented generation (RAG). To overcome this limitation, this paper introduces SAGE-HLS, the first-of-its-kind fine-tuned LLM specifically for HLS code generation. Our method includes three key advancements: (i) We implement Verilog-to-C/C++ porting, converting verified and synthesizable Verilog codes into corresponding C, creating a dataset of 16.7K HLS codes; (ii) We implement a fine-tuning strategy, which is based on instruction prompting to code generation guided by abstract syntax tree (AST); (iii) We develop a semi-automated evaluation framework using VerilogEval to assess the functionality of the generated HLS code. Our experiments show that SAGE-HLS, fined-tuned on the QwenCoder (2.5) 7B model, achieves a near 100% success rate in code synthesizability and a 75% success rate in functional correctness.
Data Dependency Inference for Industrial Code Generation Based on UML Sequence Diagrams
Paper ↗
Abstract
Large language models (LLMs) excel at generating code from natural language (NL) descriptions. However, the plain textual descriptions are inherently ambiguous and often fail to capture complex requirements like intricate system behaviors, conditional logic, and architectural constraints; implicit data dependencies in service-oriented architectures are difficult to infer and handle correctly. To bridge this gap, we propose a novel step-by-step code generation framework named UML2Dep by leveraging unambiguous formal specifications of complex requirements. First, we introduce an enhanced Unified Modeling Language (UML) sequence diagram tailored for service-oriented architectures. This diagram extends traditional visual syntax by integrating decision tables and API specifications, explicitly formalizing structural relationships and business logic flows in service interactions to rigorously eliminate linguistic ambiguity. Second, recognizing the critical role of data flow, we introduce a dedicated data dependency inference (DDI) task. DDI systematically constructs an explicit data dependency graph prior to actual code synthesis. To ensure reliability, we formalize DDI as a constrained mathematical reasoning task through novel prompting strategies, aligning with LLMs' excellent mathematical strengths. Additional static parsing and dependency pruning further reduce context complexity and cognitive load associated with intricate specifications, thereby enhancing reasoning accuracy and efficiency.
Agoran: An Agentic Open Marketplace for 6G RAN Automation
Paper ↗
Abstract
Next-generation mobile networks must reconcile the often-conflicting goals of multiple service owners. However, today's network slice controllers remain rigid, policy-bound, and unaware of the business context. We introduce Agoran Service and Resource Broker (SRB), an agentic marketplace that brings stakeholders directly into the operational loop. Inspired by the ancient Greek agora, Agoran distributes authority across three autonomous AI branches: a Legislative branch that answers compliance queries using retrieval-augmented Large Language Models (LLMs); an Executive branch that maintains real-time situational awareness through a watcher-updated vector database; and a Judicial branch that evaluates each agent message with a rule-based Trust Score, while arbitrating LLMs detect malicious behavior and apply real-time incentives to restore trust. Stakeholder-side Negotiation Agents and the SRB-side Mediator Agent negotiate feasible, Pareto-optimal offers produced by a multi-objective optimizer, reaching a consensus intent in a single round, which is then deployed to Open and AI RAN controllers. Deployed on a private 5G testbed and evaluated with realistic traces of vehicle mobility, Agoran achieved significant gains: (i) a 37% increase in throughput of eMBB slices, (ii) a 73% reduction in latency of URLLC slices, and concurrently (iii) an end-to-end 8.3% saving in PRB usage compared to a static baseline. An 1B-parameter Llama model, fine-tuned for five minutes on 100 GPT-4 dialogues, recovers approximately 80% of GPT-4.1's decision quality, while operating within 6 GiB of memory and converging in only 1.3 seconds. These results establish Agoran as a concrete, standards-aligned path toward ultra-flexible, stakeholder-centric 6G networks. A live demo is presented https://www.youtube.com/watch?v=h7vEyMu2f5w\&ab_channel=BubbleRAN.
Adaptive AI Agent Placement and Migration in Edge Intelligence Systems
Paper ↗
Abstract
The rise of LLMs such as ChatGPT and Claude fuels the need for AI agents capable of real-time task handling. However, migrating data-intensive, multi-modal edge workloads to cloud data centers, traditionally used for agent deployment, introduces significant latency. Deploying AI agents at the edge improves efficiency and reduces latency. However, edge environments present challenges due to limited and heterogeneous resources. Maintaining QoS for mobile users necessitates agent migration, which is complicated by the complexity of AI agents coordinating LLMs, task planning, memory, and external tools. This paper presents the first systematic deployment and management solution for LLM-based AI agents in dynamic edge environments. We propose a novel adaptive framework for AI agent placement and migration in edge intelligence systems. Our approach models resource constraints and latency/cost, leveraging ant colony algorithms and LLM-based optimization for efficient decision-making. It autonomously places agents to optimize resource utilization and QoS and enables lightweight agent migration by transferring only essential state. Implemented on a distributed system using AgentScope and validated across globally distributed edge servers, our solution significantly reduces deployment latency and migration costs.
Principle-Guided Verilog Optimization: IP-Safe Knowledge Transfer via Local-Cloud Collaboration
Paper ↗
Abstract
Recent years have witnessed growing interest in adopting large language models (LLMs) for Register Transfer Level (RTL) code optimization. While powerful cloud-based LLMs offer superior optimization capabilities, they pose unacceptable intellectual property (IP) leakage risks when processing proprietary hardware designs. In this paper, we propose a new scenario where Verilog code must be optimized for specific attributes without leaking sensitive IP information. We introduce the first IP-preserving edge-cloud collaborative framework that leverages the benefits of both paradigms. Our approach employs local small LLMs (e.g., Qwen-2.5-Coder-7B) to perform secure comparative analysis between paired high-quality target designs and novice draft codes, yielding general design principles that summarize key insights for improvements. These principles are then used to query stronger cloud LLMs (e.g., Deepseek-V3) for targeted code improvement, ensuring that only abstracted and IP-safe guidance reaches external services. Our experimental results demonstrate that the framework achieves significantly higher optimization success rates compared to baseline methods. For example, combining Qwen-2.5-Coder-7B and Deepseek-V3 achieves a 66.67\% optimization success rate for power utilization, outperforming Deepseek-V3 alone (49.81\%) and even commercial models like GPT-4o (55.81\%). Further investigation of local and cloud LLM combinations reveals that different model pairings exhibit varying strengths for specific optimization objectives, with interesting trends emerging when varying the number of comparative code pairs. Our work establishes a new paradigm for secure hardware design optimization that balances performance gains with IP protection.
AnalogCoder-Pro: Unifying Analog Circuit Generation and Optimization via Multi-modal LLMs
Paper ↗
Abstract
Despite advances in analog design automation, analog front-end design still heavily depends on expert intuition and iterative simulations, underscoring critical gaps in fully automated optimization for performance-critical applications. Recently, the rapid development of Large Language Models (LLMs) has brought new promise to analog design automation. However, existing work remains in its early stages, and holistic joint optimization for practical end-to-end solutions remains largely unexplored. We propose AnalogCoder-Pro, a unified multimodal LLM-based framework that integrates generative capabilities and optimization techniques to jointly explore circuit topologies and optimize device sizing, automatically generating performance-specific, fully sized schematic netlists. AnalogCoder-Pro employs rejection sampling for fine-tuning LLMs on high-quality synthesized circuit data and introduces a multimodal diagnosis and repair workflow based on functional specifications and waveform images. By leveraging LLMs to interpret generated circuit netlists, AnalogCoder-Pro automates the extraction of critical design parameters and the formulation of parameter spaces, establishing an end-to-end workflow for simultaneous topology generation and device sizing optimization. Extensive experiments demonstrate that these orthogonal approaches significantly improve the success rate of analog circuit design and enhance circuit performance.
AnalogCoder-Pro: Unifying Analog Circuit Generation and Optimization via Multi-modal LLMs
Paper ↗
Abstract
Despite recent advances, analog front-end design still relies heavily on expert intuition and iterative simulations, which limits the potential for automation. We present AnalogCoder-Pro, a multimodal large language model (LLM) framework that integrates generative and optimization techniques. The framework features a multimodal diagnosis-and-repair feedback loop that uses simulation error messages and waveform images to autonomously correct design errors. It also builds a reusable circuit tool library by archiving successful designs as modular subcircuits, accelerating the development of complex systems. Furthermore, it enables end-to-end automation by generating circuit topologies from target specifications, extracting key parameters, and applying Bayesian optimization for device sizing. On a curated benchmark suite covering 13 circuit types, AnalogCoder-Pro successfully designed 28 circuits and consistently outperformed existing LLM-based methods in figures of merit.
Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems
Paper ↗
Abstract
Traffic signal control (TSC) is vital for mitigating congestion and sustaining urban mobility. In this paper, we introduce Traffic-R1, a foundation model with human-like reasoning for TSC systems. Our model is developed through self-exploration and iteration of reinforced large language models (LLMs) with expert guidance in a simulated traffic environment. Compared to traditional reinforcement learning (RL) and recent LLM-based methods, Traffic-R1 offers three significant advantages. First, Traffic-R1 delivers zero-shot generalisation, transferring unchanged to new road networks and out-of-distribution incidents by utilizing its internal traffic control policies and human-like reasoning. Second, its 3B-parameter architecture is lightweight enough for real-time inference on mobile-class chips, enabling large-scale edge deployment. Third, Traffic-R1 provides an explainable TSC process and facilitates multi-intersection communication through its self-iteration and a new synchronous communication network. Extensive benchmarks demonstrate that Traffic-R1 sets a new state of the art, outperforming strong baselines and training-intensive RL controllers. In practice, the model now manages signals for more than 55,000 drivers daily, shortening average queues by over 5% and halving operator workload. Our checkpoint is available at https://huggingface.co/Season998/Traffic-R1.
CloudAnoAgent: Anomaly Detection for Cloud Sites via LLM Agent with Neuro-Symbolic Mechanism
Paper ↗
Abstract
Anomaly detection in cloud sites remains a critical yet challenging task. Existing approaches that rely solely on metric data often suffer from high false positive rates (FPR) due to data imbalance between normal and anomalous events, leading to significant operational overhead for system reliance engineers. Recent advances in large language models (LLMs) offer new opportunities for integrating metrics with log data, enabling more accurate and interpretable anomaly detection. In this paper, we propose CloudAnoAgent, the first neuro-symbolic LLM-based agent for anomaly detection in cloud environments. CloudAnoAgent jointly processes structured metrics and textual log data in a unified pipeline, leveraging symbolic verification to validate detection hypotheses and generate structured anomaly reports. To support systematic evaluation, we introduce CloudAnoBench, the first benchmark that provides LLM-generated paired metrics and log data with fine-grained anomaly behavior annotations, filling a critical gap in existing datasets. Experimental results demonstrate that CloudAnoAgent improves anomaly classification accuracy by 46.36% and 36.67% on average and reduces the FPR by 36.67% and 33.89% on average over traditional baselines and LLM-only baseline, with a boost on anomaly type detection accuracy by 12.8% compared to vanilla LLM prompting. These results demonstrate the strengths of our approach in improving detection accuracy, reducing false positives, and enhancing interpretability, thereby supporting practical deployment in enterprise cloud environments.
AGFT: An Adaptive GPU Frequency Tuner for Real-Time LLM Inference Optimization
Paper ↗
Abstract
The explosive growth of interactive Large Language Models (LLMs) has placed unprecedented demands for low latency on cloud GPUs, forcing them into high-power modes and causing escalating energy costs. Real-time inference workloads exhibit significant dynamic volatility, presenting substantial energy-saving opportunities. However, traditional static or rule-based power management strategies struggle to exploit these opportunities without compromising peak performance. To address this challenge, we propose AGFT (An Adaptive GPU Frequency Tuner), a framework that employs online reinforcement learning to autonomously learn an optimal frequency tuning policy. By monitoring real-time features like request load and latency, AGFT utilizes fine-grained frequency control for precise adjustments and intelligent action space pruning for stable, efficient decision-making. This creates a robust, automated energy management solution. We comprehensively evaluated AGFT in an environment simulating realistic, fluctuating inference requests. The experimental results demonstrate that AGFT successfully saves 44.3% of GPU energy consumption while introducing a minimal performance latency overhead of under 10%. This achievement translates into a comprehensive Energy-Delay Product (EDP) optimization of up to 40.3%, clearly showing that our framework can significantly enhance the energy efficiency and economic benefits of existing LLM inference clusters without compromising service quality.
AGFT: An Adaptive GPU Frequency Tuner for Real-Time LLM Inference Optimization
Paper ↗
Abstract
The explosive growth of interactive Large Language Models (LLMs) has placed unprecedented demands for low latency on cloud GPUs, forcing them into high-power modes and causing escalating energy costs. Real-time inference workloads exhibit significant dynamic volatility, presenting substantial energy-saving opportunities. However, traditional static or rule-based power management strategies struggle to exploit these opportunities without compromising peak performance. To address this challenge, we propose AGFT (An Adaptive GPU Frequency Tuner), a framework that employs online reinforcement learning to autonomously learn an optimal frequency tuning policy. By monitoring real-time features like request load and latency, AGFT utilizes fine-grained frequency control for precise adjustments and intelligent action space pruning for stable, efficient decision-making. This creates a robust, automated energy management solution. We comprehensively evaluated AGFT in an environment simulating realistic, fluctuating inference requests. The experimental results demonstrate that AGFT successfully saves 44.3% of GPU energy consumption while introducing a minimal performance latency overhead of under 10%. This achievement translates into a comprehensive Energy-Delay Product (EDP) optimization of up to 40.3%, clearly showing that our framework can significantly enhance the energy efficiency and economic benefits of existing LLM inference clusters without compromising service quality.
Tuning LLM-based Code Optimization via Meta-Prompting: An Industrial Perspective
Paper ↗
Abstract
There is a growing interest in leveraging large language models (LLMs) for automated code optimization. However, industrial platforms deploying multiple LLMs face a critical challenge: prompts optimized for one LLM often fail with others, requiring expensive model-specific prompt engineering. This cross-model prompt engineering bottleneck severely limits the practical deployment of multi-LLM optimization systems in production environments. To address this, we introduce Meta-Prompted Code Optimization (MPCO), a framework that automatically generates high-quality, task-specific prompts across diverse LLMs while maintaining industrial efficiency requirements. MPCO leverages meta-prompting to dynamically synthesize context-aware optimization prompts by integrating project metadata, task requirements, and LLM-specific contexts, and it seamlessly deploys on the ARTEMIS industrial platform for automated validation and scaling. Our comprehensive evaluation on five real-world codebases with 366 hours of runtime benchmarking demonstrates MPCO's effectiveness: it achieves overall performance improvements up to 19.06% with the best statistical rank across all systems compared to baseline methods. Analysis shows that 96% of the top-performing optimizations stem from meaningful edits. Through systematic ablation studies and meta-prompter sensitivity analysis, we identify that comprehensive context integration is essential for effective meta-prompting, and that all three major LLMs can serve effectively as meta-prompters, providing actionable insights for industrial practitioners.
DBAIOps: A Reasoning LLM-Enhanced Database Operation and Maintenance System using Knowledge Graphs
Paper ↗
Abstract
The operation and maintenance (O&M) of database systems is critical to ensuring system availability and performance, typically requiring expert experience (e.g., identifying metric-to-anomaly relations) for effective diagnosis and recovery. However, existing automatic database O&M methods, including commercial products, cannot effectively utilize expert experience. On the one hand, rule-based methods only support basic O&M tasks (e.g., metric-based anomaly detection), which are mostly numerical equations and cannot effectively incorporate literal O&M experience (e.g., troubleshooting guidance in manuals). On the other hand, LLM-based methods, which retrieve fragmented information (e.g., standard documents + RAG), often generate inaccurate or generic results. To address these limitations, we present DBAIOps, a novel hybrid database O&M system that combines reasoning LLMs with knowledge graphs to achieve DBA-style diagnosis. First, DBAIOps introduces a heterogeneous graph model for representing the diagnosis experience, and proposes a semi-automatic graph construction algorithm to build that graph from thousands of documents. Second, DBAIOps develops a collection of (800+) reusable anomaly models that identify both directly alerted metrics and implicitly correlated experience and metrics. Third, for each anomaly, DBAIOps proposes a two-stage graph evolution mechanism to explore relevant diagnosis paths and identify missing relations automatically. It then leverages a reasoning LLM (e.g., DeepSeek-R1) to infer root causes and generate clear diagnosis reports for both DBAs and common users. Our evaluation over four mainstream database systems (Oracle, MySQL, PostgreSQL, and DM8) demonstrates that DBAIOps outperforms state-of-the-art baselines, 34.85% and 47.22% higher in root cause and human evaluation accuracy, respectively.
CADDesigner: Conceptual Design of CAD Models Based on General-Purpose Agent
Paper ↗
Abstract
Computer-Aided Design (CAD) plays a pivotal role in industrial manufacturing but typically requires a high level of expertise from designers. To lower the entry barrier and improve design efficiency, we present an agent for CAD conceptual design powered by large language models (LLMs). The agent accepts both abstract textual descriptions and freehand sketches as input, engaging in interactive dialogue with users to refine and clarify design requirements through comprehensive requirement analysis. Built upon a novel Context-Independent Imperative Paradigm (CIP), the agent generates high-quality CAD modeling code. During the generation process, the agent incorporates iterative visual feedback to improve model quality. Generated design cases are stored in a structured knowledge base, enabling continuous improvement of the agent's code generation capabilities. Experimental results demonstrate that our method achieves state-of-the-art performance in CAD code generation.
CADDesigner: Conceptual Design of CAD Models Based on General-Purpose Agent
Paper ↗
Abstract
Computer-Aided Design (CAD) plays a pivotal role in industrial manufacturing but typically requires a high level of expertise from designers. To lower the entry barrier and improve design efficiency, we present an agent for CAD conceptual design powered by large language models (LLMs). The agent accepts both abstract textual descriptions and freehand sketches as input, engaging in interactive dialogue with users to refine and clarify design requirements through comprehensive requirement analysis. Built upon a novel Context-Independent Imperative Paradigm (CIP), the agent generates high-quality CAD modeling code. During the generation process, the agent incorporates iterative visual feedback to improve model quality. Generated design cases are stored in a structured knowledge base, enabling continuous improvement of the agent's code generation capabilities. Experimental results demonstrate that our method achieves state-of-the-art performance in CAD code generation.
AutoEDA: Enabling EDA Flow Automation through Microservice-Based LLM Agents
Paper ↗
Abstract
Modern Electronic Design Automation (EDA) workflows, especially the RTL-to-GDSII flow, require heavily manual scripting and demonstrate a multitude of tool-specific interactions which limits scalability and efficiency. While LLMs introduces strides for automation, existing LLM solutions require expensive fine-tuning and do not contain standardized frameworks for integration and evaluation. We introduce AutoEDA, a framework for EDA automation that leverages paralleled learning through the Model Context Protocol (MCP) specific for standardized and scalable natural language experience across the entire RTL-to-GDSII flow. AutoEDA limits fine-tuning through structured prompt engineering, implements intelligent parameter extraction and task decomposition, and provides an extended CodeBLEU metric to evaluate the quality of TCL scripts. Results from experiments over five previously curated benchmarks show improvements in automation accuracy and efficiency, as well as script quality when compared to existing methods. AutoEDA is released open-sourced to support reproducibility and the EDA community. Available at: https://github.com/AndyLu666/MCP-EDA-Server
MCeT: Behavioral Model Correctness Evaluation using Large Language Models
Paper ↗
Abstract
Behavioral model diagrams, e.g., sequence diagrams, are an essential form of documentation that are typically designed by system engineers from requirements documentation, either fully manually or assisted by design tools. With the growing use of Large Language Models (LLM) as AI modeling assistants, more automation will be involved in generating diagrams. This necessitates the advancement of automatic model correctness evaluation tools. Such a tool can be used to evaluate both manually and AI automatically generated models; to provide feedback to system engineers, and enable AI assistants to self-evaluate and self-enhance their generated models. In this paper, we propose MCeT, the first fully automated tool to evaluate the correctness of a behavioral model, sequence diagrams in particular, against its corresponding requirements text and produce a list of issues that the model has. We utilize LLMs for the correctness evaluation tasks as they have shown outstanding natural language understanding ability. However, we show that directly asking an LLM to compare a diagram to requirements finds less than 35% of issues that experienced engineers can find. We propose to supplement the direct check with a fine-grained, multi-perspective approach; we split the diagram into atomic, non-divisible interactions, and split the requirements text into atomic, self-contained items. We compare the diagram with atomic requirements and each diagram-atom with the requirements. We also propose a self-consistency checking approach that combines perspectives to mitigate LLM hallucinated issues. Our combined approach improves upon the precision of the direct approach from 0.58 to 0.81 in a dataset of real requirements. Moreover, the approach finds 90% more issues that the experienced engineers found than the direct approach, and reports an average of 6 new issues per diagram.
MCeT: Behavioral Model Correctness Evaluation using Large Language Models
Paper ↗
Abstract
Behavioral model diagrams, e.g., sequence diagrams, are an essential form of documentation that are typically designed by system engineers from requirements documentation, either fully manually or assisted by design tools. With the growing use of Large Language Models (LLM) as AI modeling assistants, more automation will be involved in generating diagrams. This necessitates the advancement of automatic model correctness evaluation tools. Such a tool can be used to evaluate both manually and AI automatically generated models; to provide feedback to system engineers, and enable AI assistants to self-evaluate and self-enhance their generated models. In this paper, we propose MCeT, the first fully automated tool to evaluate the correctness of a behavioral model, sequence diagrams in particular, against its corresponding requirements text and produce a list of issues that the model has. We utilize LLMs for the correctness evaluation tasks as they have shown outstanding natural language understanding ability. However, we show that directly asking an LLM to compare a diagram to requirements finds less than 35% of issues that experienced engineers can find. We propose to supplement the direct check with a fine-grained, multi-perspective approach; we split the diagram into atomic, non-divisible interactions, and split the requirements text into atomic, self-contained items. We compare the diagram with atomic requirements and each diagram-atom with the requirements. We also propose a self-consistency checking approach that combines perspectives to mitigate LLM hallucinated issues. Our combined approach improves upon the precision of the direct approach from 0.58 to 0.81 in a dataset of real requirements. Moreover, the approach finds 90% more issues that the experienced engineers found than the direct approach, and reports an average of 6 new issues per diagram.
Geak: Introducing Triton Kernel AI Agent & Evaluation Benchmarks
Paper ↗
Abstract
The demand for AI-generated GPU kernels is rapidly growing, influenced by the need for scalable, hardware-optimized solutions in both industry and academia. As deep learning workloads grow in complexity and diversity, it is imperative to automate low-level kernel development to meet performance and productivity demands. Major cloud providers, semiconductor companies, and research institutions are now investing heavily in AI-driven code generation for GPUs, aiming to reduce manual optimization efforts while achieving near-expert performance on hardware like AMD MI300X. The Triton language, a Python-based DSL for GPU programming, has emerged as a popular target for such AI-generated kernels due to its balance of performance and ease-of-coding. In this work, we present an evaluation suite for Triton-based GPU kernels and GEAK (Generating Efficient AI-centric GPU Kernels)-a framework that leverages cutting-edge LLMs to generate performant Triton code specifically for AMD GPUs, including the AMD MI300X and MI250. GEAK leverages inference-time compute scaling to produce Triton-based GPU kernels using a reasoning loop adapted from Reflexion-style feedback mechanisms. On two evaluation benchmarks, GEAK significantly outperformed the baselines of directly prompting frontier LLMs as well as Reflexion-based generation pipelines by achieving correctness up to $63$% and execution speed up of up to $2.59$X. These results highlight the promise of GEAK-like agentic code generation for accelerating the adoption of diverse hardware platforms and democratizing access to expert-level kernel performance.
AutoBridge: Automating Smart Device Integration with Centralized Platform
Paper ↗
Abstract
Multimodal IoT systems coordinate diverse IoT devices to deliver human-centered services. The ability to incorporate new IoT devices under the management of a centralized platform is an essential requirement. However, it requires significant human expertise and effort to program the complex IoT integration code that enables the platform to understand and control the device functions. Therefore, we propose AutoBridge to automate IoT integration code generation. Specifically, AutoBridge adopts a divide-and-conquer strategy: it first generates device control logic by progressively retrieving device-specific knowledge, then synthesizes platformcompliant integration code using platform-specific knowledge. To ensure correctness, AutoBridge features a multi-stage debugging pipeline, including an automated debugger for virtual IoT device testing and an interactive hardware-in-the-loop debugger that requires only binary user feedback (yes and no) for real-device verification. We evaluate AutoBridge on a benchmark of 34 IoT devices across two open-source IoT platforms. The results demonstrate that AutoBridge can achieves an average success rate of 93.87% and an average function coverage of 94.87%, without any human involvement. With minimal binary yes and no feedback from users, the code is then revised to reach 100% function coverage. A user study with 15 participants further shows that AutoBridge outperforms expert programmers by 50% to 80% in code accuracy, even when the programmers are allowed to use commercial code LLMs.
Automatically discovering heuristics in a complex SAT solver with large language models
Paper ↗
Abstract
Satisfiability problem (SAT) is a cornerstone of computational complexity with broad industrial applications, and it remains challenging to optimize modern SAT solvers in real-world settings due to their intricate architectures. While automatic configuration frameworks have been developed, they rely on manually constrained search spaces and yield limited performance gains. This work introduces a novel paradigm which effectively optimizes complex SAT solvers via Large Language Models (LLMs), and a tool called AutoModSAT is developed. Three fundamental challenges are addressed in order to achieve superior performance: (1) LLM-friendly solver: Systematic guidelines are proposed for developing a modularized solver to meet LLMs' compatibility, emphasizing code simplification, information share and bug reduction; (2) Automatic prompt optimization: An unsupervised automatic prompt optimization method is introduced to advance the diversity of LLMs' output; (3) Efficient search strategy: We design a presearch strategy and an EA evolutionary algorithm for the final efficient and effective discovery of heuristics. Extensive experiments across a wide range of datasets demonstrate that AutoModSAT achieves 50% performance improvement over the baseline solver and achieves 30% superiority against the state-of-the-art (SOTA) solvers. Moreover, AutoModSAT attains a 20% speedup on average compared to parameter-tuned alternatives of the SOTA solvers, showcasing the enhanced capability in handling complex problem instances. This work bridges the gap between AI-driven heuristics discovery and mission-critical system optimization, and provides both methodological advancements and empirically validated results for next-generation complex solver development.
The Multi-Agent Fault Localization System Based on Monte Carlo Tree Search Approach
Paper ↗
Abstract
In real-world scenarios, due to the highly decoupled and flexible nature of microservices, it poses greater challenges to system reliability. The more frequent occurrence of incidents has created a demand for Root Cause Analysis(RCA) methods that enable rapid identification and recovery of incidents. Large language model (LLM) provides a new path for quickly locating and recovering from incidents by leveraging their powerful generalization ability combined with expert experience. Current LLM for RCA frameworks are based on ideas like ReAct and Chain-of-Thought, but the hallucination of LLM and the propagation nature of anomalies often lead to incorrect localization results. Moreover, the massive amount of anomalous information generated in large, complex systems presents a huge challenge for the context window length of LLMs. To address these challenges, we propose KnowledgeMind, an innovative LLM multi-agent system based on Monte Carlo Tree Search and a knowledge base reward mechanism for standardized service-by-service reasoning. Compared to State-Of-The-Art(SOTA) LLM for RCA methods, our service-by-service exploration approach significantly reduces the burden on the maximum context window length, requiring only one-tenth of its size. Additionally, by incorporating a rule-based real-time reward mechanism, our method effectively mitigates hallucinations during the inference process. Compared to the SOTA LLM for RCA framework, our method achieves a 49.29% to 128.35% improvement in root cause localization accuracy.
OFCnetLLM: Large Language Model for Network Monitoring and Alertness
Paper ↗
Abstract
The rapid evolution of network infrastructure is bringing new challenges and opportunities for efficient network management, optimization, and security. With very large monitoring databases becoming expensive to explore, the use of AI and Generative AI can help reduce costs of managing these datasets. This paper explores the use of Large Language Models (LLMs) to revolutionize network monitoring management by addressing the limitations of query finding and pattern analysis. We leverage LLMs to enhance anomaly detection, automate root-cause analysis, and automate incident analysis to build a well-monitored network management team using AI. Through a real-world example of developing our own OFCNetLLM, based on the open-source LLM model, we demonstrate practical applications of OFCnetLLM in the OFC conference network. Our model is developed as a multi-agent approach and is still evolving, and we present early results here.
Toward Intelligent Electronic-Photonic Design Automation for Large-Scale Photonic Integrated Circuits: from Device Inverse Design to Physical Layout Generation
Paper ↗
Abstract
Photonic Integrated Circuits (PICs) offer tremendous advantages in bandwidth, parallelism, and energy efficiency, making them essential for emerging applications in artificial intelligence (AI), high-performance computing (HPC), sensing, and communications. However, the design of modern PICs, which now integrate hundreds to thousands of components, remains largely manual, resulting in inefficiency, poor scalability, and susceptibility to errors. To address these challenges, we propose PoLaRIS, a comprehensive Intelligent Electronic-Photonic Design Automation (EPDA) framework that spans both device-level synthesis and system-level physical layout. PoLaRIS combines a robust, fabrication-aware inverse design engine with a routing-informed placement and curvy-aware detailed router, enabling the automated generation of design rule violation (DRV)-free and performance-optimized layouts. By unifying physics-driven optimization with machine learning and domain-specific algorithms, PoLaRIS significantly accelerates PIC development, lowers design barriers, and lays the groundwork for scalable photonic system design automation.
Edge Agentic AI Framework for Autonomous Network Optimisation in O-RAN
Paper ↗
Abstract
The deployment of AI agents within legacy Radio Access Network (RAN) infrastructure poses significant safety and reliability challenges for future 6G networks. This paper presents a novel Edge AI framework for autonomous network optimisation in Open RAN environments, addressing these challenges through three core innovations: (1) a persona-based multi-tools architecture enabling distributed, context-aware decision-making; (2) proactive anomaly detection agent powered by traffic predictive tool; and (3) a safety, aligned reward mechanism that balances performance with operational stability. Integrated into the RAN Intelligent Controller (RIC), our framework leverages multimodal data fusion, including network KPIs, a traffic prediction model, and external information sources, to anticipate and respond to dynamic network conditions. Extensive evaluation using realistic 5G scenarios demonstrates that the edge framework achieves zero network outages under high-stress conditions, compared to 8.4% for traditional fixed-power networks and 3.3% for large language model (LLM) agent-based approaches, while maintaining near real-time responsiveness and consistent QoS. These results establish that, when equipped with the right tools and contextual awareness, AI agents can be safely and effectively deployed in critical network infrastructure, laying the framework for intelligent and autonomous 5G and beyond network operations.
Edge Agentic AI Framework for Autonomous Network Optimisation in O-RAN
Paper ↗
Abstract
The deployment of AI agents within legacy Radio Access Network (RAN) infrastructure poses significant safety and reliability challenges for future 6G networks. This paper presents a novel Edge AI framework for autonomous network optimisation in Open RAN environments, addressing these challenges through three core innovations: (1) a persona-based multi-tools architecture enabling distributed, context-aware decision-making; (2) proactive anomaly detection agent powered by traffic predictive tool; and (3) a safety, aligned reward mechanism that balances performance with operational stability. Integrated into the RAN Intelligent Controller (RIC), our framework leverages multimodal data fusion, including network KPIs, a traffic prediction model, and external information sources, to anticipate and respond to dynamic network conditions. Extensive evaluation using realistic 5G scenarios demonstrates that the edge framework achieves zero network outages under high-stress conditions, compared to 8.4% for traditional fixed-power networks and 3.3% for large language model (LLM) agent-based approaches, while maintaining near real-time responsiveness and consistent QoS. These results establish that, when equipped with the right tools and contextual awareness, AI agents can be safely and effectively deployed in critical network infrastructure, laying the framework for intelligent and autonomous 5G and beyond network operations.
A Multi-Agent Generative AI Framework for IC Module-Level Verification Automation
Paper ↗
Abstract
As large language models demonstrate enormous potential in the field of Electronic Design Automation (EDA), generative AI-assisted chip design is attracting widespread attention from academia and industry. Although these technologies have made preliminary progress in tasks such as code generation, their application in chip verification -- a critical bottleneck in the chip development cycle -- remains at an exploratory stage. This paper proposes an innovative Multi-Agent Verification Framework (MAVF) aimed at addressing the limitations of current single-LLM approaches in complex verification tasks. Our framework builds an automated transformation system from design specifications to testbench through the collaborative work of multiple specialized agents, including specification parsing, verification strategy generation, and code implementation. Through verification experiments on multiple chip modules of varying complexity, results show that MAVF significantly outperforms traditional manual methods and single-dialogue generative AI approaches in verification document parsing and generation, as well as automated testbench generation. This research opens new directions for exploring generative AI applications in verification automation, potentially providing effective approaches to solving the most challenging bottleneck issues in chip design.
Large Language Models for Wireless Communications: From Adaptation to Autonomy
Paper ↗
Abstract
The emergence of large language models (LLMs) has revolutionized artificial intelligence, offering unprecedented capabilities in reasoning, generalization, and zero-shot learning. These strengths open new frontiers in wireless communications, where increasing complexity and dynamics demand intelligent and adaptive solutions. This article explores the role of LLMs in transforming wireless systems across three key directions: adapting pretrained LLMs for core communication tasks, developing wireless-specific foundation models to balance versatility and efficiency, and enabling agentic LLMs with autonomous reasoning and coordination capabilities. We highlight recent advances, practical case studies, and the unique benefits of LLM-based approaches over traditional methods. Finally, we outline open challenges and research opportunities, including multimodal fusion, collaboration with lightweight models, and self-improving capabilities, charting a path toward intelligent, adaptive, and autonomous wireless networks of the future.
HLSDebugger: Identification and Correction of Logic Bugs in HLS Code with LLM Solutions
Paper ↗
Abstract
High-level synthesis (HLS) accelerates hardware design by enabling the automatic translation of high-level descriptions into efficient hardware implementations. However, debugging HLS code is a challenging and labor-intensive task, especially for novice circuit designers or software engineers without sufficient hardware domain knowledge. The recent emergence of Large Language Models (LLMs) is promising in automating the HLS debugging process. Despite the great potential, three key challenges persist when applying LLMs to HLS logic debugging: 1) High-quality circuit data for training LLMs is scarce, posing a significant challenge. 2) Debugging logic bugs in hardware is inherently more complex than identifying software bugs with existing golden test cases. 3) The absence of reliable test cases requires multi-tasking solutions, performing both bug identification and correction. complicates the multi-tasking required for effective HLS debugging. In this work, we propose a customized solution named HLSDebugger to address the challenges. HLSDebugger first generates and releases a large labeled dataset with 300K data samples, targeting HLS logic bugs. The HLSDebugger model adopts an encoder-decoder structure, performing bug location identification, bug type prediction, and bug correction with the same model. HLSDebugger significantly outperforms advanced LLMs like GPT-4 in bug identification and by more than 3x in bug correction. It makes a substantial advancement in the exploration of automated debugging of HLS code.
LLM4VV: Evaluating Cutting-Edge LLMs for Generation and Evaluation of Directive-Based Parallel Programming Model Compiler Tests
Paper ↗
Abstract
The usage of Large Language Models (LLMs) for software and test development has continued to increase since LLMs were first introduced, but only recently have the expectations of LLMs become more realistic. Verifying the correctness of code generated by LLMs is key to improving their usefulness, but there have been no comprehensive and fully autonomous solutions developed yet. Hallucinations are a major concern when LLMs are applied blindly to problems without taking the time and effort to verify their outputs, and an inability to explain the logical reasoning of LLMs leads to issues with trusting their results. To address these challenges while also aiming to effectively apply LLMs, this paper proposes a dual-LLM system (i.e. a generative LLM and a discriminative LLM) and experiments with the usage of LLMs for the generation of a large volume of compiler tests. We experimented with a number of LLMs possessing varying parameter counts and presented results using ten carefully-chosen metrics that we describe in detail in our narrative. Through our findings, it is evident that LLMs possess the promising potential to generate quality compiler tests and verify them automatically.
LLM4VV: Evaluating Cutting-Edge LLMs for Generation and Evaluation of Directive-Based Parallel Programming Model Compiler Tests
Paper ↗
Abstract
The usage of Large Language Models (LLMs) for software and test development has continued to increase since LLMs were first introduced, but only recently have the expectations of LLMs become more realistic. Verifying the correctness of code generated by LLMs is key to improving their usefulness, but there have been no comprehensive and fully autonomous solutions developed yet. Hallucinations are a major concern when LLMs are applied blindly to problems without taking the time and effort to verify their outputs, and an inability to explain the logical reasoning of LLMs leads to issues with trusting their results. To address these challenges while also aiming to effectively apply LLMs, this paper proposes a dual-LLM system (i.e. a generative LLM and a discriminative LLM) and experiments with the usage of LLMs for the generation of a large volume of compiler tests. We experimented with a number of LLMs possessing varying parameter counts and presented results using ten carefully-chosen metrics that we describe in detail in our narrative. Through our findings, it is evident that LLMs possess the promising potential to generate quality compiler tests and verify them automatically.
A2HCoder: An LLM-Driven Coding Agent for Hierarchical Algorithm-to-HDL Translation
Paper ↗
Abstract
In wireless communication systems, stringent requirements such as ultra-low latency and power consumption have significantly increased the demand for efficient algorithm-to-hardware deployment. However, a persistent and substantial gap remains between algorithm design and hardware implementation. Bridging this gap traditionally requires extensive domain expertise and time-consuming manual development, due to fundamental mismatches between high-level programming languages like MATLAB and hardware description languages (HDLs) such as Verilog-in terms of memory access patterns, data processing manners, and datatype representations. To address this challenge, we propose A2HCoder: a Hierarchical Algorithm-to-HDL Coding Agent, powered by large language models (LLMs), designed to enable agile and reliable algorithm-to-hardware translation. A2HCoder introduces a hierarchical framework that enhances both robustness and interpretability while suppressing common hallucination issues in LLM-generated code. In the horizontal dimension, A2HCoder decomposes complex algorithms into modular functional blocks, simplifying code generation and improving consistency. In the vertical dimension, instead of relying on end-to-end generation, A2HCoder performs step-by-step, fine-grained translation, leveraging external toolchains such as MATLAB and Vitis HLS for debugging and circuit-level synthesis. This structured process significantly mitigates hallucinations and ensures hardware-level correctness. We validate A2HCoder through a real-world deployment case in the 5G wireless communication domain, demonstrating its practicality, reliability, and deployment efficiency.
Automated HEMT Model Construction from Datasheets via Multi-Modal Intelligence and Prior-Knowledge-Free Optimization
Paper ↗
Abstract
Parameter extraction for industry-standard device models like ASM-HEMT is crucial in circuit design workflows. However, many manufacturers do not provide such models, leaving users to build them using only datasheets. Unfortunately, datasheets lack sufficient information for standard step-by-step extraction. Moreover, manual data extraction from datasheets is highly time-consuming, and the absence of a fully automated method forces engineers to perform tedious manual work. To address this challenge, this paper introduces a novel, end-to-end framework that fully automates the generation of simulation-ready ASM-HEMT SPICE models directly from PDF datasheets. Our framework is founded on two core innovations: 1) a multi-modal AI pipeline that integrates computer vision with a large language model (LLM) to robustly parse heterogeneous datasheet layouts and digitize characteristic curves, and 2) a novel Iterative-Focusing Tree-structured Parzen Estimator (IF-TPE) optimization algorithm is specifically designed for device parameter extraction under the high-dimensional, sparse-data condition by adaptively refining the parameter search space. Experimental validation on a diverse set of 17 commercial HEMT devices from 10 manufacturers confirms the framework's accuracy and robustness. The generated models demonstrate excellent agreement with published DC and RF characteristics. As the first fully automated workflow of its kind, our proposed solution offers a transformative approach to device modeling, poised to significantly accelerate the circuit design cycle by eliminating the need for manual parameter extraction.
LLMs-guided adaptive compensator: Bringing Adaptivity to Automatic Control Systems with Large Language Models
Paper ↗
Abstract
With rapid advances in code generation, reasoning, and problem-solving, Large Language Models (LLMs) are increasingly applied in robotics. Most existing work focuses on high-level tasks such as task decomposition. A few studies have explored the use of LLMs in feedback controller design; however, these efforts are restricted to overly simplified systems, fixed-structure gain tuning, and lack real-world validation. To further investigate LLMs in automatic control, this work targets a key subfield: adaptive control. Inspired by the framework of model reference adaptive control (MRAC), we propose an LLM-guided adaptive compensator framework that avoids designing controllers from scratch. Instead, the LLMs are prompted using the discrepancies between an unknown system and a reference system to design a compensator that aligns the response of the unknown system with that of the reference, thereby achieving adaptivity. Experiments evaluate five methods: LLM-guided adaptive compensator, LLM-guided adaptive controller, indirect adaptive control, learning-based adaptive control, and MRAC, on soft and humanoid robots in both simulated and real-world environments. Results show that the LLM-guided adaptive compensator outperforms traditional adaptive controllers and significantly reduces reasoning complexity compared to the LLM-guided adaptive controller. The Lyapunov-based analysis and reasoning-path inspection demonstrate that the LLM-guided adaptive compensator enables a more structured design process by transforming mathematical derivation into a reasoning task, while exhibiting strong generalizability, adaptability, and robustness. This study opens a new direction for applying LLMs in the field of automatic control, offering greater deployability and practicality compared to vision-language models.
Large Language Model Agent for Structural Drawing Generation Using ReAct Prompt Engineering and Retrieval Augmented Generation
Paper ↗
Abstract
Structural drawings are widely used in many fields, e.g., mechanical engineering, civil engineering, etc. In civil engineering, structural drawings serve as the main communication tool between architects, engineers, and builders to avoid conflicts, act as legal documentation, and provide a reference for future maintenance or evaluation needs. They are often organized using key elements such as title/subtitle blocks, scales, plan views, elevation view, sections, and detailed sections, which are annotated with standardized symbols and line types for interpretation by engineers and contractors. Despite advances in software capabilities, the task of generating a structural drawing remains labor-intensive and time-consuming for structural engineers. Here we introduce a novel generative AI-based method for generating structural drawings employing a large language model (LLM) agent. The method incorporates a retrieval-augmented generation (RAG) technique using externally-sourced facts to enhance the accuracy and reliability of the language model. This method is capable of understanding varied natural language descriptions, processing these to extract necessary information, and generating code to produce the desired structural drawing in AutoCAD. The approach developed, demonstrated and evaluated herein enables the efficient and direct conversion of a structural drawing's natural language description into an AutoCAD drawing, significantly reducing the workload compared to current working process associated with manual drawing production, facilitating the typical iterative process of engineers for expressing design ideas in a simplified way.
"X of Information'' Continuum: A Survey on AI-Driven Multi-dimensional Metrics for Next-Generation Networked Systems
Paper ↗
Abstract
The development of next-generation networking systems has inherently shifted from throughput-based paradigms towards intelligent, information-aware designs that emphasize the quality, relevance, and utility of transmitted information, rather than sheer data volume. While classical network metrics, such as latency and packet loss, remain significant, they are insufficient to quantify the nuanced information quality requirements of modern intelligent applications, including autonomous vehicles, digital twins, and metaverse environments. In this survey, we present the first comprehensive study of the ``X of Information'' continuum by introducing a systematic four-dimensional taxonomic framework that structures information metrics along temporal, quality/utility, reliability/robustness, and network/communication dimensions. We uncover the increasing interdependencies among these dimensions, whereby temporal freshness triggers quality evaluation, which in turn helps with reliability appraisal, ultimately enabling effective network delivery. Our analysis reveals that artificial intelligence technologies, such as deep reinforcement learning, multi-agent systems, and neural optimization models, enable adaptive, context-aware optimization of competing information quality objectives. In our extensive study of six critical application domains, covering autonomous transportation, industrial IoT, healthcare digital twins, UAV communications, LLM ecosystems, and metaverse settings, we illustrate the revolutionary promise of multi-dimensional information metrics for meeting diverse operational needs. Our survey identifies prominent implementation challenges, including ...
Efficient and Scalable Agentic AI with Heterogeneous Systems
Paper ↗
Abstract
AI agents are emerging as a dominant workload in a wide range of applications, promising to be the vehicle that delivers the promised benefits of AI to enterprises and consumers. Unlike conventional software or static inference, agentic workloads are dynamic and structurally complex. Often these agents are directed graphs of compute and IO operations that span multi-modal data input and conversion), data processing and context gathering (e.g vector DB lookups), multiple LLM inferences, tool calls, etc. To scale AI agent usage, we need efficient and scalable deployment and agent-serving infrastructure. To tackle this challenge, in this paper, we present a system design for dynamic orchestration of AI agent workloads on heterogeneous compute infrastructure spanning CPUs and accelerators, both from different vendors and across different performance tiers within a single vendor. The system delivers several building blocks: a framework for planning and optimizing agentic AI execution graphs using cost models that account for compute, memory, and bandwidth constraints of different HW; a MLIR based representation and compilation system that can decompose AI agent execution graphs into granular operators and generate code for different HW options; and a dynamic orchestration system that can place the granular components across a heterogeneous compute infrastructure and stitch them together while meeting an end-to-end SLA. Our design performs a systems level TCO optimization and preliminary results show that leveraging a heterogeneous infrastructure can deliver significant TCO benefits. A preliminary surprising finding is that for some workloads a heterogeneous combination of older generation GPUs with newer accelerators can deliver similar TCO as the latest generation homogenous GPU infrastructure design, potentially extending the life of deployed infrastructure.
MCP4EDA: LLM-Powered Model Context Protocol RTL-to-GDSII Automation with Backend Aware Synthesis Optimization
Paper ↗
Abstract
This paper presents MCP4EDA, the first Model Context Protocol server that enables Large Language Models (LLMs) to control and optimize the complete open-source RTL-to-GDSII design flow through natural language interaction. The system integrates Yosys synthesis, Icarus Verilog simulation, OpenLane place-and-route, GTKWave analysis, and KLayout visualization into a unified LLM-accessible interface, enabling designers to execute complex multi-tool EDA workflows conversationally via AI assistants such as Claude Desktop and Cursor IDE. The principal contribution is a backend-aware synthesis optimization methodology wherein LLMs analyze actual post-layout timing, power, and area metrics from OpenLane results to iteratively refine synthesis TCL scripts, establishing a closed-loop optimization system that bridges the traditional gap between synthesis estimates and physical implementation reality. In contrast to conventional flows that rely on wire-load models, this methodology leverages real backend performance data to guide synthesis parameter tuning, optimization sequence selection, and constraint refinement, with the LLM functioning as an intelligent design space exploration agent. Experimental evaluation on representative digital designs demonstrates 15-30% improvements in timing closure and 10-20% area reduction compared to default synthesis flows, establishing MCP4EDA as the first practical LLM-controlled end-to-end open-source EDA automation system. The code and demo are avaiable at: http://www.agent4eda.com/
Mut4All: Fuzzing Compilers via LLM-Synthesized Mutators Learned from Bug Reports
Paper ↗
Abstract
Mutation-based fuzzing is effective for uncovering compiler bugs, but designing high-quality mutators for modern languages with complex constructs (e.g., templates, macros) remains challenging. Existing methods rely heavily on manual design or human-in-the-loop correction, limiting scalability and cross-language generalizability. We present Mut4All, a fully automated, language-agnostic framework that synthesizes mutators using Large Language Models (LLMs) and compiler-specific knowledge from bug reports. It consists of three agents: (1) a mutator invention agent that identifies mutation targets and generates mutator metadata using compiler-related insights; (2) a mutator implementation synthesis agent, fine-tuned to produce initial implementations; and (3) a mutator refinement agent that verifies and corrects the mutators via unit-test feedback. Mut4All processes 1000 bug reports (500 Rust, 500 C++), yielding 319 Rust and 403 C++ mutators at ~$0.08 each via GPT-4o. Our customized fuzzer, using these mutators, finds 62 bugs in Rust compilers (38 new, 7 fixed) and 34 bugs in C++ compilers (16 new, 1 fixed). Mut4All outperforms existing methods in both unique crash detection and coverage, ranking first on Rust and second on C++.
iPLAN: Redefining Indoor Wireless Network Planning Through Large Language Models
Paper ↗
Abstract
Efficient indoor wireless network (IWN) planning is crucial for providing high-quality 5G in-building services. However, traditional meta-heuristic and artificial intelligence-based planning methods face significant challenges due to the intricate interplay between indoor environments (IEs) and IWN demands. In this article, we present an indoor wireless network Planning with large LANguage models (iPLAN) framework, which integrates multi-modal IE representations into large language model (LLM)-powered optimizers to improve IWN planning. First, we instate the role of LLMs as optimizers, outlining embedding techniques for IEs, and introducing two core applications of iPLAN: (i) IWN planning based on pre-existing IEs and (ii) joint design of IWN and IE for new wireless-friendly buildings. For the former, we embed essential information into LLM optimizers by leveraging indoor descriptions, domain-specific knowledge, and performance-driven perception. For the latter, we conceptualize a multi-agent strategy, where intelligent agents collaboratively address key planning sub-tasks in a step-by-step manner while ensuring optimal trade-offs between the agents. The simulation results demonstrate that iPLAN achieves superior performance in IWN planning tasks and optimizes building wireless performance through the joint design of IEs and IWNs, exemplifying a paradigm shift in IWN planning.
Large Language Model-Based Task Offloading and Resource Allocation for Digital Twin Edge Computing Networks
Paper ↗
Abstract
In this paper, we propose a general digital twin edge computing network comprising multiple vehicles and a server. Each vehicle generates multiple computing tasks within a time slot, leading to queuing challenges when offloading tasks to the server. The study investigates task offloading strategies, queue stability, and resource allocation. Lyapunov optimization is employed to transform long-term constraints into tractable short-term decisions. To solve the resulting problem, an in-context learning approach based on large language model (LLM) is adopted, replacing the conventional multi-agent reinforcement learning (MARL) framework. Experimental results demonstrate that the LLM-based method achieves comparable or even superior performance to MARL.
Large Language Model Powered Automated Modeling and Optimization of Active Distribution Network Dispatch Problems
Paper ↗
Abstract
The increasing penetration of distributed energy resources into active distribution networks (ADNs) has made effective ADN dispatch imperative. However, the numerous newly-integrated ADN operators, such as distribution system aggregators, virtual power plant managers, and end prosumers, often lack specialized expertise in power system operation, modeling, optimization, and programming. This knowledge gap renders reliance on human experts both costly and time-intensive. To address this challenge and enable intelligent, flexible ADN dispatch, this paper proposes a large language model (LLM) powered automated modeling and optimization approach. First, the ADN dispatch problems are decomposed into sequential stages, and a multi-LLM coordination architecture is designed. This framework comprises an Information Extractor, a Problem Formulator, and a Code Programmer, tasked with information retrieval, optimization problem formulation, and code implementation, respectively. Afterwards, tailored refinement techniques are developed for each LLM agent, greatly improving the accuracy and reliability of generated content. The proposed approach features a user-centric interface that enables ADN operators to derive dispatch strategies via simple natural language queries, eliminating technical barriers and increasing efficiency. Comprehensive comparisons and end-to-end demonstrations on various test cases validate the effectiveness of the proposed architecture and methods.
GENIAL: Generative Design Space Exploration via Network Inversion for Low Power Algorithmic Logic Units
Paper ↗
Abstract
As AI workloads proliferate, optimizing arithmetic units is becoming increasingly important to reduce the footprint of digital systems. Conventional design flows, which often rely on manual or heuristics-based optimization, are limited in their ability to thoroughly explore the vast design space. In this paper, we introduce GENIAL, a machine learning-based framework for the automatic generation and optimization of arithmetic units, more specifically multipliers. At the core of GENIAL is a Transformer-based surrogate model trained in two stages, involving self-supervised pretraining followed by supervised finetuning, to robustly forecast key hardware metrics such as power and area from abstracted design representations. By inverting the surrogate model, GENIAL efficiently searches for new operand encodings that directly minimize power consumption in arithmetic units for specific input data distributions. Extensive experiments on large datasets demonstrate that GENIAL is consistently more sample efficient than other methods, and converges faster towards optimized designs. This enables to deploy a high-effort logic synthesis optimization flow in the loop, improving the accuracy of the surrogate model. Notably, GENIAL automatically discovers encodings that achieve up to 18% switching activity savings within multipliers on representative AI workloads compared with the conventional two's complement. We also demonstrate the versatility of our approach by achieving significant improvements on Finite State Machines, highlighting GENIAL's applicability for a wide spectrum of logic functions. Together, these advances mark a significant step toward automated Quality-of-Results-optimized combinational circuit generation for digital systems.
GenAI for Automotive Software Development: From Requirements to Wheels
Paper ↗
Abstract
This paper introduces a GenAI-empowered approach to automated development of automotive software, with emphasis on autonomous and Advanced Driver Assistance Systems (ADAS) capabilities. The process starts with requirements as input, while the main generated outputs are test scenario code for simulation environment, together with implementation of desired ADAS capabilities targeting hardware platform of the vehicle connected to testbench. Moreover, we introduce additional steps for requirements consistency checking leveraging Model-Driven Engineering (MDE). In the proposed workflow, Large Language Models (LLMs) are used for model-based summarization of requirements (Ecore metamodel, XMI model instance and OCL constraint creation), test scenario generation, simulation code (Python) and target platform code generation (C++). Additionally, Retrieval Augmented Generation (RAG) is adopted to enhance test scenario generation from autonomous driving regulations-related documents. Our approach aims shorter compliance and re-engineering cycles, as well as reduced development and testing time when it comes to ADAS-related capabilities.
TimelyHLS: LLM-Based Timing-Aware and Architecture-Specific FPGA HLS Optimization
Paper ↗
Abstract
Achieving timing closure and design-specific optimizations in FPGA-targeted High-Level Synthesis (HLS) remains a significant challenge due to the complex interaction between architectural constraints, resource utilization, and the absence of automated support for platform-specific pragmas. In this work, we propose TimelyHLS, a novel framework integrating Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) to automatically generate and iteratively refine HLS code optimized for FPGA-specific timing and performance requirements. TimelyHLS is driven by a structured architectural knowledge base containing FPGA-specific features, synthesis directives, and pragma templates. Given a kernel, TimelyHLS generates HLS code annotated with both timing-critical and design-specific pragmas. The synthesized RTL is then evaluated using commercial toolchains, and simulation correctness is verified against reference outputs via custom testbenches. TimelyHLS iteratively incorporates synthesis logs and performance reports into the LLM engine for refinement in the presence of functional discrepancies. Experimental results across 10 FPGA architectures and diverse benchmarks show that TimelyHLS reduces the need for manual tuning by up to 70%, while achieving up to 4x latency speedup (e.g., 3.85x for Matrix Multiplication, 3.7x for Bitonic Sort) and over 50% area savings in certain cases (e.g., 57% FF reduction in Viterbi). TimelyHLS consistently achieves timing closure and functional correctness across platforms, highlighting the effectiveness of LLM-driven, architecture-aware synthesis in automating FPGA design.
FedChip: Federated LLM for Artificial Intelligence Accelerator Chip Design
Paper ↗
Abstract
AI hardware design is advancing rapidly, driven by the promise of design automation to make chip development faster, more efficient, and more accessible to a wide range of users. Amongst automation tools, Large Language Models (LLMs) offer a promising solution by automating and streamlining parts of the design process. However, their potential is hindered by data privacy concerns and the lack of domain-specific training. To address this, we introduce FedChip, a Federated fine-tuning approach that enables multiple Chip design parties to collaboratively enhance a shared LLM dedicated for automated hardware design generation while protecting proprietary data. FedChip enables parties to train the model on proprietary local data and improve the shared LLM's performance. To exemplify FedChip's deployment, we create and release APTPU-Gen, a dataset of 30k design variations spanning various performance metric values such as power, performance, and area (PPA). To encourage the LLM to generate designs that achieve a balance across multiple quality metrics, we propose a new design evaluation metric, Chip@k, which statistically evaluates the quality of generated designs against predefined acceptance criteria. Experimental results show that FedChip improves design quality by more than 77% over high-end LLMs while maintaining data privacy
An AI-driven EDA Algorithm-Empowered VCO and LDO Co-Design Method
Paper ↗
Abstract
Traditionally, the output noise and power supply rejection of low-dropout regulators (LDOs) are optimized to minimize power supply fluctuations, reducing their impact on the low-frequency noise of target voltage-controlled oscillators (VCOs). However, this sequential design approach does not fully address the trade-offs between high-frequency and LDO-induced low-frequency phase noise. To overcome this limitation, this paper presents a co-design method for low phase-noise LC-tank VCOs powered by LDOs. It is difficult to carry out the co-design using traditional manual design techniques. Hence, an efficient AI-driven EDA algorithm is used. To validate the proposed method, a 5.6 GHz LC-tank VCO with an integrated LDO is designed using a 65 nm CMOS process. Simulations show that the co-design method improves phase noise by 1.2 dB at a 1 MHz offset and reduces dynamic power consumption by 28.8%, with FoM increased by 2.4 dBc/Hz compared to the conventional sequential design method.
Rethinking LLM-Based RTL Code Optimization Via Timing Logic Metamorphosis
Paper ↗
Abstract
Register Transfer Level(RTL) code optimization is crucial for achieving high performance and low power consumption in digital circuit design. However, traditional optimization methods often rely on manual tuning and heuristics, which can be time-consuming and error-prone. Recent studies proposed to leverage Large Language Models(LLMs) to assist in RTL code optimization. LLMs can generate optimized code snippets based on natural language descriptions, potentially speeding up the optimization process. However, existing approaches have not thoroughly evaluated the effectiveness of LLM-Based code optimization methods for RTL code with complex timing logic. To address this gap, we conducted a comprehensive empirical investigation to assess the capability of LLM-Based RTL code optimization methods in handling RTL code with complex timing logic. In this study, we first propose a new benchmark for RTL optimization evaluation. It comprises four subsets, each corresponding to a specific area of RTL code optimization. Then we introduce a method based on metamorphosis to systematically evaluate the effectiveness of LLM-Based RTL code optimization methods.Our key insight is that the optimization effectiveness should remain consistent for semantically equivalent but more complex code. After intensive experiments, we revealed several key findings. (1) LLM-Based RTL optimization methods can effectively optimize logic operations and outperform existing compiler-based methods. (2) LLM-Based RTL optimization methods do not perform better than existing compiler-based methods on RTL code with complex timing logic, particularly in timing control flow optimization and clock domain optimization. This is primarily attributed to the challenges LLMs face in understanding timing logic in RTL code. Based on these findings, we provide insights for further research in leveraging LLMs for RTL code optimization.
An advanced AI driven database system
Paper ↗
Abstract
Contemporary database systems, while effective, suffer severe issues related to complexity and usability, especially among individuals who lack technical expertise but are unfamiliar with query languages like Structured Query Language (SQL). This paper presents a new database system supported by Artificial Intelligence (AI), which is intended to improve the management of data using natural language processing (NLP) - based intuitive interfaces, and automatic creation of structured queries and semi-structured data formats like yet another markup language (YAML), java script object notation (JSON), and application program interface (API) documentation. The system is intended to strengthen the potential of databases through the integration of Large Language Models (LLMs) and advanced machine learning algorithms. The integration is purposed to allow the automation of fundamental tasks such as data modeling, schema creation, query comprehension, and performance optimization. We present in this paper a system that aims to alleviate the main problems with current database technologies. It is meant to reduce the need for technical skills, manual tuning for better performance, and the potential for human error. The AI database employs generative schema inference and format selection to build its schema models and execution formats.
ApproxGNN: A Pretrained GNN for Parameter Prediction in Design Space Exploration for Approximate Computing
Paper ↗
Abstract
Approximate computing offers promising energy efficiency benefits for error-tolerant applications, but discovering optimal approximations requires extensive design space exploration (DSE). Predicting the accuracy of circuits composed of approximate components without performing complete synthesis remains a challenging problem. Current machine learning approaches used to automate this task require retraining for each new circuit configuration, making them computationally expensive and time-consuming. This paper presents ApproxGNN, a construction methodology for a pre-trained graph neural network model predicting QoR and HW cost of approximate accelerators employing approximate adders from a library. This approach is applicable in DSE for assignment of approximate components to operations in accelerator. Our approach introduces novel component feature extraction based on learned embeddings rather than traditional error metrics, enabling improved transferability to unseen circuits. ApproxGNN models can be trained with a small number of approximate components, supports transfer to multiple prediction tasks, utilizes precomputed embeddings for efficiency, and significantly improves accuracy of the prediction of approximation error. On a set of image convolutional filters, our experimental results demonstrate that the proposed embeddings improve prediction accuracy (mean square error) by 50% compared to conventional methods. Furthermore, the overall prediction accuracy is 30% better than statistical machine learning approaches without fine-tuning and 54% better with fast finetuning.
SVAgent: AI Agent for Hardware Security Verification Assertion
Paper ↗
Abstract
Verification using SystemVerilog assertions (SVA) is one of the most popular methods for detecting circuit design vulnerabilities. However, with the globalization of integrated circuit design and the continuous upgrading of security requirements, the SVA development model has exposed major limitations. It is not only inefficient in development, but also unable to effectively deal with the increasing number of security vulnerabilities in modern complex integrated circuits. In response to these challenges, this paper proposes an innovative SVA automatic generation framework SVAgent. SVAgent introduces a requirement decomposition mechanism to transform the original complex requirements into a structured, gradually solvable fine-grained problem-solving chain. Experiments have shown that SVAgent can effectively suppress the influence of hallucinations and random answers, and the key evaluation indicators such as the accuracy and consistency of the SVA are significantly better than existing frameworks. More importantly, we successfully integrated SVAgent into the most mainstream integrated circuit vulnerability assessment framework and verified its practicality and reliability in a real engineering design environment.
RealBench: Benchmarking Verilog Generation Models with Real-World IP Designs
Paper ↗
Abstract
The automatic generation of Verilog code using Large Language Models (LLMs) has garnered significant interest in hardware design automation. However, existing benchmarks for evaluating LLMs in Verilog generation fall short in replicating real-world design workflows due to their designs' simplicity, inadequate design specifications, and less rigorous verification environments. To address these limitations, we present RealBench, the first benchmark aiming at real-world IP-level Verilog generation tasks. RealBench features complex, structured, real-world open-source IP designs, multi-modal and formatted design specifications, and rigorous verification environments, including 100% line coverage testbenches and a formal checker. It supports both module-level and system-level tasks, enabling comprehensive assessments of LLM capabilities. Evaluations on various LLMs and agents reveal that even one of the best-performing LLMs, o1-preview, achieves only a 13.3% pass@1 on module-level tasks and 0% on system-level tasks, highlighting the need for stronger Verilog generation models in the future. The benchmark is open-sourced at https://github.com/IPRC-DIP/RealBench.
VeriRAG: A Retrieval-Augmented Framework for Automated RTL Testability Repair
Paper ↗
Abstract
Large language models (LLMs) have demonstrated immense potential in computer-aided design (CAD), particularly for automated debugging and verification within electronic design automation (EDA) tools. However, Design for Testability (DFT) remains a relatively underexplored area. This paper presents VeriRAG, the first LLM-assisted DFT-EDA framework. VeriRAG leverages a Retrieval-Augmented Generation (RAG) approach to enable LLM to revise code to ensure DFT compliance. VeriRAG integrates (1) an autoencoder-based similarity measurement model for precise retrieval of reference RTL designs for the LLM, and (2) an iterative code revision pipeline that allows the LLM to ensure DFT compliance while maintaining synthesizability. To support VeriRAG, we introduce VeriDFT, a Verilog-based DFT dataset curated for DFT-aware RTL repairs. VeriRAG retrieves structurally similar RTL designs from VeriDFT, each paired with a rigorously validated correction, as references for code repair. With VeriRAG and VeriDFT, we achieve fully automated DFT correction -- resulting in a 7.72-fold improvement in successful repair rate compared to the zero-shot baseline (Fig. 5 in Section V). Ablation studies further confirm the contribution of each component of the VeriRAG framework. We open-source our data, models, and scripts at https://github.com/yuyangdu01/LLM4DFT.
SimdBench: Benchmarking Large Language Models for SIMD-Intrinsic Code Generation
Paper ↗
Abstract
SIMD (Single Instruction Multiple Data) instructions and their compiler intrinsics are widely supported by modern processors to accelerate performance-critical tasks. SIMD intrinsic programming, a trade-off between coding productivity and high performance, is widely used in the development of mainstream performance-critical libraries and daily computing tasks. Large Language Models (LLMs), which have demonstrated strong and comprehensive capabilities in code generation, show promise in assisting programmers with the challenges of SIMD intrinsic programming. However, existing code-generation benchmarks focus on only scalar code, and it is unclear how LLMs perform in generating vectorized code using SIMD intrinsics. To fill this gap, we propose SimdBench, the first code benchmark specifically designed for SIMD-intrinsic code generation, comprising 136 carefully crafted tasks and targeting five representative SIMD intrinsics: SSE (x86 Streaming SIMD Extension), AVX (x86 Advanced Vector Extension), Neon (ARM Advanced SIMD Extension), SVE (ARM Scalable Vector Extension), and RVV (RISC-V Vector Extension). We conduct a systematic evaluation (measuring both correctness and performance) of 18 representative LLMs on SimdBench, resulting in a series of novel and insightful findings. Our evaluation results demonstrate that LLMs exhibit a universal decrease in pass@k during SIMD-intrinsic code generation compared to scalar-code generation. Our in-depth analysis highlights promising directions for the further advancement of LLMs in the challenging domain of SIMD-intrinsic code generation. SimdBench is fully open source at https://anonymous.4open.science/r/SimdBench-1B3F/ to benefit the broader research community.
AnalogFed: Federated Discovery of Analog Circuit Topologies with Generative AI
Paper ↗
Abstract
Recent breakthroughs in AI/ML offer exciting opportunities to revolutionize analog design automation through data-driven approaches. In particular, researchers are increasingly fascinated by harnessing the power of generative AI to automate the discovery of novel analog circuit topologies. Unlocking the full potential of generative AI in these data-driven discoveries requires access to large and diverse datasets.Yet, there is a significant barrier in the analog domain--Analog circuit design is inherently proprietary, involving not only confidential circuit structures but also the underlying commercial semiconductor processes. As a result, current generative AI research is largely confined to individual researchers who construct small, narrowly focused private datasets. This fragmentation severely limits collaborative innovation and impedes progress across the research community. To address these challenges, we propose AnalogFed. AnalogFed enables collaborative topology discovery across decentralized clients (e.g., individual researchers or institutions) without requiring the sharing of raw private data. To make this vision practical, we introduce a suite of techniques tailored to the unique challenges of applying FedL in analog design--from generative model development and data heterogeneity handling to privacy-preserving strategies that ensure both flexibility and security for circuit designers and semiconductor manufacturers. Extensive experiments across varying client counts and dataset sizes demonstrate that AnalogFed achieves performance comparable to centralized baselines--while maintaining strict data privacy. Specifically, the generative AI model within AnalogFed achieves state-of-the-art efficiency and scalability in the design of analog circuit topologies.
VeriOpt: PPA-Aware High-Quality Verilog Generation via Multi-Role LLMs
Paper ↗
Abstract
The rapid adoption of large language models(LLMs) in hardware design has primarily focused on generating functionally correct Verilog code, overlooking critical Power Performance-Area(PPA) metrics essential for industrial-grade designs. To bridge this gap, we propose VeriOpt, a novel framework that leverages role-based prompting and PPA-aware optimization to enable LLMs to produce high-quality, synthesizable Verilog. VeriOpt structures LLM interactions into specialized roles (e.g., Planner, Programmer, Reviewer, Evaluator) to emulate human design workflows, while integrating PPA constraints directly into the prompting pipeline. By combining multi-modal feedback (e.g., synthesis reports, timing diagrams) with PPA aware prompting, VeriOpt achieves PPA-efficient code generation without sacrificing functional correctness. Experimental results demonstrate up to 88% reduction in power, 76% reduction in area and 73% improvement in timing closure compared to baseline LLM-generated RTL, validated using industry standard EDA tools. At the same time achieves 86% success rate in functionality evaluation. Our work advances the state-of-the-art AI-driven hardware design by addressing the critical gap between correctness and quality, paving the way for reliable LLM adoption in production workflows.
NPUEval: Optimizing NPU Kernels with LLMs and Open Source Compilers
Paper ↗
Abstract
Neural processing units (NPUs) are gaining prominence in power-sensitive devices like client devices, with AI PCs being defined by their inclusion of these specialized processors. Running AI workloads efficiently on these devices requires libraries of optimized kernels. Creating efficient kernels demands expertise in domain-specific C++ with vector intrinsics and in-depth knowledge of the target architecture. Unlike GPU programming, which has had years to mature, NPU programming is new, with smaller and more fragmented developer communities across hardware platforms. This fragmentation poses a challenge when utilizing LLMs to assist in writing NPU kernels, as domain-specific optimized code examples are underrepresented in LLM pre-training data. In this paper we introduce NPUEval -- a benchmark for writing and evaluating NPU kernels, consisting of 102 common operators for machine learning workloads. We evaluate LLM generated code on actual hardware based on both functional correctness and vectorization efficiency using open source compiler tools targeting the AMD NPU. We evaluate a range of state-of-the-art LLMs with a mix of proprietary and open-weight models. Latest reasoning models like DeepSeek R1, show promising results achieving out-of-the-box 50%+ vectorization on select kernels. However, the average score across the entire dataset remains roughly 10% even with compiler feedback and vectorized kernel examples -- showing that this is a challenging dataset even for frontier models. The dataset and evaluation code will be released with a permissive open source license, providing an essential benchmark for advancing research in code generation and NPU kernel optimization.
NetIntent: Leveraging Large Language Models for End-to-End Intent-Based SDN Automation
Paper ↗
Abstract
Intent-Based Networking (IBN) often leverages the programmability of Software-Defined Networking (SDN) to simplify network management. However, significant challenges remain in automating the entire pipeline, from user-specified high-level intents to device-specific low-level configurations. Existing solutions often rely on rigid, rule-based translators and fixed APIs, limiting extensibility and adaptability. By contrast, recent advances in large language models (LLMs) offer a promising pathway that leverages natural language understanding and flexible reasoning. However, it is unclear to what extent LLMs can perform IBN tasks. To address this, we introduce IBNBench, a first-of-its-kind benchmarking suite comprising four novel datasets: Intent2Flow-ODL, Intent2Flow-ONOS, FlowConflict-ODL, and FlowConflict-ONOS. These datasets are specifically designed for evaluating LLMs performance in intent translation and conflict detection tasks within the industry-grade SDN controllers ODL and ONOS. Our results provide the first comprehensive comparison of 33 open-source LLMs on IBNBench and related datasets, revealing a wide range of performance outcomes. However, while these results demonstrate the potential of LLMs for isolated IBN tasks, integrating LLMs into a fully autonomous IBN pipeline remains unexplored. Thus, our second contribution is NetIntent, a unified and adaptable framework that leverages LLMs to automate the full IBN lifecycle, including translation, activation, and assurance within SDN systems. NetIntent orchestrates both LLM and non-LLM agents, supporting dynamic re-prompting and contextual feedback to robustly execute user-defined intents with minimal human intervention. Our implementation of NetIntent across both ODL and ONOS SDN controllers achieves a consistent and adaptive end-to-end IBN realization.
CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning
Paper ↗
Abstract
The exponential growth in demand for GPU computing resources, driven by the rapid advancement of Large Language Models, has created an urgent need for automated CUDA optimization strategies. While recent advances in LLMs show promise for code generation, current SOTA models (e.g. R1, o1) achieve low success rates in improving CUDA speed. In this paper, we introduce CUDA-L1, an automated reinforcement learning framework for CUDA optimization. CUDA-L1 achieves performance improvements on the CUDA optimization task: trained on NVIDIA A100, it delivers an average speedup of x17.7 across all 250 CUDA kernels of KernelBench, with peak speedups reaching x449. Furthermore, the model also demonstrates excellent portability across GPU architectures, achieving average speedups of x17.8 on H100, x19.0 on RTX 3090, x16.5 on L40, x14.7 on H800, and x13.9 on H20 despite being optimized specifically for A100. Beyond these benchmark results, CUDA-L1 demonstrates several remarkable properties: 1) Discovers a variety of CUDA optimization techniques and learns to combine them strategically to achieve optimal performance; 2) Uncovers fundamental principles of CUDA optimization; 3) Identifies non-obvious performance bottlenecks and rejects seemingly beneficial optimizations that harm performance. The capabilities of CUDA-L1 demonstrate that reinforcement learning can transform an initially poor-performing LLM into an effective CUDA optimizer through speedup-based reward signals alone, without human expertise or domain knowledge. More importantly, the trained RL model extend the acquired reasoning abilities to new kernels. This paradigm opens possibilities for automated optimization of CUDA operations, and holds promise to substantially promote GPU efficiency and alleviate the rising pressure on GPU computing resources.
CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning
Paper ↗
Abstract
The exponential growth in demand for GPU computing resources has created an urgent need for automated CUDA optimization strategies. While recent advances in LLMs show promise for code generation, current SOTA models achieve low success rates in improving CUDA speed. In this paper, we introduce CUDA-L1, an automated reinforcement learning framework for CUDA optimization that employs a novel contrastive RL algorithm. CUDA-L1 achieves significant performance improvements on the CUDA optimization task: trained on NVIDIA A100, it delivers an average speedup of x3.12 with a median speedup of x1.42 across all 250 CUDA kernels of KernelBench, with peak speedups reaching x120. Furthermore, the model also demonstrates portability across GPU architectures, achieving average speedups of x3.12 on L40, x2.50 on RTX 3090, x2.39 on H100, and x2.37 on H20 despite being optimized specifically for A100. The capabilities of CUDA-L1 demonstrate that, RL can transform an initially poor-performing LLM into an effective CUDA optimizer through speedup-based reward signals alone, without human expertise or domain knowledge. This paradigm opens possibilities for automated optimization of CUDA operations, and holds promise to substantially promote GPU efficiency and alleviate the rising pressure on GPU computing resources. We also identify important challenges posed by training RL models for tasks like CUDA development, where RL often learns to exploit loopholes in reward functions rather than solve the intended optimization problems. By identifying these failure modes and analyzing their root causes, we develop practical methods for creating more robust training procedures that prevent reward hacking.
CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning
Paper ↗
Abstract
The exponential growth in demand for GPU computing resources, driven by the rapid advancement of Large Language Models, has created an urgent need for automated CUDA optimization strategies. While recent advances in LLMs show promise for code generation, current SOTA models (e.g. R1, o1) achieve low success rates in improving CUDA speed. In this paper, we introduce CUDA-L1, an automated reinforcement learning framework for CUDA optimization. CUDA-L1 achieves performance improvements on the CUDA optimization task: trained on NVIDIA A100, it delivers an average speedup of x17.7 across all 250 CUDA kernels of KernelBench, with peak speedups reaching x449. Furthermore, the model also demonstrates excellent portability across GPU architectures, achieving average speedups of x17.8 on H100, x19.0 on RTX 3090, x16.5 on L40, x14.7 on H800, and x13.9 on H20 despite being optimized specifically for A100. Beyond these benchmark results, CUDA-L1 demonstrates several remarkable properties: 1) Discovers a variety of CUDA optimization techniques and learns to combine them strategically to achieve optimal performance; 2) Uncovers fundamental principles of CUDA optimization; 3) Identifies non-obvious performance bottlenecks and rejects seemingly beneficial optimizations that harm performance. The capabilities of CUDA-L1 demonstrate that reinforcement learning can transform an initially poor-performing LLM into an effective CUDA optimizer through speedup-based reward signals alone, without human expertise or domain knowledge. More importantly, the trained RL model extend the acquired reasoning abilities to new kernels. This paradigm opens possibilities for automated optimization of CUDA operations, and holds promise to substantially promote GPU efficiency and alleviate the rising pressure on GPU computing resources.
CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning
Paper ↗
Abstract
The exponential growth in demand for GPU computing resources has created an urgent need for automated CUDA optimization strategies. While recent advances in LLMs show promise for code generation, current SOTA models achieve low success rates in improving CUDA speed. In this paper, we introduce CUDA-L1, an automated reinforcement learning framework for CUDA optimization that employs a novel contrastive RL algorithm. CUDA-L1 achieves significant performance improvements on the CUDA optimization task: trained on NVIDIA A100, it delivers an average speedup of x3.12 with a median speedup of x1.42 across all 250 CUDA kernels of KernelBench, with peak speedups reaching x120. Furthermore, the model also demonstrates portability across GPU architectures, achieving average speedups of x3.12 on L40, x2.50 on RTX 3090, x2.39 on H100, and x2.37 on H20 despite being optimized specifically for A100. The capabilities of CUDA-L1 demonstrate that, RL can transform an initially poor-performing LLM into an effective CUDA optimizer through speedup-based reward signals alone, without human expertise or domain knowledge. This paradigm opens possibilities for automated optimization of CUDA operations, and holds promise to substantially promote GPU efficiency and alleviate the rising pressure on GPU computing resources. We also identify important challenges posed by training RL models for tasks like CUDA development, where RL often learns to exploit loopholes in reward functions rather than solve the intended optimization problems. By identifying these failure modes and analyzing their root causes, we develop practical methods for creating more robust training procedures that prevent reward hacking.
CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning
Paper ↗
Abstract
The exponential growth in demand for GPU computing resources has created an urgent need for automated CUDA optimization strategies. While recent advances in LLMs show promise for code generation, current SOTA models achieve low success rates in improving CUDA speed. In this paper, we introduce CUDA-L1, an automated reinforcement learning framework for CUDA optimization that employs a novel contrastive RL algorithm. CUDA-L1 achieves significant performance improvements on the CUDA optimization task: trained on A100, it delivers an average speedup of x3.12 with a median speedup of x1.42 against default baselines over across all 250 CUDA kernels of KernelBench, with peak speedups reaching x120. In addition to the default baseline provided by KernelBench, CUDA-L1 demonstrates x2.77 over Torch Compile, x2.88 over Torch Compile with reduce overhead, x2.81 over CUDA Graph implementations, and remarkably x7.72 over cuDNN libraries. Furthermore, the model also demonstrates portability across different GPU architectures. Beyond these benchmark results, CUDA-L1 demonstrates several properties: it 1) discovers a variety of CUDA optimization techniques and learns to combine them strategically to achieve optimal performance; 2) uncovers fundamental principles of CUDA optimization, such as the multiplicative nature of optimizations; 3) identifies non-obvious performance bottlenecks and rejects seemingly beneficial optimizations that actually harm performance. The capabilities demonstrate that, RL can transform an initially poor-performing LLM into an effective CUDA optimizer through speedup-based reward signals alone, without human expertise or domain knowledge. This paradigm opens possibilities for automated optimization of CUDA operations, and holds promise to substantially promote GPU efficiency and alleviate the rising pressure on GPU computing resources.
CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning
Paper ↗
Abstract
The exponential growth in demand for GPU computing resources has created an urgent need for automated CUDA optimization strategies. While recent advances in LLMs show promise for code generation, current SOTA models achieve low success rates in improving CUDA speed. In this paper, we introduce CUDA-L1, an automated reinforcement learning framework for CUDA optimization that employs a novel contrastive RL algorithm. CUDA-L1 achieves significant performance improvements on the CUDA optimization task: trained on A100, it delivers an average speedup of x3.12 with a median speedup of x1.42 against default baselines over across all 250 CUDA kernels of KernelBench, with peak speedups reaching x120. In addition to the default baseline provided by KernelBench, CUDA-L1 demonstrates x2.77 over Torch Compile, x2.88 over Torch Compile with reduce overhead, x2.81 over CUDA Graph implementations, and remarkably x7.72 over cuDNN libraries. Furthermore, the model also demonstrates portability across different GPU architectures. Beyond these benchmark results, CUDA-L1 demonstrates several properties: it 1) discovers a variety of CUDA optimization techniques and learns to combine them strategically to achieve optimal performance; 2) uncovers fundamental principles of CUDA optimization, such as the multiplicative nature of optimizations; 3) identifies non-obvious performance bottlenecks and rejects seemingly beneficial optimizations that actually harm performance. The capabilities demonstrate that, RL can transform an initially poor-performing LLM into an effective CUDA optimizer through speedup-based reward signals alone, without human expertise or domain knowledge. This paradigm opens possibilities for automated optimization of CUDA operations, and holds promise to substantially promote GPU efficiency and alleviate the rising pressure on GPU computing resources.
Target Circuit Matching in Large-Scale Netlists using GNN-Based Region Prediction
Paper ↗
Abstract
Subgraph matching plays an important role in electronic design automation (EDA) and circuit verification. Traditional rule-based methods have limitations in generalizing to arbitrary target circuits. Furthermore, node-to-node matching approaches tend to be computationally inefficient, particularly for large-scale circuits. Deep learning methods have emerged as a potential solution to address these challenges, but existing models fail to efficiently capture global subgraph embeddings or rely on inefficient matching matrices, which limits their effectiveness for large circuits. In this paper, we propose an efficient graph matching approach that utilizes Graph Neural Networks (GNNs) to predict regions of high probability for containing the target circuit. Specifically, we construct various negative samples to enable GNNs to accurately learn the presence of target circuits and develop an approach to directly extracting subgraph embeddings from the entire circuit, which captures global subgraph information and addresses the inefficiency of applying GNNs to all candidate subgraphs. Extensive experiments demonstrate that our approach significantly outperforms existing methods in terms of time efficiency and target region prediction, offering a scalable and effective solution for subgraph matching in large-scale circuits.
RIDAS: A Multi-Agent Framework for AI-RAN with Representation- and Intention-Driven Agents
Paper ↗
Abstract
Sixth generation (6G) networks demand tight integration of artificial intelligence (AI) into radio access networks (RANs) to meet stringent quality of service (QoS) and resource efficiency requirements. Existing solutions struggle to bridge the gap between high level user intents and the low level, parameterized configurations required for optimal performance. To address this challenge, we propose RIDAS, a multi agent framework composed of representation driven agents (RDAs) and an intention driven agent (IDA). RDAs expose open interface with tunable control parameters (rank and quantization bits, enabling explicit trade) offs between distortion and transmission rate. The IDA employs a two stage planning scheme (bandwidth pre allocation and reallocation) driven by a large language model (LLM) to map user intents and system state into optimal RDA configurations. Experiments demonstrate that RIDAS supports 44.71\% more users than WirelessAgent under equivalent QoS constraints. These results validate ability of RIDAS to capture user intent and allocate resources more efficiently in AI RAN environments.
RIDAS: A Multi-Agent Framework for AI-RAN with Representation- and Intention-Driven Agents
Paper ↗
Abstract
Sixth generation (6G) networks demand tight integration of artificial intelligence (AI) into radio access networks (RANs) to meet stringent quality of service (QoS) and resource efficiency requirements. Existing solutions struggle to bridge the gap between high level user intents and the low level, parameterized configurations required for optimal performance. To address this challenge, we propose RIDAS, a multi agent framework composed of representation driven agents (RDAs) and an intention driven agent (IDA). RDAs expose open interface with tunable control parameters (rank and quantization bits, enabling explicit trade) offs between distortion and transmission rate. The IDA employs a two stage planning scheme (bandwidth pre allocation and reallocation) driven by a large language model (LLM) to map user intents and system state into optimal RDA configurations. Experiments demonstrate that RIDAS supports 36.47% more users than WirelessAgent under equivalent QoS constraints. These results validate ability of RIDAS to capture user intent and allocate resources more efficiently in AI RAN environments.
Intent-Based Network for RAN Management with Large Language Models
Paper ↗
Abstract
Advanced intelligent automation becomes an important feature to deal with the increased complexity in managing wireless networks. This paper proposes a novel automation approach of intent-based network for Radio Access Networks (RANs) management by leveraging Large Language Models (LLMs). The proposed method enhances intent translation, autonomously interpreting high-level objectives, reasoning over complex network states, and generating precise configurations of the RAN by integrating LLMs within an agentic architecture. We propose a structured prompt engineering technique and demonstrate that the network can automatically improve its energy efficiency by dynamically optimizing critical RAN parameters through a closed-loop mechanism. It showcases the potential to enable robust resource management in RAN by adapting strategies based on real-time feedback via LLM-orchestrated agentic systems.
Intent-Based Network for RAN Management with Large Language Models
Paper ↗
Abstract
Advanced intelligent automation becomes an important feature to deal with the increased complexity in managing wireless networks. This paper proposes a novel automation approach of intent-based network for Radio Access Networks (RANs) management by leveraging Large Language Models (LLMs). The proposed method enhances intent translation, autonomously interpreting high-level objectives, reasoning over complex network states, and generating precise configurations of the RAN by integrating LLMs within an agentic architecture. We propose a structured prompt engineering technique and demonstrate that the network can automatically improve its energy efficiency by dynamically optimizing critical RAN parameters through a closed-loop mechanism. It showcases the potential to enable robust resource management in RAN by adapting strategies based on real-time feedback via LLM-orchestrated agentic systems.
LLM-Based Config Synthesis requires Disambiguation
Paper ↗
Abstract
Beyond hallucinations, another problem in program synthesis using LLMs is ambiguity in user intent. We illustrate the ambiguity problem in a networking context for LLM-based incremental configuration synthesis of route-maps and ACLs. These structures frequently overlap in header space, making the relative priority of actions impossible for the LLM to infer without user interaction. Measurements in a large cloud identify complex ACLs with 100's of overlaps, showing ambiguity is a real problem. We propose a prototype system, Clarify, which uses an LLM augmented with a new module called a Disambiguator that helps elicit user intent. On a small synthetic workload, Clarify incrementally synthesizes routing policies after disambiguation and then verifies them. Our treatment of ambiguities is useful more generally when the intent of updates can be correctly synthesized by LLMs, but their integration is ambiguous and can lead to different global behaviors.
SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?
Paper ↗
Abstract
Code performance optimization is paramount in real-world software engineering and critical for production-level systems. While Large Language Models (LLMs) have demonstrated impressive capabilities in code generation and bug fixing, their proficiency in enhancing code performance at the repository level remains largely unexplored. To address this gap, we introduce SWE-Perf, the first benchmark specifically designed to systematically evaluate LLMs on code performance optimization tasks within authentic repository contexts. SWE-Perf comprises 140 carefully curated instances, each derived from performance-improving pull requests from popular GitHub repositories. Each benchmark instance includes the relevant codebase, target functions, performance-related tests, expert-authored patches, and executable environments. Through a comprehensive evaluation of representative methods that span file-level and repo-level approaches (e.g., Agentless and OpenHands), we reveal a substantial capability gap between existing LLMs and expert-level optimization performance, highlighting critical research opportunities in this emerging field.
Chain-of-Descriptions: Improving Code LLMs for VHDL Code Generation and Summarization
Paper ↗
Abstract
Large Language Models (LLMs) have become widely used across diverse NLP tasks and domains, demonstrating their adaptability and effectiveness. In the realm of Electronic Design Automation (EDA), LLMs show promise for tasks like Register-Transfer Level (RTL) code generation and summarization. However, despite the proliferation of LLMs for general code-related tasks, there's a dearth of research focused on evaluating and refining these models for hardware description languages (HDLs), notably VHDL. In this study, we evaluate the performance of existing code LLMs for VHDL code generation and summarization using various metrics and two datasets -- VHDL-Eval and VHDL-Xform. The latter, an in-house dataset, aims to gauge LLMs' understanding of functionally equivalent code. Our findings reveal consistent underperformance of these models across different metrics, underscoring a significant gap in their suitability for this domain. To address this challenge, we propose Chain-of-Descriptions (CoDes), a novel approach to enhance the performance of LLMs for VHDL code generation and summarization tasks. CoDes involves generating a series of intermediate descriptive steps based on: (i) the problem statement for code generation, and (ii) the VHDL code for summarization. These steps are then integrated with the original input prompt (problem statement or code) and provided as input to the LLMs to generate the final output. Our experiments demonstrate that the CoDes approach significantly surpasses the standard prompting strategy across various metrics on both datasets. This method not only improves the quality of VHDL code generation and summarization but also serves as a framework for future research aimed at enhancing code LLMs for VHDL.
Design Automation in Quantum Error Correction
Paper ↗
Abstract
Quantum error correction (QEC) underpins practical fault-tolerant quantum computing (FTQC) by addressing the fragility of quantum states and mitigating decoherence-induced errors. As quantum devices scale, integrating robust QEC protocols is imperative to suppress logical error rates below threshold and ensure reliable operation, though current frameworks suffer from substantial qubit overheads and hardware inefficiencies. Design automation in the QEC flow is thus critical, enabling automated synthesis, transpilation, layout, and verification of error-corrected circuits to reduce qubit footprints and push fault-tolerance margins. This chapter presents a comprehensive treatment of design automation in QEC, structured into four main sections. The first section delves into the theoretical aspects of QEC, covering logical versus physical qubit representations, stabilizer code construction, and error syndrome extraction mechanisms. In the second section, we outline the QEC design flow, detailing the areas highlighting the need for design automation. The third section surveys recent advancements in design automation techniques, including algorithmic $T$-gate optimization, modified surface code architecture to incorporate lesser qubit overhead, and machine-learning-based decoder automation. The final section examines near-term FTQC architectures, integrating automated QEC pipelines into scalable hardware platforms and discussing end-to-end verification methodologies. Each section is complemented by case studies of recent research works, illustrating practical implementations and performance trade-offs. Collectively, this chapter aims to equip readers with a holistic understanding of design automation in QEC system design in the fault-tolerant landscape of quantum computing.
Extremal Testing for Network Software using LLMs
Paper ↗
Abstract
Physicists often manually consider extreme cases when testing a theory. In this paper, we show how to automate extremal testing of network software using LLMs in two steps: first, ask the LLM to generate input constraints (e.g., DNS name length limits); then ask the LLM to generate tests that violate the constraints. We demonstrate how easy this process is by generating extremal tests for HTTP, BGP and DNS implementations, each of which uncovered new bugs. We show how this methodology extends to centralized network software such as shortest path algorithms, and how LLMs can generate filtering code to reject extremal input. We propose using agentic AI to further automate extremal testing. LLM-generated extremal testing goes beyond an old technique in software testing called Boundary Value Analysis.
An Agentic Flow for Finite State Machine Extraction using Prompt Chaining
Paper ↗
Abstract
Finite-State Machines (FSMs) are critical for modeling the operational logic of network protocols, enabling verification, analysis, and vulnerability discovery. However, existing FSM extraction techniques face limitations such as scalability, incomplete coverage, and ambiguity in natural language specifications. In this paper, we propose FlowFSM, a novel agentic framework that leverages Large Language Models (LLMs) combined with prompt chaining and chain-of-thought reasoning to extract accurate FSMs from raw RFC documents. FlowFSM systematically processes protocol specifications, identifies state transitions, and constructs structured rule-books by chaining agent outputs. Experimental evaluation across FTP and RTSP protocols demonstrates that FlowFSM achieves high extraction precision while minimizing hallucinated transitions, showing promising results. Our findings highlight the potential of agent-based LLM systems in the advancement of protocol analysis and FSM inference for cybersecurity and reverse engineering applications.
SIMCODE: A Benchmark for Natural Language to ns-3 Network Simulation Code Generation
Paper ↗
Abstract
Large language models (LLMs) have demonstrated remarkable capabilities in code generation across various domains. However, their effectiveness in generating simulation scripts for domain-specific environments like ns-3 remains underexplored. Despite the growing interest in automating network simulations, existing tools primarily focus on interactive automation over rigorous evaluation. To facilitate systematic evaluation, we introduce SIMCODE, the first benchmark to evaluate LLMs' ability to generate ns-3 simulation code from natural language. SIMCODE includes 400 tasks across introductory, intermediate, and advanced levels, with solutions and test cases. Using SIMCODE, we evaluate three prominent LLMs, Gemini-2.0, GPT-4.1, and Qwen-3, across six prompt techniques. Furthermore, investigating task-specific fine-tuning's impact reveals that while GPT-4.1 outperforms others, execution accuracy remains modest, with substantial room for improvement. Error analysis identifies missing headers and API mismatches as dominant failures. Nevertheless, SIMCODE provides a foundational step toward evaluating LLMs and research in domain-aware generative systems.
Mapping Fusion: Improving FPGA Technology Mapping with ASIC Mapper
Paper ↗
Abstract
LUT (Look-Up Table) mapping is a critical step in FPGA logic synthesis, where a logic network is transformed into a form that can be directly implemented using the FPGA's LUTs. An FPGA LUT is a flexible digital memory structure that can implement any logic function of a limited number of inputs, typically 4 to 6 inputs, depending on the FPGA architecture. The goal of LUT mapping is to map the Boolean network into LUTs, where each LUT can implement any function with a fixed number of inputs. In parallel to FPGA technology mapping, ASIC technology mapping maps the Boolean network to user-defined standard cells, which has traditionally been developed separately from LUT mapping algorithms. However, in this work, our motivating examples demonstrate that ASIC technology mappers can potentially improve the performance of LUT mappers, such that standard cell mapping and LUT mapping work in an incremental manner. Therefore, we propose the FuseMap framework, which explores this opportunity to improve LUT mapping in the FPGA design flow by utilizing reinforcement learning to make design-specific choices during cell selection. The effectiveness of FuseMap is evaluated on a wide range of benchmarks, different technology libraries, and technology mappers. The experimental results demonstrate that FuseMap achieves higher mapping accuracy while reducing delay and area across diverse circuit designs collected from ISCAS 85/89, ITC/ISCAS 99, VTR 8.0, and EPFL benchmarks.
AssertCoder: LLM-Based Assertion Generation via Multimodal Specification Extraction
Paper ↗
Abstract
Assertion-Based Verification (ABV) is critical for ensuring functional correctness in modern hardware systems. However, manually writing high-quality SVAs remains labor-intensive and error-prone. To bridge this gap, we propose AssertCoder, a novel unified framework that automatically generates high-quality SVAs directly from multimodal hardware design specifications. AssertCoder employs a modality-sensitive preprocessing to parse heterogeneous specification formats (text, tables, diagrams, and formulas), followed by a set of dedicated semantic analyzers that extract structured representations aligned with signal-level semantics. These representations are utilized to drive assertion synthesis via multi-step chain-of-thought (CoT) prompting. The framework incorporates a mutation-based evaluation approach to assess assertion quality via model checking and further refine the generated assertions. Experimental evaluation across three real-world Register-Transfer Level (RTL) designs demonstrates AssertCoder's superior performance, achieving an average increase of 8.4% in functional correctness and 5.8% in mutation detection compared to existing state-of-the-art approaches.
SPICEAssistant: LLM using SPICE Simulation Tools for Schematic Design of Switched-Mode Power Supplies
Paper ↗
Abstract
State-of-the-art large language models (LLMs) show high performance across a wide range of tasks in many domains of science. In the field of electronic design automation (EDA), it is yet to be determined to what extent they are capable to understand, adapt, and dimension electronic circuits. This paper focuses on the application of LLMs to switched-mode power supply (SMPS) design on printed circuit boards (PCBs). Particular challenges for LLMs in this context include their limited ability to interpret results from key simulation tools like SPICE and the multi-step design process. To address these challenges, we suggest SPICEAssistant, a framework that provides a broad selection of tools to an LLM. The tools serve as an interface to SPICE, allowing the LLM to interact flexibly with the simulator to estimate the impact of its modifications to the circuit. To evaluate the performance of SPICEAssistant, we defined a benchmark consisting of 256 questions testing the ability to adapt circuit netlists to fulfil different SMPS design tasks. The benchmarking results show that simulation feedback effectively improves SMPS design capabilities of LLMs. An increasing number of simulation iterations leads to enhanced performance. The SPICEAssistant framework significantly outperforms the standalone LLM GPT-4o on the benchmark by approximately 38%.
Cross-Timeslot Optimization for Distributed GPU Inference Using Reinforcement Learning
Paper ↗
Abstract
The rapid growth of large language model (LLM) services imposes increasing demands on distributed GPU inference infrastructure. Most existing scheduling systems rely on the current system state to make decisions, without considering how task demand and resource availability evolve over time. This lack of temporal awareness leads to inefficient GPU utilization, high task migration overhead, and poor system responsiveness under dynamic workloads. In this work, we identify the fundamental limitations of these instantaneous-state-only scheduling approaches and propose Temporal Optimal Resource scheduling via Two-layer Architecture (TORTA). TORTA introduces a spatiotemporal scheduling framework that captures both long-term workload patterns and short-term execution constraints. It adopts a two-layer design: a macro-level scheduler leverages reinforcement learning and optimal transport to coordinate inter-region task distribution, while a micro-level allocator refines task-to-server assignments within each region to reduce latency and switching costs. Experimental results across multiple network topologies show that TORTA reduces average inference response time by up to 15\%, improves load balance by approximately 4-5\%, and cuts total operational cost by 10-20\% compared to state-of-the-art baseline methods.
Temporal-Aware GPU Resource Allocation for Distributed LLM Inference via Reinforcement Learning
Paper ↗
Abstract
The rapid growth of large language model (LLM) services imposes increasing demands on distributed GPU inference infrastructure. Most existing scheduling systems follow a reactive paradigm, relying solely on the current system state to make decisions, without considering how task demand and resource availability evolve over time. This lack of temporal awareness in reactive approaches leads to inefficient GPU utilization, high task migration overhead, and poor system responsiveness under dynamic workloads. In this work, we identify the fundamental limitations of these instantaneous-state-only scheduling approaches and propose Temporal Optimal Resource scheduling via Two-layer Architecture (TORTA). TORTA introduces a spatiotemporal scheduling framework that captures both long-term workload patterns and short-term execution constraints. It adopts a two-layer design: a macro-level scheduler leverages reinforcement learning and optimal transport to coordinate inter-region task distribution, while a micro-level allocator refines task-to-server assignments within each region to reduce latency and switching costs. Experimental results across multiple network topologies show that TORTA reduces average inference response time by up to 15\%, improves load balance by approximately 4-5\%, and cuts total operational cost by 10-20\% compared to state-of-the-art baseline methods.
Temporal-Aware GPU Resource Allocation for Distributed LLM Inference via Reinforcement Learning
Paper ↗
Abstract
The rapid growth of large language model (LLM) services imposes increasing demands on distributed GPU inference infrastructure. Most existing scheduling systems follow a reactive paradigm, relying solely on the current system state to make decisions, without considering how task demand and resource availability evolve over time. This lack of temporal awareness in reactive approaches leads to inefficient GPU utilization, high task migration overhead, and poor system responsiveness under dynamic workloads. In this work, we identify the fundamental limitations of these instantaneous-state-only scheduling approaches and propose Temporal Optimal Resource scheduling via Two-layer Architecture (TORTA). TORTA introduces a spatiotemporal scheduling framework that captures both long-term workload patterns and short-term execution constraints. It adopts a two-layer design: a macro-level scheduler leverages reinforcement learning and optimal transport to coordinate inter-region task distribution, while a micro-level allocator refines task-to-server assignments within each region to reduce latency and switching costs. Experimental results across multiple network topologies show that TORTA reduces average inference response time by up to 15\%, improves load balance by approximately 4-5\%, and cuts total operational cost by 10-20\% compared to state-of-the-art baseline methods.
FRSICL: LLM-Enabled In-Context Learning Flight Resource Allocation for Fresh Data Collection in UAV-Assisted Wildfire Monitoring
Paper ↗
Abstract
Unmanned Aerial Vehicles (UAVs) are vital for public safety, particularly in wildfire monitoring, where early detection minimizes environmental impact. In UAV-Assisted Wildfire Monitoring (UAWM) systems, joint optimization of sensor transmission scheduling and velocity is critical for minimizing Age of Information (AoI) from stale sensor data. Deep Reinforcement Learning (DRL) has been used for such optimization; however, its limitations such as low sampling efficiency, simulation-to-reality gaps, and complex training render it unsuitable for time-critical applications like wildfire monitoring. This paper introduces a new online Flight Resource Allocation scheme based on LLM-Enabled In-Context Learning (FRSICL) to jointly optimize the UAV's flight control and data collection schedule along the trajectory in real time, thereby asymptotically minimizing the average AoI across ground sensors. In contrast to DRL, FRSICL generates data collection schedules and controls velocity using natural language task descriptions and feedback from the environment, enabling dynamic decision-making without extensive retraining. Simulation results confirm the effectiveness of the proposed FRSICL compared to Proximal Policy Optimization (PPO) and Nearest-Neighbor baselines.
AnalogTester: A Large Language Model-Based Framework for Automatic Testbench Generation in Analog Circuit Design
Paper ↗
Abstract
Recent advancements have demonstrated the significant potential of large language models (LLMs) in analog circuit design. Nevertheless, testbench construction for analog circuits remains manual, creating a critical bottleneck in achieving fully automated design processes. Particularly when replicating circuit designs from academic papers, manual Testbench construction demands time-intensive implementation and frequent adjustments, which fails to address the dynamic diversity and flexibility requirements for automation. AnalogTester tackles automated analog design challenges through an LLM-powered pipeline: a) domain-knowledge integration, b) paper information extraction, c) simulation scheme synthesis, and d) testbench code generation with Tsinghua Electronic Design (TED). AnalogTester has demonstrated automated Testbench generation capabilities for three fundamental analog circuit types: operational amplifiers (op-amps), bandgap references (BGRs), and low-dropout regulators (LDOs), while maintaining a scalable framework for adaptation to broader circuit topologies. Furthermore, AnalogTester can generate circuit knowledge data and TED code corpus, establishing fundamental training datasets for LLM specialization in analog circuit design automation.
Iceberg: Enhancing HLS Modeling with Synthetic Data
Paper ↗
Abstract
Deep learning-based prediction models for High-Level Synthesis (HLS) of hardware designs often struggle to generalize. In this paper, we study how to close the generalizability gap of these models through pretraining on synthetic data and introduce Iceberg, a synthetic data augmentation approach that expands both large language model (LLM)-generated programs and weak labels of unseen design configurations. Our weak label generation method is integrated with an in-context model architecture, enabling meta-learning from actual and proximate labels. Iceberg improves the geometric mean modeling accuracy by $86.4\%$ when adapt to six real-world applications with few-shot examples and achieves a $2.47\times$ and a $1.12\times$ better offline DSE performance when adapting to two different test datasets. Our open-sourced code is here: https://github.com/UCLA-VAST/iceberg
CADmium: Fine-Tuning Code Language Models for Text-Driven Sequential CAD Design
Paper ↗
Abstract
Computer-aided design (CAD) is the digital construction of 2D and 3D objects, and is central to a wide range of engineering and manufacturing applications like automobile and aviation. Despite its importance, CAD modeling remains largely a time-intensive, manual task. Recent works have attempted to automate this process with small transformer-based models and handcrafted CAD sequence representations. However, there has been little effort to leverage the potential of large language models (LLMs) for sequential CAD design. In this work, we introduce a new large-scale dataset of more than 170k CAD models annotated with high-quality, human-like descriptions generated with our pipeline based on GPT-4.1. Using this dataset, we fine-tune powerful code-LLMs to generate CAD sequences represented in a JSON-based format from natural language descriptions, demonstrating the viability and effectiveness of this approach for text-conditioned CAD generation. Because simple metrics often fail to reflect the quality of generated objects, we introduce geometric and topological metrics based on sphericity, mean curvature, and Euler characteristic to provide richer structural insights. Our experiments and ablation studies on both synthetic and human-annotated data demonstrate that CADmium is able to automate CAD design, drastically speeding up the design of new objects. The dataset, code, and fine-tuned models are available online.
Prompting for Performance: Exploring LLMs for Configuring Software
Paper ↗
Abstract
Software systems usually provide numerous configuration options that can affect performance metrics such as execution time, memory usage, binary size, or bitrate. On the one hand, making informed decisions is challenging and requires domain expertise in options and their combinations. On the other hand, machine learning techniques can search vast configuration spaces, but with a high computational cost, since concrete executions of numerous configurations are required. In this exploratory study, we investigate whether large language models (LLMs) can assist in performance-oriented software configuration through prompts. We evaluate several LLMs on tasks including identifying relevant options, ranking configurations, and recommending performant configurations across various configurable systems, such as compilers, video encoders, and SAT solvers. Our preliminary results reveal both positive abilities and notable limitations: depending on the task and systems, LLMs can well align with expert knowledge, whereas hallucinations or superficial reasoning can emerge in other cases. These findings represent a first step toward systematic evaluations and the design of LLM-based solutions to assist with software configuration.
DALI-PD: Diffusion-based Synthetic Layout Heatmap Generation for ML in Physical Design
Paper ↗
Abstract
Machine learning (ML) has demonstrated significant promise in various physical design (PD) tasks. However, model generalizability remains limited by the availability of high-quality, large-scale training datasets. Creating such datasets is often computationally expensive and constrained by IP. While very few public datasets are available, they are typically static, slow to generate, and require frequent updates. To address these limitations, we present DALI-PD, a scalable framework for generating synthetic layout heatmaps to accelerate ML in PD research. DALI-PD uses a diffusion model to generate diverse layout heatmaps via fast inference in seconds. The heatmaps include power, IR drop, congestion, macro placement, and cell density maps. Using DALI-PD, we created a dataset comprising over 20,000 layout configurations with varying macro counts and placements. These heatmaps closely resemble real layouts and improve ML accuracy on downstream ML tasks such as IR drop or congestion prediction.
LLM-Powered Quantum Code Transpilation
Paper ↗
Abstract
There exist various Software Development Kits (SDKs) tailored to different quantum computing platforms. These are known as Quantum SDKs (QSDKs). Examples include but are not limited to Qiskit, Cirq, and PennyLane. However, this diversity presents significant challenges for interoperability and cross-platform development of hybrid quantum-classical software systems. Traditional rule-based transpilers for translating code between QSDKs are time-consuming to design and maintain, requiring deep expertise and rigid mappings in the source and destination code. In this study, we explore the use of Large Language Models (LLMs) as a flexible and automated solution. Leveraging their pretrained knowledge and contextual reasoning capabilities, we position LLMs as programming language-agnostic transpilers capable of converting quantum programs from one QSDK to another while preserving functional equivalence. Our approach eliminates the need for manually defined transformation rules and offers a scalable solution to quantum software portability. This work represents a step toward enabling intelligent, general-purpose transpilation in the quantum computing ecosystem.
HedraRAG: Coordinating LLM Generation and Database Retrieval in Heterogeneous RAG Serving
Paper ↗
Abstract
This paper addresses emerging system-level challenges in heterogeneous retrieval-augmented generation (RAG) serving, where complex multi-stage workflows and diverse request patterns complicate efficient execution. We present HedraRAG, a runtime system built on a graph-based abstraction that exposes optimization opportunities across stage-level parallelism, intra-request similarity, and inter-request skewness. These opportunities are realized through dynamic graph transformations, such as node splitting, reordering, edge addition, and dependency rewiring, applied to wavefronts of subgraphs spanning concurrent requests. The resulting execution plans are mapped onto hybrid CPU-GPU pipelines to improve resource utilization and reduce latency. Evaluations across a wide range of RAG workflows demonstrate speedups exceeding 1.5x and reaching up to 5x over existing frameworks, showcasing the effectiveness of coordinated generation and retrieval in serving environments.
HedraRAG: Coordinating LLM Generation and Database Retrieval in Heterogeneous RAG Serving
Paper ↗
Abstract
This paper addresses emerging system-level challenges in heterogeneous retrieval-augmented generation (RAG) serving, where complex multi-stage workflows and diverse request patterns complicate efficient execution. We present HedraRAG, a runtime system built on a graph-based abstraction that exposes optimization opportunities across stage-level parallelism, intra-request similarity, and inter-request skewness. These opportunities are realized through dynamic graph transformations, such as node splitting, reordering, edge addition, and dependency rewiring, applied to wavefronts of subgraphs spanning concurrent requests. The resulting execution plans are mapped onto hybrid CPU-GPU pipelines to improve resource utilization and reduce latency. Evaluations across a wide range of RAG workflows demonstrate speedups exceeding 1.5x and reaching up to 5x over existing frameworks, showcasing the effectiveness of coordinated generation and retrieval in serving environments.
Agentic Large Language Models for Conceptual Systems Engineering and Design
Paper ↗
Abstract
Early-stage engineering design involves complex, iterative reasoning, yet existing large language model (LLM) workflows struggle to maintain task continuity and generate executable models. We evaluate whether a structured multi-agent system (MAS) can more effectively manage requirements extraction, functional decomposition, and simulator code generation than a simpler two-agent system (2AS). The target application is a solar-powered water filtration system as described in a cahier des charges. We introduce the Design-State Graph (DSG), a JSON-serializable representation that bundles requirements, physical embodiments, and Python-based physics models into graph nodes. A nine-role MAS iteratively builds and refines the DSG, while the 2AS collapses the process to a Generator-Reflector loop. Both systems run a total of 60 experiments (2 LLMs - Llama 3.3 70B vs reasoning-distilled DeepSeek R1 70B x 2 agent configurations x 3 temperatures x 5 seeds). We report a JSON validity, requirement coverage, embodiment presence, code compatibility, workflow completion, runtime, and graph size. Across all runs, both MAS and 2AS maintained perfect JSON integrity and embodiment tagging. Requirement coverage remained minimal (less than 20\%). Code compatibility peaked at 100\% under specific 2AS settings but averaged below 50\% for MAS. Only the reasoning-distilled model reliably flagged workflow completion. Powered by DeepSeek R1 70B, the MAS generated more granular DSGs (average 5-6 nodes) whereas 2AS mode-collapsed. Structured multi-agent orchestration enhanced design detail. Reasoning-distilled LLM improved completion rates, yet low requirements and fidelity gaps in coding persisted.
VerilogDB: The Largest, Highest-Quality Dataset with a Preprocessing Framework for LLM-based RTL Generation
Paper ↗
Abstract
Large Language Models (LLMs) are gaining popularity for hardware design automation, particularly through Register Transfer Level (RTL) code generation. In this work, we examine the current literature on RTL generation using LLMs and identify key requirements for training and fine-tuning datasets. We construct a robust Verilog dataset through an automated three-pronged process involving database (DB) creation and management with PostgreSQL, data collection from code hosting sites like OpenCores and GitHub, and data preprocessing to verify the codes' syntax, run logic synthesis, and extract relevant module metadata. We implement a scalable and efficient DB infrastructure to support analysis and detail our preprocessing pipeline to enforce high-quality data before DB insertion. The resulting dataset comprises 20,392 Verilog samples, 751 MB of Verilog code data, which is the largest high-quality Verilog dataset for LLM fine-tuning to our knowledge. We further evaluate the dataset, address associated challenges, and explore potential applications for future research and development in LLM-based hardware generation.
Text to model via SysML: Automated generation of dynamical system computational models from unstructured natural language text via enhanced System Modeling Language diagrams
Paper ↗
Abstract
This paper contributes to speeding up the design and deployment of engineering dynamical systems by proposing a strategy for exploiting domain and expert knowledge for the automated generation of dynamical system computational model starting from a corpus of document relevant to the dynamical system of interest and an input document describing the specific system. This strategy is implemented in five steps and, crucially, it uses system modeling language diagrams (SysML) to extract accurate information about the dependencies, attributes, and operations of components. Natural Language Processing (NLP) strategies and Large Language Models (LLMs) are employed in specific tasks to improve intermediate outputs of the SySML diagrams automated generation, such as: list of key nouns; list of extracted relationships; list of key phrases and key relationships; block attribute values; block relationships; and BDD diagram generation. The applicability of automated SysML diagram generation is illustrated with different case studies. The computational models of complex dynamical systems from SysML diagrams are then obtained via code generation and computational model generation steps. In the code generation step, NLP strategies are used for summarization, while LLMs are used for validation only. The proposed approach is not limited to a specific system, domain, or computational software. The applicability of the proposed approach is shown via an end-to-end example from text to model of a simple pendulum, showing improved performance compared to results yielded by LLMs only.
Towards LLM-based Root Cause Analysis of Hardware Design Failures
Paper ↗
Abstract
With advances in large language models (LLMs), new opportunities have emerged to develop tools that support the digital hardware design process. In this work, we explore how LLMs can assist with explaining the root cause of design issues and bugs that are revealed during synthesis and simulation, a necessary milestone on the pathway towards widespread use of LLMs in the hardware design process and for hardware security analysis. We find promising results: for our corpus of 34 different buggy scenarios, OpenAI's o3-mini reasoning model reached a correct determination 100% of the time under pass@5 scoring, with other state of the art models and configurations usually achieving more than 80% performance and more than 90% when assisted with retrieval-augmented generation.
gigiProfiler: Diagnosing Performance Issues by Uncovering Application Resource Bottlenecks
Paper ↗
Abstract
Diagnosing performance bottlenecks in modern software is essential yet challenging, particularly as applications become more complex and rely on custom resource management policies. While traditional profilers effectively identify execution bottlenecks by tracing system-level metrics, they fall short when it comes to application-level resource contention caused by waiting for application-level events. In this work, we introduce OmniResource Profiling, a performance analysis approach that integrates system-level and application-level resource tracing to diagnose resource bottlenecks comprehensively. gigiProfiler, our realization of OmniResource Profiling, uses a hybrid LLM-static analysis approach to identify application-defined resources offline and analyze their impact on performance during buggy executions to uncover the performance bottleneck. gigiProfiler then samples and records critical variables related to these bottleneck resources during buggy execution and compares their value with those from normal executions to identify the root causes. We evaluated gigiProfiler on 12 real-world performance issues across five applications. gigiProfiler accurately identified performance bottlenecks in all cases. gigiProfiler also successfully diagnosed the root causes of two newly emerged, previously undiagnosed problems, with the findings confirmed by developers.
SLDB: An End-To-End Heterogeneous System-on-Chip Benchmark Suite for LLM-Aided Design
Paper ↗
Abstract
Over the last few years, Large Language Models (LLMs) have emerged as a valuable tool for Electronic Design Automation (EDA). State-of-the-art research in LLM-aided design has demonstrated the ability of LLMs to generate syntactically correct RTL code, showcasing encouraging prospects for integrating AI into the hardware design process. A key enabler of these advancements is the availability of high-quality benchmarks to evaluate new approaches. However, existing datasets and benchmarks fall short of system-level design, as they focus primarily on component-level information and low-complexity designs. To address this gap, we introduce the System-Level Design Benchmark (SLDB), a dataset tailored for evaluating LLMs in system-level integration and configuration tasks. SLDB includes a curated benchmark suite of 10 baseline SoC designs, whose components can be combined into an exponential number of distinct tile-based SoCs through a synthetic library. The dataset provides full SoC configurations, accelerator integration code, communication parameters, and accelerator-aware system configurations, along with testing-application code, compatible with the ESP platform[1].
PrefixAgent: An LLM-Powered Design Framework for Efficient Prefix Adder Optimization
Paper ↗
Abstract
Prefix adders are fundamental arithmetic circuits, but their design space grows exponentially with bit-width, posing significant optimization challenges. Previous works face limitations in performance, generalization, and scalability. To address these challenges, we propose PrefixAgent, a large language model (LLM)-powered framework that enables efficient prefix adder optimization. Specifically, PrefixAgent reformulates the problem into subtasks including backbone synthesis and structure refinement, which effectively reduces the search space. More importantly, this new design perspective enables us to efficiently collect enormous high-quality data and reasoning traces with E-graph, which further results in an effective fine-tuning of LLM. Experimental results show that PrefixAgent synthesizes prefix adders with consistently smaller areas compared to baseline methods, while maintaining scalability and generalization in commercial EDA flows.
iThermTroj: Exploiting Intermittent Thermal Trojans in Multi-Processor System-on-Chips
Paper ↗
Abstract
Thermal Trojan attacks present a pressing concern for the security and reliability of System-on-Chips (SoCs), especially in mobile applications. The situation becomes more complicated when such attacks are more evasive and operate sporadically to stay hidden from detection mechanisms. In this paper, we introduce Intermittent Thermal Trojans (iThermTroj) that exploit the chips' thermal information in a random time-triggered manner. According to our experiments, iThermTroj attack can easily bypass available threshold-based thermal Trojan detection solutions. We investigate SoC vulnerabilities to variations of iThermTroj through an in-depth analysis of Trojan activation and duration scenarios. We also propose a set of tiny Machine Learning classifiers for run-time anomaly detection to protect SoCs against such intermittent thermal Trojan attacks. Compared to existing methods, our approach improves the attack detection rate by 29.4\%, 17.2\%, and 14.3\% in scenarios where iThermTroj manipulates up to 80\%, 60\%, and 40\% of SoC's thermal data, respectively. Additionally, our method increases the full protection resolution to 0.8 degrees Celsius, meaning that any temperature manipulations exceeding $\pm 0.8$ degrees will be detected with 100\% accuracy.
ChipSeek-R1: Generating Human-Surpassing RTL with LLM via Hierarchical Reward-Driven Reinforcement Learning
Paper ↗
Abstract
Large Language Models (LLMs) show significant potential for automating Register-Transfer Level (RTL) code generation. However, current approaches face a critical challenge: they can not simultaneously optimize for functional correctness and hardware quality (Power, Performance, Area - PPA). Methods based on supervised fine-tuning often generate functionally correct but PPA-suboptimal code, lacking mechanisms to learn optimization principles. In contrast, post-processing techniques that attempt to improve PPA metrics after generation are often inefficient because they operate externally without updating the LLM's parameters, thus failing to enhance the model's intrinsic design capabilities. To bridge this gap, we introduce ChipSeek-R1, a hierarchical reward-driven reinforcement learning framework to train LLMs to generate RTL code that achieves both functional correctness and optimized PPA metrics. ChipSeek-R1 employs a hierarchical reward system, which incorporates direct feedback on syntax, functional correctness (from simulators) and PPA metrics (from synthesis tools) during reinforcement learning. This enables the model to learn complex hardware design trade-offs via trial-and-error, generating RTL code that is both functionally correct and PPA-optimized. Evaluating ChipSeek-R1 on standard benchmarks (VerilogEval, RTLLM), we achieve state-of-the-art results in functional correctness. Notably, on the RTLLM benchmark, ChipSeek-R1 generated 27 RTL designs surpassing the PPA metrics of the original human-written code. Our findings demonstrate the effectiveness of integrating toolchain feedback into LLM training and highlight the potential for reinforcement learning to enable automated generation of human-surpassing RTL code. We open-source our code in anonymous github.
Performance Evaluation of General Purpose Large Language Models for Basic Linear Algebra Subprograms Code Generation
Paper ↗
Abstract
Generative AI technology based on Large Language Models (LLM) has been developed and applied to assist or automatically generate program codes. In this paper, we evaluate the capability of existing general LLMs for Basic Linear Algebra Subprograms (BLAS) code generation for CPUs. We use two LLMs provided by OpenAI: GPT-4.1, a Generative Pre-trained Transformer (GPT) model, and o4-mini, one of the o-series of Reasoning models. Both have been released in April 2025. For the routines from level-1 to 3 BLAS, we tried to generate (1) C code without optimization from routine name only, (2) C code with basic performance optimizations (thread parallelization, SIMD vectorization, and cache blocking) from routine name only, and (3) C code with basic performance optimizations based on Fortran reference code. As a result, we found that correct code can be generated in many cases even when only routine name are given. We also confirmed that thread parallelization with OpenMP, SIMD vectorization, and cache blocking can be implemented to some extent, and that the code is faster than the reference code.
HLStrans: Dataset for LLM-Driven C-to-HLS Hardware Code Synthesis
Paper ↗
Abstract
High-level synthesis (HLS) enables software developers to describe and implement hardware at a higher level of abstraction by using C/C++ instead of traditional hardware description languages to automatically generate FPGA-ready designs. However, generating HLS code significantly differs from standard C/C++: it disallows certain coding idioms, relies on specialized libraries, and critically requires fine-grained transformations and the insertion of optimization directives (pragmas) to achieve high performance. Large language models (LLMs) have shown promise in automating such transformations, yet existing open-source datasets lack sufficient complexity and optimization diversity. To address this gap, we introduce the HLStrans dataset, a comprehensive collection of 137 distinct real word programs, each annotated with a variety of C-to-HLS transformations that yield over 23K labeled design variants. These include a broad spectrum of pragmas and code-level optimizations. We benchmark state-of-the-art LLMs on this dataset to evaluate their ability to generate synthesizable, high-performance HLS code. As part of an ongoing effort, we plan to expand the HLStrans dataset in both scale and program variety, further empowering research at the intersection of AI and hardware synthesis.
FIXME: Towards End-to-End Benchmarking of LLM-Aided Design Verification
Paper ↗
Abstract
Despite the transformative potential of Large Language Models (LLMs) in hardware design, a comprehensive evaluation of their capabilities in design verification remains underexplored. Current efforts predominantly focus on RTL generation and basic debugging, overlooking the critical domain of functional verification, which is the primary bottleneck in modern design methodologies due to the rapid escalation of hardware complexity. We present FIXME, the first end-to-end, multi-model, and open-source evaluation framework for assessing LLM performance in hardware functional verification (FV) to address this crucial gap. FIXME introduces a structured three-level difficulty hierarchy spanning six verification sub-domains and 180 diverse tasks, enabling in-depth analysis across the design lifecycle. Leveraging a collaborative AI-human approach, we construct a high-quality dataset using 100% silicon-proven designs, ensuring comprehensive coverage of real-world challenges. Furthermore, we enhance the functional coverage by 45.57% through expert-guided optimization. By rigorously evaluating state-of-the-art LLMs such as GPT-4, Claude3, and LlaMA3, we identify key areas for improvement and outline promising research directions to unlock the full potential of LLM-driven automation in hardware design verification. The benchmark is available at https://github.com/ChatDesignVerification/FIXME.
Generative AI for CAD Automation: Leveraging Large Language Models for 3D Modelling
Paper ↗
Abstract
Large Language Models (LLMs) are revolutionizing industries by enhancing efficiency, scalability, and innovation. This paper investigates the potential of LLMs in automating Computer-Aided Design (CAD) workflows, by integrating FreeCAD with LLM as CAD design tool. Traditional CAD processes are often complex and require specialized sketching skills, posing challenges for rapid prototyping and generative design. We propose a framework where LLMs generate initial CAD scripts from natural language descriptions, which are then executed and refined iteratively based on error feedback. Through a series of experiments with increasing complexity, we assess the effectiveness of this approach. Our findings reveal that LLMs perform well for simple to moderately complex designs but struggle with highly constrained models, necessitating multiple refinements. The study highlights the need for improved memory retrieval, adaptive prompt engineering, and hybrid AI techniques to enhance script robustness. Future directions include integrating cloud-based execution and exploring advanced LLM capabilities to further streamline CAD automation. This work underscores the transformative potential of LLMs in design workflows while identifying critical areas for future development.
ForgeHLS: A Large-Scale, Open-Source Dataset for High-Level Synthesis
Paper ↗
Abstract
High-Level Synthesis (HLS) plays a crucial role in modern hardware design by transforming high-level code into optimized hardware implementations. However, progress in applying machine learning (ML) to HLS optimization has been hindered by a shortage of sufficiently large and diverse datasets. To bridge this gap, we introduce ForgeHLS, a large-scale, open-source dataset explicitly designed for ML-driven HLS research. ForgeHLS comprises over 400,000 diverse designs generated from 536 kernels covering a broad range of application domains. Each kernel includes systematically automated pragma insertions (loop unrolling, pipelining, array partitioning), combined with extensive design space exploration using Bayesian optimization. Compared to existing datasets, ForgeHLS significantly enhances scale, diversity, and design coverage. We further define and evaluate representative downstream tasks, such as Quality of Result (QoR) prediction and automated pragma exploration, clearly demonstrating ForgeHLS's utility for developing and improving ML-based HLS optimization methodologies.
ForgeHLS: A Large-Scale, Open-Source Dataset for High-Level Synthesis
Paper ↗
Abstract
High-Level Synthesis (HLS) plays a crucial role in modern hardware design by transforming high-level code into optimized hardware implementations. However, progress in applying machine learning (ML) to HLS optimization has been hindered by a shortage of sufficiently large and diverse datasets. To bridge this gap, we introduce ForgeHLS, a large-scale, open-source dataset explicitly designed for ML-driven HLS research. ForgeHLS comprises over 400k diverse designs generated from 846 kernels covering a broad range of application domains, consuming over 200k CPU hours during dataset construction. Each kernel includes systematically automated pragma insertions (loop unrolling, pipelining, array partitioning), combined with extensive design space exploration using Bayesian optimization. Compared to existing datasets, ForgeHLS significantly enhances scale, diversity, and design coverage. We further define and evaluate representative downstream tasks in Quality of Result (QoR) prediction and automated pragma exploration, clearly demonstrating ForgeHLS utility for developing and improving ML-based HLS optimization methodologies. The dataset and code are public at https://github.com/zedong-peng/ForgeHLS.
RCA Copilot: Transforming Network Data into Actionable Insights via Large Language Models
Paper ↗
Abstract
Ensuring the reliability and availability of complex networked services demands effective root cause analysis (RCA) across cloud environments, data centers, and on-premises networks. Traditional RCA methods, which involve manual inspection of data sources such as logs and telemetry data, are often time-consuming and challenging for on-call engineers. While statistical inference methods have been employed to estimate the causality of network events, these approaches alone are similarly challenging and suffer from a lack of interpretability, making it difficult for engineers to understand the predictions made by black-box models. In this paper, we present RCACopilot, an advanced on-call system that combines statistical tests and large language model (LLM) reasoning to automate RCA across various network environments. RCACopilot gathers and synthesizes critical runtime diagnostic information, predicts the root cause of incidents, provides a clear explanatory narrative, and offers targeted action steps for engineers to resolve the issues. By utilizing LLM reasoning techniques and retrieval, RCACopilot delivers accurate and practical support for operators.
LLM-Driven Auto Configuration for Transient IoT Device Collaboration
Paper ↗
Abstract
Today's Internet of Things (IoT) has evolved from simple sensing and actuation devices to those with embedded processing and intelligent services, enabling rich collaborations between users and their devices. However, enabling such collaboration becomes challenging when transient devices need to interact with host devices in temporarily visited environments. In such cases, fine-grained access control policies are necessary to ensure secure interactions; however, manually implementing them is often impractical for non-expert users. Moreover, at run-time, the system must automatically configure the devices and enforce such fine-grained access control rules. Additionally, the system must address the heterogeneity of devices. In this paper, we present CollabIoT, a system that enables secure and seamless device collaboration in transient IoT environments. CollabIoT employs a Large language Model (LLM)-driven approach to convert users' high-level intents to fine-grained access control policies. To support secure and seamless device collaboration, CollabIoT adopts capability-based access control for authorization and uses lightweight proxies for policy enforcement, providing hardware-independent abstractions. We implement a prototype of CollabIoT's policy generation and auto configuration pipelines and evaluate its efficacy on an IoT testbed and in large-scale emulated environments. We show that our LLM-based policy generation pipeline is able to generate functional and correct policies with 100% accuracy. At runtime, our evaluation shows that our system configures new devices in ~150 ms, and our proxy-based data plane incurs network overheads of up to 2 ms and access control overheads up to 0.3 ms.
On the Convergence of Large Language Model Optimizer for Black-Box Network Management
Paper ↗
Abstract
Future wireless networks are expected to incorporate diverse services that often lack general mathematical models. To address such black-box network management tasks, the large language model (LLM) optimizer framework, which leverages pretrained LLMs as optimization agents, has recently been promoted as a promising solution. This framework utilizes natural language prompts describing the given optimization problems along with past solutions generated by LLMs themselves. As a result, LLMs can obtain efficient solutions autonomously without knowing the mathematical models of the objective functions. Although the viability of the LLM optimizer (LLMO) framework has been studied in various black-box scenarios, it has so far been limited to numerical simulations. For the first time, this paper establishes a theoretical foundation for the LLMO framework. With careful investigations of LLM inference steps, we can interpret the LLMO procedure as a finite-state Markov chain, and prove the convergence of the framework. Our results are extended to a more advanced multiple LLM architecture, where the impact of multiple LLMs is rigorously verified in terms of the convergence rate. Comprehensive numerical simulations validate our theoretical results and provide a deeper understanding of the underlying mechanisms of the LLMO framework.
Hey AI, Generate Me a Hardware Code! Agentic AI-based Hardware Design & Verification
Paper ↗
Abstract
Modern Integrated Circuits (ICs) are becoming increasingly complex, and so is their development process. Hardware design verification entails a methodical and disciplined approach to the planning, development, execution, and sign-off of functionally correct hardware designs. This tedious process requires significant effort and time to ensure a bug-free tape-out. The field of Natural Language Processing has undergone a significant transformation with the advent of Large Language Models (LLMs). These powerful models, often referred to as Generative AI (GenAI), have revolutionized how machines understand and generate human language, enabling unprecedented advancements in a wide array of applications, including hardware design verification. This paper presents an agentic AI-based approach to hardware design verification, which empowers AI agents, in collaboration with Humain-in-the-Loop (HITL) intervention, to engage in a more dynamic, iterative, and self-reflective process, ultimately performing end-to-end hardware design and verification. This methodology is evaluated on five open-source designs, achieving over 95% coverage with reduced verification time while demonstrating superior performance, adaptability, and configurability.
DecoRTL: A Run-time Decoding Framework for RTL Code Generation with LLMs
Paper ↗
Abstract
As one of their many applications, large language models (LLMs) have recently shown promise in automating register transfer level (RTL) code generation. However, conventional LLM decoding strategies, originally designed for natural language, often fail to meet the structural and semantic demands of RTL, leading to hallucinated, repetitive, or invalid code outputs. In this paper, we first investigate the root causes of these decoding failures through an empirical analysis of token-level entropy during RTL generation. Our findings reveal that LLMs exhibit low confidence in regions of structural ambiguity or semantic complexity, showing that standard decoding strategies fail to differentiate between regions requiring determinism (syntax-critical regions) and those that benefit from creative exploratory variability (design-critical regions). Then, to overcome this, we introduce DecoRTL, a novel run-time decoding strategy, that is both syntax-aware and contrastive for RTL code generation. DecoRTL integrates two complementary components: (i) self-consistency sampling, which generates multiple candidates and re-ranks them based on token-level agreement to promote correctness while maintaining diversity; and (ii) syntax-aware temperature adaptation, which classifies tokens by their syntactical and functional roles and adjusts the sampling temperature accordingly, enforcing low temperature for syntax-critical tokens and higher temperature for exploratory ones. Our approach operates entirely at inference time without requiring any additional model fine-tuning. Through evaluations on multiple open-source LLMs using the VerilogEval benchmark, we demonstrate significant improvements in syntactic validity, functional correctness, and output diversity, while the execution overhead (performance overhead) is imperceptible.
CROP: Circuit Retrieval and Optimization with Parameter Guidance using LLMs
Paper ↗
Abstract
Modern very large-scale integration (VLSI) design requires the implementation of integrated circuits using electronic design automation (EDA) tools. Due to the complexity of EDA algorithms, the vast parameter space poses a huge challenge to chip design optimization, as the combination of even moderate numbers of parameters creates an enormous solution space to explore. Manual parameter selection remains industrial practice despite being excessively laborious and limited by expert experience. To address this issue, we present CROP, the first large language model (LLM)-powered automatic VLSI design flow tuning framework. Our approach includes: (1) a scalable methodology for transforming RTL source code into dense vector representations, (2) an embedding-based retrieval system for matching designs with semantically similar circuits, and (3) a retrieval-augmented generation (RAG)-enhanced LLM-guided parameter search system that constrains the search process with prior knowledge from similar designs. Experiment results demonstrate CROP's ability to achieve superior quality-of-results (QoR) with fewer iterations than existing approaches on industrial designs, including a 9.9% reduction in power consumption.
CROP: Circuit Retrieval and Optimization with Parameter Guidance using LLMs
Paper ↗
Abstract
Modern very large-scale integration (VLSI) design requires the implementation of integrated circuits using electronic design automation (EDA) tools. Due to the complexity of EDA algorithms, the vast parameter space poses a huge challenge to chip design optimization, as the combination of even moderate numbers of parameters creates an enormous solution space to explore. Manual parameter selection remains industrial practice despite being excessively laborious and limited by expert experience. To address this issue, we present CROP, the first large language model (LLM)-powered automatic VLSI design flow tuning framework. Our approach includes: (1) a scalable methodology for transforming RTL source code into dense vector representations, (2) an embedding-based retrieval system for matching designs with semantically similar circuits, and (3) a retrieval-augmented generation (RAG)-enhanced LLM-guided parameter search system that constrains the search process with prior knowledge from similar designs. Experiment results demonstrate CROP's ability to achieve superior quality-of-results (QoR) with fewer iterations than existing approaches on industrial designs, including a 9.9% reduction in power consumption.
ChatHLS: Towards Systematic Design Automation and Optimization for High-Level Synthesis
Paper ↗
Abstract
The increasing complexity of computational demands has accelerated the adoption of domain-specific accelerators, yet traditional hardware design methodologies remain constrained by prolonged development and verification cycles. High-Level Synthesis (HLS) bridges the gap between software and hardware by enabling hardware design from high-level programming languages. However, its widespread adoption is hindered by strict coding constraints and intricate hardware-specific optimizations, creating significant obstacles for developers. Recent advancements in Large Language Models (LLMs) demonstrate substantial potential in hardware design automation. However, their effectiveness is limited by the scarcity of high-quality datasets, particularly in the context of HLS. To address these challenges, we introduce ChatHLS, an agile HLS design automation and optimization workflow that leverages fine-tuned LLMs integrated within a multi-agent framework for error correction and design optimization. Our extensive evaluations reveal that ChatHLS achieves an average repair pass rate of 82.7% over 612 test cases, outperforming the GPT-4o and Llama3-8B by 19.1% and 63.0%, respectively. Furthermore, ChatHLS delivers performance enhancements ranging from 1.9$\times$ to 14.8$\times$ upon resource-constrained kernels. By enabling sophisticated optimization reasoning within practical computational budgets, ChatHLS attains a 4.9$\times$ geometric mean speedup compared to state-of-the-art DSL-based approaches. These results underscore the potential of ChatHLS in substantially expediting hardware development cycles while maintaining rigorous standards of design reliability and optimization quality.
ChatHLS: Towards Systematic Design Automation and Optimization for High-Level Synthesis
Paper ↗
Abstract
The increasing complexity of computational demands has spurred the adoption of domain-specific accelerators, yet traditional hardware design methodologies remain constrained by prolonged development and verification cycles. High-Level Synthesis (HLS) bridges the software-hardware gap by enabling hardware design from high-level languages. However, its widespread adoption is hindered by strict coding constraints and intricate hardware-specific optimizations. To address these challenges, we introduce ChatHLS, an agile HLS design automation workflow that leverages fine-tuned LLMs integrated within a multi-agent framework for HLS-specific error correction and design optimization. Through navigating LLM training with a novel verification-oriented data augmentation paradigm, ChatHLS achieves an average repair pass rate of 82.7% over 612 error cases. Furthermore, by enabling optimization reasoning within practical computational budgets, ChatHLS delivers performance improvements ranging from 1.9$\times$ to 14.8$\times$ on resource-constrained kernels, attaining a 3.6$\times$ average speedup compared to SOTA approaches. These results underscore the potential of ChatHLS in substantially expediting hardware development cycles while upholding rigorous standards of design reliability and quality.
Towards a Playground to Democratize Experimentation and Benchmarking of AI Agents for Network Troubleshooting
Paper ↗
Abstract
Recent research has demonstrated the effectiveness of Artificial Intelligence (AI), and more specifically, Large Language Models (LLMs), in supporting network configuration synthesis and automating network diagnosis tasks, among others. In this preliminary work, we restrict our focus to the application of AI agents to network troubleshooting and elaborate on the need for a standardized, reproducible, and open benchmarking platform, where to build and evaluate AI agents with low operational effort.
iPanda: An LLM-based Agent for Automated Conformance Testing of Communication Protocols
Paper ↗
Abstract
Conformance testing is essential for ensuring that protocol implementations comply with their specifications. However, traditional testing approaches involve manually creating numerous test cases and scripts, making the process labor-intensive and inefficient. Recently, Large Language Models (LLMs) have demonstrated impressive text comprehension and code generation abilities, providing promising opportunities for automation. In this paper, we propose iPanda, the first framework that leverages LLMs to automate protocol conformance testing. Given a protocol specification document and its implementation, iPanda first employs a keyword-based method to automatically generate comprehensive test cases. Then, it utilizes retrieval-augmented generation and customized CoT strategy to effectively interpret the implementation and produce executable test programs. To further enhance programs' quality, iPanda incorporates an iterative optimization mechanism to refine generated test scripts interactively. Finally, by executing and analyzing the generated tests, iPanda systematically verifies compliance between implementations and protocol specifications. Comprehensive experiments on various protocols show that iPanda significantly outperforms pure LLM-based approaches, improving the success rate (Pass@1) of test-program generation by factors ranging from 4.675 times to 10.751 times.
An AST-guided LLM Approach for SVRF Code Synthesis
Paper ↗
Abstract
Standard Verification Rule Format (SVRF) is essential for semiconductor applications like Design Rule Check (DRC), Layout Versus Schematic (LVS), and Optical Proximity Correction (OPC) and it faces challenges as advancing nodes create complex design rules that renders traditional SVRF development ineffective and highlight an expertise gap. This paper introduces a novel methodology integrating Abstract Syntax Tree (AST) embedding and Retrieval-Augmented Generation (RAG) for enhanced SVRF code synthesis, ensuring semantic accuracy and error minimization through structural validation with domain-specific insights for precise code generation. We evaluate different T5-based models and propose an innovative SVRF-specific scoring framework that complements standard metrics like BLEU and ROUGE-L. In our approach, AST provides rigorous structural validation, while RAG infuses relevant domain knowledge, effectively enhancing the code generation workflow. Testing on a comprehensive benchmark of 740 DRC rule implementations, our methodology demonstrates up to a 40\% improvement in code generation accuracy compared to basic text-based fine-tuning process. This fusion of industry expertise with advanced coding strategies not only optimizes SVRF development under limited dataset constraints but also creates a more intuitive and efficient coding environment. Consequently, users can rapidly iterate through design cycles, reduce manual error correction, and significantly improve overall productivity.
Fuzzing: Randomness? Reasoning! Efficient Directed Fuzzing via Large Language Models
Paper ↗
Abstract
Fuzzing is highly effective in detecting bugs due to the key contribution of randomness. However, randomness significantly reduces the efficiency of fuzzing, causing it to cost days or weeks to expose bugs. Even though directed fuzzing reduces randomness by guiding fuzzing towards target buggy locations, the dilemma of randomness still challenges directed fuzzers. Two critical components, which are seeds and mutators, contain randomness and are closely tied to the conditions required for triggering bugs. Therefore, to address the challenge of randomness, we propose to use large language models (LLMs) to remove the randomness in seeds and reduce the randomness in mutators. With their strong reasoning and code generation capabilities, LLMs can be used to generate reachable seeds that target pre-determined locations and to construct bug-specific mutators tailored for specific bugs. We propose RandLuzz, which integrates LLMs and directed fuzzing, to improve the quality of seeds and mutators, resulting in efficient bug exposure. RandLuzz analyzes function call chain or functionality to guide LLMs in generating reachable seeds. To construct bug-specific mutators, RandLuzz uses LLMs to perform bug analysis, obtaining information such as bug causes and mutation suggestions, which further help generate code that performs bug-specific mutations. We evaluate RandLuzz by comparing it with four state-of-the-art directed fuzzers, AFLGo, Beacon, WindRanger, and SelectFuzz. With RandLuzz-generated seeds, the fuzzers achieve an average speedup ranging from 2.1$\times$ to 4.8$\times$ compared to using widely-used initial seeds. Additionally, when evaluated on individual bugs, RandLuzz achieves up to a 2.7$\times$ speedup compared to the second-fastest exposure. On 8 bugs, RandLuzz can even expose them within 60 seconds.
P4OMP: Retrieval-Augmented Prompting for OpenMP Parallelism in Serial Code
Paper ↗
Abstract
We present P4OMP, a retrieval-augmented framework for transforming serial C/C++ code into OpenMP-annotated parallel code using large language models (LLMs). To our knowledge, this is the first system to apply retrieval-based prompting for OpenMP pragma correctness without model fine-tuning or compiler instrumentation. P4OMP leverages Retrieval-Augmented Generation (RAG) with structured instructional knowledge from OpenMP tutorials to improve the reliability of prompt-driven code generation. By grounding generation in the retrieved context, P4OMP improves syntactic correctness compared to baseline prompting with GPT-3.5-Turbo. We evaluate P4OMP against a baseline, GPT-3.5-Turbo without retrieval, on a comprehensive benchmark of 108 real-world C++ programs drawn from Stack Overflow, PolyBench, and NAS benchmark suites. P4OMP achieves 100% compilation success on all parallelizable cases, while the baseline fails to compile in 20 out of 108 cases. Six cases that rely on non-random-access iterators or thread-unsafe constructs are excluded due to fundamental OpenMP limitations. A detailed analysis demonstrates how P4OMP consistently avoids scoping errors, syntactic misuse, and invalid directive combinations that commonly affect baseline-generated code. We further demonstrate strong runtime scaling across seven compute-intensive benchmarks on an HPC cluster. P4OMP offers a robust, modular pipeline that significantly improves the reliability and applicability of LLM-generated OpenMP code.
Image2Net: Datasets, Benchmark and Hybrid Framework to Convert Analog Circuit Diagrams into Netlists
Paper ↗
Abstract
Large Language Model (LLM) exhibits great potential in designing of analog integrated circuits (IC) because of its excellence in abstraction and generalization for knowledge. However, further development of LLM-based analog ICs heavily relies on textual description of analog ICs, while existing analog ICs are mostly illustrated in image-based circuit diagrams rather than text-based netlists. Converting circuit diagrams to netlists help LLMs to enrich the knowledge of analog IC. Nevertheless, previously proposed conversion frameworks face challenges in further application because of limited support of image styles and circuit elements. Up to now, it still remains a challenging task to effectively convert complex circuit diagrams into netlists. To this end, this paper constructs and opensources a new dataset with rich styles of circuit diagrams as well as balanced distribution of simple and complex analog ICs. And a hybrid framework, named Image2Net, is proposed for practical conversion from circuit diagrams to netlists. The netlist edit distance (NED) is also introduced to precisely assess the difference between the converted netlists and ground truth. Based on our benchmark, Image2Net achieves 80.77\% successful rate, which is 34.62\%-45.19\% higher than previous works. Specifically, the proposed work shows 0.116 averaged NED, which is 62.1\%-69.6\% lower than state-of-the-arts.
EvoVerilog: Large Langugage Model Assisted Evolution of Verilog Code
Paper ↗
Abstract
Large Language Models (LLMs) have demonstrated great potential in automating the generation of Verilog hardware description language code for hardware design. This automation is critical to reducing human effort in the complex and error-prone process of hardware design. However, existing approaches predominantly rely on human intervention and fine-tuning using curated datasets, limiting their scalability in automated design workflows. Although recent iterative search techniques have emerged, they often fail to explore diverse design solutions and may underperform simpler approaches such as repeated prompting. To address these limitations, we introduce EvoVerilog, a novel framework that combines the reasoning capabilities of LLMs with evolutionary algorithms to automatically generate and refine Verilog code. EvoVerilog utilizes a multiobjective, population-based search strategy to explore a wide range of design possibilities without requiring human intervention. Extensive experiments demonstrate that EvoVerilog achieves state-of-the-art performance, with pass@10 scores of 89.1 and 80.2 on the VerilogEval-Machine and VerilogEval-Human benchmarks, respectively. Furthermore, the framework showcases its ability to explore diverse designs by simultaneously generating a variety of functional Verilog code while optimizing resource utilization.
ParEval-Repo: A Benchmark Suite for Evaluating LLMs with Repository-level HPC Translation Tasks
Paper ↗
Abstract
GPGPU architectures have become significantly diverse in recent years, which has led to an emergence of a variety of specialized programming models and software stacks to support them. While portable execution models exist, they still require significant developer effort to port to and optimize for different hardware architectures. Recent advances in large language models (LLMs) can help us reduce some of this programmer burden. In this paper, we present a novel benchmark and testing framework, ParEval-Repo, which can be used to evaluate the efficacy of LLM-based approaches in automatically translating entire codebases across GPGPU execution models. ParEval-Repo includes several scientific computing and AI mini-applications in a range of programming models, and levels of repository complexity. We use ParEval-Repo to evaluate a range of state-of-the-art open-source and commercial LLMs, with both a non-agentic and a top-down agentic approach. We assess code generated by the LLMs and approaches in terms of compilability, functional correctness, categories of build errors, and the cost of translation in terms of the number of inference tokens. Our results demonstrate that LLM translation of scientific applications is feasible for small programs but difficulty with generating functional build systems and cross-file dependencies pose challenges in scaling to larger codebases.
Omniwise: Predicting GPU Kernels Performance with LLMs
Paper ↗
Abstract
In recent years, the rapid advancement of deep neural networks (DNNs) has revolutionized artificial intelligence, enabling models with unprecedented capabilities in understanding, generating, and processing complex data. These powerful architectures have transformed a wide range of downstream applications, tackling tasks beyond human reach. In this paper, we introduce Omniwise, the first end-to-end, self-supervised fine-tuning pipeline that applies large language models (LLMs) to GPU kernel performance prediction--a novel use case in performance profiling. Omniwise is model-agnostic and lightweight, achieving strong results even with a small 3B-parameter model. It can predict key performance metrics, including memory bandwidth, cache hit rates, GFLOPs, and arithmetic intensity, directly from kernel code without the need for code execution or profiling tools. Our approach achieves over 90% of predictions within 10% relative error on GPU kernels executed on AMD MI250 and MI300X architectures. In addition to the pipeline, we develop an online inference server and a Visual Studio Code plugin that seamlessly integrate LLM-based performance prediction into developers' workflows.
GPU Kernel Scientist: An LLM-Driven Framework for Iterative Kernel Optimization
Paper ↗
Abstract
Optimizing GPU kernels for high performance is a complex task, often demanding deep architectural knowledge, extensive profiling, and iterative experimentation. This challenge is amplified when targeting newer or less-documented GPU architectures where traditional development aids are scarce. This paper introduces an LLM-powered "GPU Kernel Scientist," an automated methodology for iteratively refining accelerator kernels. Our methodology employs LLMs in a multi-stage, evolutionary process: (a) strategically selecting promising prior code versions as a basis for new iterations; (b) generating hypotheses for optimization experiments, based on existing code and assimilated knowledge from general GPU literature; and (c) autonomously implementing these experiments through code modification and subsequent submission to an external evaluation system, using only observed timing data as performance feedback. We detail how this approach navigates the challenges of the AMD MI300 target architecture and leverages LLMs to compensate for limited domain-specific human expertise. Since quantitative results from an ongoing performance competition were embargoed on paper submission date, we present the architectural design, operational workflow, and qualitative insights, highlighting the potential of LLM-driven agents to democratise and accelerate GPU kernel optimization, especially in resource-constrained or rapidly evolving hardware environments.
GPU Kernel Scientist: An LLM-Driven Framework for Iterative Kernel Optimization
Paper ↗
Abstract
Optimizing GPU kernels for high performance is a complex task, often demanding deep architectural knowledge, extensive profiling, and iterative experimentation. This challenge is amplified when targeting newer or less-documented GPU architectures where traditional development aids are scarce. This paper introduces an LLM-powered "GPU Kernel Scientist," an automated methodology for iteratively refining accelerator kernels. Our methodology employs LLMs in a multi-stage, evolutionary process: (a) strategically selecting promising prior code versions as a basis for new iterations; (b) generating hypotheses for optimization experiments, based on existing code and assimilated knowledge from general GPU literature; and (c) autonomously implementing these experiments through code modification and subsequent submission to an external evaluation system, using only observed timing data as performance feedback. We detail how this approach navigates the challenges of the AMD MI300 target architecture and leverages LLMs to compensate for limited domain-specific human expertise. In addition to our results, we present the architectural design, operational workflow, and qualitative insights, highlighting the potential of LLM-driven agents to democratise and accelerate GPU kernel optimization, especially in resource-constrained or rapidly updating hardware environment.
SV-LLM: An Agentic Approach for SoC Security Verification using Large Language Models
Paper ↗
Abstract
Ensuring the security of complex system-on-chips (SoCs) designs is a critical imperative, yet traditional verification techniques struggle to keep pace due to significant challenges in automation, scalability, comprehensiveness, and adaptability. The advent of large language models (LLMs), with their remarkable capabilities in natural language understanding, code generation, and advanced reasoning, presents a new paradigm for tackling these issues. Moving beyond monolithic models, an agentic approach allows for the creation of multi-agent systems where specialized LLMs collaborate to solve complex problems more effectively. Recognizing this opportunity, we introduce SV-LLM, a novel multi-agent assistant system designed to automate and enhance SoC security verification. By integrating specialized agents for tasks like verification question answering, security asset identification, threat modeling, test plan and property generation, vulnerability detection, and simulation-based bug validation, SV-LLM streamlines the workflow. To optimize their performance in these diverse tasks, agents leverage different learning paradigms, such as in-context learning, fine-tuning, and retrieval-augmented generation (RAG). The system aims to reduce manual intervention, improve accuracy, and accelerate security analysis, supporting proactive identification and mitigation of risks early in the design cycle. We demonstrate its potential to transform hardware security practices through illustrative case studies and experiments that showcase its applicability and efficacy.
Accelerating Photonic Integrated Circuit Design: Traditional, ML and Quantum Methods
Paper ↗
Abstract
Photonic Integrated Circuits (PICs) provide superior speed, bandwidth, and energy efficiency, making them ideal for communication, sensing, and quantum computing applications. Despite their potential, PIC design workflows and integration lag behind those in electronics, calling for groundbreaking advancements. This review outlines the state of PIC design, comparing traditional simulation methods with machine learning approaches that enhance scalability and efficiency. It also explores the promise of quantum algorithms and quantum-inspired methods to address design challenges.
A Large Language Model-based Multi-Agent Framework for Analog Circuits' Sizing Relationships Extraction
Paper ↗
Abstract
In the design process of the analog circuit pre-layout phase, device sizing is an important step in determining whether an analog circuit can meet the required performance metrics. Many existing techniques extract the circuit sizing task as a mathematical optimization problem to solve and continuously improve the optimization efficiency from a mathematical perspective. But they ignore the automatic introduction of prior knowledge, fail to achieve effective pruning of the search space, which thereby leads to a considerable compression margin remaining in the search space. To alleviate this problem, we propose a large language model (LLM)-based multi-agent framework for analog circuits' sizing relationships extraction from academic papers. The search space in the sizing process can be effectively pruned based on the sizing relationship extracted by this framework. Eventually, we conducted tests on 3 types of circuits, and the optimization efficiency was improved by $2.32 \sim 26.6 \times$. This work demonstrates that the LLM can effectively prune the search space for analog circuit sizing, providing a new solution for the combination of LLMs and conventional analog circuit design automation methods.
Leveraging Large Language Model for Intelligent Log Processing and Autonomous Debugging in Cloud AI Platforms
Paper ↗
Abstract
With the increasing complexity and rapid expansion of the scale of AI systems in cloud platforms, the log data generated during system operation is massive, unstructured, and semantically ambiguous, which brings great challenges to fault location and system self-repair. In order to solve this problem, this paper proposes an intelligent log processing and automatic debugging framework based on Large Language Model (LLM), named Intelligent Debugger (LLM-ID). This method is extended on the basis of the existing pre-trained Transformer model, and integrates a multi-stage semantic inference mechanism to realize the context understanding of system logs and the automatic reconstruction of fault chains. Firstly, the system log is dynamically structured, and the unsupervised clustering and embedding mechanism is used to extract the event template and semantic schema. Subsequently, the fine-tuned LLM combined with the multi-round attention mechanism to perform contextual reasoning on the log sequence to generate potential fault assumptions and root cause paths. Furthermore, this paper introduces a reinforcement learning-based policy-guided recovery planner, which is driven by the remediation strategy generated by LLM to support dynamic decision-making and adaptive debugging in the cloud environment. Compared with the existing rule engine or traditional log analysis system, the proposed model has stronger semantic understanding ability, continuous learning ability and heterogeneous environment adaptability. Experiments on the cloud platform log dataset show that LLM-ID improves the fault location accuracy by 16.2%, which is significantly better than the current mainstream methods
TROJAN-GUARD: Hardware Trojans Detection Using GNN in RTL Designs
Paper ↗
Abstract
Chip manufacturing is a complex process, and to achieve a faster time to market, an increasing number of untrusted third-party tools and designs from around the world are being utilized. The use of these untrusted third party intellectual properties (IPs) and tools increases the risk of adversaries inserting hardware trojans (HTs). The covert nature of HTs poses significant threats to cyberspace, potentially leading to severe consequences for national security, the economy, and personal privacy. Many graph neural network (GNN)-based HT detection methods have been proposed. However, they perform poorly on larger designs because they rely on training with smaller designs. Additionally, these methods do not explore different GNN models that are well-suited for HT detection or provide efficient training and inference processes. We propose a novel framework that generates graph embeddings for large designs (e.g., RISC-V) and incorporates various GNN models tailored for HT detection. Furthermore, our framework introduces domain-specific techniques for efficient training and inference by implementing model quantization. Model quantization reduces the precision of the weights, lowering the computational requirements, enhancing processing speed without significantly affecting detection accuracy. We evaluate our framework using a custom dataset, and our results demonstrate a precision of 98.66% and a recall (true positive rate) of 92.30%, highlighting the effectiveness and efficiency of our approach in detecting hardware trojans in large-scale chip designs
LASA: Enhancing SoC Security Verification with LLM-Aided Property Generation
Paper ↗
Abstract
Ensuring the security of modern System-on-Chip (SoC) designs poses significant challenges due to increasing complexity and distributed assets across the intellectual property (IP) blocks. Formal property verification (FPV) provides the capability to model and validate design behaviors through security properties with model checkers; however, current practices require significant manual efforts to create such properties, making them time-consuming, costly, and error-prone. The emergence of Large Language Models (LLMs) has showcased remarkable proficiency across diverse domains, including HDL code generation and verification tasks. Current LLM-based techniques often produce vacuous assertions and lack efficient prompt generation, comprehensive verification, and bug detection. This paper presents LASA, a novel framework that leverages LLMs and retrieval-augmented generation (RAG) to produce non-vacuous security properties and SystemVerilog Assertions (SVA) from design specifications and related documentation for bus-based SoC designs. LASA integrates commercial EDA tool for FPV to generate coverage metrics and iteratively refines prompts through a feedback loop to enhance coverage. The effectiveness of LASA is validated through various open-source SoC designs, demonstrating high coverage values with an average of ~88\%, denoting comprehensive verification through efficient generation of security properties and SVAs. LASA also demonstrates bug detection capabilities, identifying five unique bugs in the buggy OpenTitan SoC from Hack@DAC'24 competition.
Improving Compiler Bug Isolation by Leveraging Large Language Models
Paper ↗
Abstract
Compilers play a foundational role in building reliable software systems, and bugs within them can lead to catastrophic consequences. The compilation process typically involves hundreds of files, making traditional automated bug isolation techniques inapplicable due to scalability or effectiveness issues. Current mainstream compiler bug localization techniques have limitations in test program mutation and resource consumption. Inspired by the recent advances of pre-trained Large Language Models (LLMs), we propose an innovative approach named AutoCBI, which (1) uses LLMs to summarize compiler file functions and (2) employs specialized prompts to guide LLM in reordering suspicious file rankings. This approach leverages four types of information: the failing test program, source file function summaries, lists of suspicious files identified through analyzing test coverage, as well as compilation configurations with related output messages, resulting in a refined ranking of suspicious files. Our evaluation of AutoCBI against state-of-the-art approaches (DiWi, RecBi and FuseFL) on 120 real-world bugs from the widely-used GCC and LLVM compilers demonstrates its effectiveness. Specifically, AutoCBI isolates 66.67%/69.23%, 300%/340%, and 100%/57.14% more bugs than RecBi, DiWi, and FuseFL, respectively, in the Top-1 ranked results for GCC/LLVM. Additionally, the ablation study underscores the significance of each component in our approach.
VeriLocc: End-to-End Cross-Architecture Register Allocation via LLM
Paper ↗
Abstract
Modern GPUs evolve rapidly, yet production compilers still rely on hand-crafted register allocation heuristics that require substantial re-tuning for each hardware generation. We introduce VeriLocc, a framework that combines large language models (LLMs) with formal compiler techniques to enable generalizable and verifiable register allocation across GPU architectures. VeriLocc fine-tunes an LLM to translate intermediate representations (MIRs) into target-specific register assignments, aided by static analysis for cross-architecture normalization and generalization and a verifier-guided regeneration loop to ensure correctness. Evaluated on matrix multiplication (GEMM) and multi-head attention (MHA), VeriLocc achieves 85-99% single-shot accuracy and near-100% pass@100. Case study shows that VeriLocc discovers more performant assignments than expert-tuned libraries, outperforming rocBLAS by over 10% in runtime.
RCNet: $ΔΣ$ IADCs as Recurrent AutoEncoders
Paper ↗
Abstract
This paper proposes a deep learning model (RCNet) for Delta-Sigma ($\Delta\Sigma$) ADCs. Recurrent Neural Networks (RNNs) allow to describe both modulators and filters. This analogy is applied to Incremental ADCs (IADC). High-end optimizers combined with full-custom losses are used to define additional hardware design constraints: quantized weights, signal saturation, temporal noise injection, devices area. Focusing on DC conversion, our early results demonstrate that $SNR$ defined as an Effective Number Of Bits (ENOB) can be optimized under a certain hardware mapping complexity. The proposed RCNet succeeded to provide design tradeoffs in terms of $SNR$ ($>$13bit) versus area constraints ($<$14pF total capacitor) at a given $OSR$ (80 samples). Interestingly, it appears that the best RCNet architectures do not necessarily rely on high-order modulators, leveraging additional topology exploration degrees of freedom.
LiteGD: Lightweight and Dynamic GPU Dispatching for Large-scale Heterogeneous Clusters
Paper ↗
Abstract
Although multi-GPU execution has become the de-facto paradigm for training and serving large language models (LLMs), today's schedulers still rely on a simple heuristic: pick GPUs that are physically close. This proximity rule was adequate for small, uniform clusters, but it breaks down in modern fabrics where link capacities differ by up to an order of magnitude across PCIe, NVLink, and CXL tiers. Consequently, jobs placed by locality alone often suffer from severe bandwidth imbalance and unpredictable performance. In this paper, We present LiteGD, a lightweight, globally-aware GPU dispatching system that delivers near-optimal bandwidth without incurring prohibitive state or search overheads. Instead of materializing the full O(N^2) connectivity matrix, LiteGD encodes the fabric with a sparsified Tiny-Transformer trained on a few thousand random bandwidth probes, enabling fast adaptation to incremental hardware changes. LiteGD also employs a bidirectional tree search approach to find the optimal GPU dispatching in the data generated in the previous step, which can identify near-optimal solutions while reducing search overhead. We implement and evaluate LiteGD in both real and simulated GPU clusters with homogeneous and heterogeneous interconnects, respectively. Experimental results demonstrate that LiteGD consistently achieves high GPU Bandwidth Efficacy, approximately 90% across various cluster configurations and 80% in a real-world H100 cluster, significantly outperforming conventional default and interconnect topology-aware dispatching methods, particularly in large-scale heterogeneous environments.
Intelligent Assistants for the Semiconductor Failure Analysis with LLM-Based Planning Agents
Paper ↗
Abstract
Failure Analysis (FA) is a highly intricate and knowledge-intensive process. The integration of AI components within the computational infrastructure of FA labs has the potential to automate a variety of tasks, including the detection of non-conformities in images, the retrieval of analogous cases from diverse data sources, and the generation of reports from annotated images. However, as the number of deployed AI models increases, the challenge lies in orchestrating these components into cohesive and efficient workflows that seamlessly integrate with the FA process. This paper investigates the design and implementation of a Large Language Model (LLM)-based Planning Agent (LPA) to assist FA engineers in solving their analysis cases. The LPA integrates LLMs with advanced planning capabilities and external tool utilization, enabling autonomous processing of complex queries, retrieval of relevant data from external systems, and generation of human-readable responses. Evaluation results demonstrate the agent's operational effectiveness and reliability in supporting FA tasks.
Intelligent Assistants for the Semiconductor Failure Analysis with LLM-Based Planning Agents
Paper ↗
Abstract
Failure Analysis (FA) is a highly intricate and knowledge-intensive process. The integration of AI components within the computational infrastructure of FA labs has the potential to automate a variety of tasks, including the detection of non-conformities in images, the retrieval of analogous cases from diverse data sources, and the generation of reports from annotated images. However, as the number of deployed AI models increases, the challenge lies in orchestrating these components into cohesive and efficient workflows that seamlessly integrate with the FA process. This paper investigates the design and implementation of an agentic AI system for semiconductor FA using a Large Language Model (LLM)-based Planning Agent (LPA). The LPA integrates LLMs with advanced planning capabilities and external tool utilization, allowing autonomous processing of complex queries, retrieval of relevant data from external systems, and generation of human-readable responses. The evaluation results demonstrate the agent's operational effectiveness and reliability in supporting FA tasks.
ChatModel: Automating Reference Model Design and Verification with LLMs
Paper ↗
Abstract
As the complexity of integrated circuit designs continues to escalate, the functional verification becomes increasingly challenging. Reference models, critical for accelerating the verification process, are themselves becoming more intricate and time-consuming to develop. Despite the promise shown by large language models (LLMs) in code programming, effectively generating complex reference models remains a significant hurdle. To address these challenges, we introduce ChatModel, the first LLM-aided agile reference model generation and verification platform. ChatModel streamlines the transition from design specifications to fully functional reference models by integrating design standardization and hierarchical agile modeling. Employing a building-block generation strategy, it not only enhances the design capabilities of LLMs for reference models but also significantly boosts verification efficiency. We evaluated ChatModel on 300 designs of varying complexity, demonstrating substantial improvements in both efficiency and quality of reference model generation. ChatModel achieved a peak performance improvement of 55.02% compared to alternative methods, with notable enhancements in generation stability, and delivered a 9.18x increase in its capacity to produce reference model designs. Furthermore, it accelerated the iterative process of reference model design and validation by an average of 5.90x compared to traditional approaches. These results highlight the potential of ChatModel to significantly advance the automation of reference model generation and validation.
ChatModel: Automating Reference Model Design and Verification with LLMs
Paper ↗
Abstract
As the complexity of integrated circuit designs continues to escalate, the functional verification becomes increasingly challenging. Reference models, critical for accelerating the verification process, are themselves becoming more intricate and time-consuming to develop. Despite the promise shown by large language models (LLMs) in code programming, effectively generating complex reference models remains a significant hurdle. To address these challenges, we introduce ChatModel, the first LLM-aided agile reference model generation and verification platform. ChatModel streamlines the transition from design specifications to fully functional reference models by integrating design standardization and hierarchical agile modeling. Employing a building-block generation strategy, it not only enhances the design capabilities of LLMs for reference models but also significantly boosts verification efficiency. We evaluated ChatModel on 300 designs of varying complexity, demonstrating substantial improvements in both efficiency and quality of reference model generation. ChatModel achieved a peak performance improvement of 55.02% compared to alternative methods, with notable enhancements in generation stability, and delivered a 9.18x increase in its capacity to produce reference model designs. Furthermore, it accelerated the iterative process of reference model design and validation by an average of 5.90x compared to traditional approaches. These results highlight the potential of ChatModel to significantly advance the automation of reference model generation and validation.
Guaranteed Guess: A Language Modeling Approach for CISC-to-RISC Transpilation with Testing Guarantees
Paper ↗
Abstract
The hardware ecosystem is rapidly evolving, with increasing interest in translating low-level programs across different instruction set architectures (ISAs) in a quick, flexible, and correct way to enhance the portability and longevity of existing code. A particularly challenging class of this transpilation problem is translating between complex- (CISC) and reduced- (RISC) hardware architectures, due to fundamental differences in instruction complexity, memory models, and execution paradigms. In this work, we introduce GG (Guaranteed Guess), an ISA-centric transpilation pipeline that combines the translation power of pre-trained large language models (LLMs) with the rigor of established software testing constructs. Our method generates candidate translations using an LLM from one ISA to another, and embeds such translations within a software-testing framework to build quantifiable confidence in the translation. We evaluate our GG approach over two diverse datasets, enforce high code coverage (>98%) across unit tests, and achieve functional/semantic correctness of 99% on HumanEval programs and 49% on BringupBench programs, respectively. Further, we compare our approach to the state-of-the-art Rosetta 2 framework on Apple Silicon, showcasing 1.73x faster runtime performance, 1.47x better energy efficiency, and 2.41x better memory usage for our transpiled code, demonstrating the effectiveness of GG for real-world CISC-to-RISC translation tasks. We will open-source our codes, data, models, and benchmarks to establish a common foundation for ISA-level code translation research.
Spec2RTL-Agent: Automated Hardware Code Generation from Complex Specifications Using LLM Agent Systems
Paper ↗
Abstract
Despite recent progress in generating hardware RTL code with LLMs, existing solutions still suffer from a substantial gap between practical application scenarios and the requirements of real-world RTL code development. Prior approaches either focus on overly simplified hardware descriptions or depend on extensive human guidance to process complex specifications, limiting their scalability and automation potential. In this paper, we address this gap by proposing an LLM agent system, termed Spec2RTL-Agent, designed to directly process complex specification documentation and generate corresponding RTL code implementations, advancing LLM-based RTL code generation toward more realistic application settings. To achieve this goal, Spec2RTL-Agent introduces a novel multi-agent collaboration framework that integrates three key enablers: (1) a reasoning and understanding module that translates specifications into structured, step-by-step implementation plans; (2) a progressive coding and prompt optimization module that iteratively refines the code across multiple representations to enhance correctness and synthesisability for RTL conversion; and (3) an adaptive reflection module that identifies and traces the source of errors during generation, ensuring a more robust code generation flow. Instead of directly generating RTL from natural language, our system strategically generates synthesizable C++ code, which is then optimized for HLS. This agent-driven refinement ensures greater correctness and compatibility compared to naive direct RTL generation approaches. We evaluate Spec2RTL-Agent on three specification documents, showing it generates accurate RTL code with up to 75% fewer human interventions than existing methods. This highlights its role as the first fully automated multi-agent system for RTL generation from unstructured specs, reducing reliance on human effort in hardware design.
Spec2RTL-Agent: Automated Hardware Code Generation from Complex Specifications Using LLM Agent Systems
Paper ↗
Abstract
Despite recent progress in generating hardware RTL code with LLMs, existing solutions still suffer from a substantial gap between practical application scenarios and the requirements of real-world RTL code development. Prior approaches either focus on overly simplified hardware descriptions or depend on extensive human guidance to process complex specifications, limiting their scalability and automation potential. In this paper, we address this gap by proposing an LLM agent system, termed Spec2RTL-Agent, designed to directly process complex specification documentation and generate corresponding RTL code implementations, advancing LLM-based RTL code generation toward more realistic application settings. To achieve this goal, Spec2RTL-Agent introduces a novel multi-agent collaboration framework that integrates three key enablers: (1) a reasoning and understanding module that translates specifications into structured, step-by-step implementation plans; (2) a progressive coding and prompt optimization module that iteratively refines the code across multiple representations to enhance correctness and synthesisability for RTL conversion; and (3) an adaptive reflection module that identifies and traces the source of errors during generation, ensuring a more robust code generation flow. Instead of directly generating RTL from natural language, our system strategically generates synthesizable C++ code, which is then optimized for HLS. This agent-driven refinement ensures greater correctness and compatibility compared to naive direct RTL generation approaches. We evaluate Spec2RTL-Agent on three specification documents, showing it generates accurate RTL code with up to 75% fewer human interventions than existing methods. This highlights its role as the first fully automated multi-agent system for RTL generation from unstructured specs, reducing reliance on human effort in hardware design.
Spec2RTL-Agent: Automated Hardware Code Generation from Complex Specifications Using LLM Agent Systems
Paper ↗
Abstract
Despite recent progress in generating hardware RTL code with LLMs, existing solutions still suffer from a substantial gap between practical application scenarios and the requirements of real-world RTL code development. Prior approaches either focus on overly simplified hardware descriptions or depend on extensive human guidance to process complex specifications, limiting their scalability and automation potential. In this paper, we address this gap by proposing an LLM agent system, termed Spec2RTL-Agent, designed to directly process complex specification documentation and generate corresponding RTL code implementations, advancing LLM-based RTL code generation toward more realistic application settings. To achieve this goal, Spec2RTL-Agent introduces a novel multi-agent collaboration framework that integrates three key enablers: (1) a reasoning and understanding module that translates specifications into structured, step-by-step implementation plans; (2) a progressive coding and prompt optimization module that iteratively refines the code across multiple representations to enhance correctness and synthesisability for RTL conversion; and (3) an adaptive reflection module that identifies and traces the source of errors during generation, ensuring a more robust code generation flow. Instead of directly generating RTL from natural language, our system strategically generates synthesizable C++ code, which is then optimized for HLS. This agent-driven refinement ensures greater correctness and compatibility compared to naive direct RTL generation approaches. We evaluate Spec2RTL-Agent on three specification documents, showing it generates accurate RTL code with up to 75% fewer human interventions than existing methods. This highlights its role as the first fully automated multi-agent system for RTL generation from unstructured specs, reducing reliance on human effort in hardware design.
Cloud Infrastructure Management in the Age of AI Agents
Paper ↗
Abstract
Cloud infrastructure is the cornerstone of the modern IT industry. However, managing this infrastructure effectively requires considerable manual effort from the DevOps engineering team. We make a case for developing AI agents powered by large language models (LLMs) to automate cloud infrastructure management tasks. In a preliminary study, we investigate the potential for AI agents to use different cloud/user interfaces such as software development kits (SDK), command line interfaces (CLI), Infrastructure-as-Code (IaC) platforms, and web portals. We report takeaways on their effectiveness on different management tasks, and identify research challenges and potential solutions.
PRO-V: An Efficient Program Generation Multi-Agent System for Automatic RTL Verification
Paper ↗
Abstract
LLM-assisted hardware verification is gaining substantial attention due to its potential to significantly reduce the cost and effort of crafting effective testbenches. It also serves as a critical enabler for LLM-aided end-to-end hardware language design. However, existing current LLMs often struggle with Register Transfer Level (RTL) code generation, resulting in testbenches that exhibit functional errors in Hardware Description Languages (HDL) logic. Motivated by the strong performance of LLMs in Python code generation under inference-time sampling strategies, and their promising capabilities as judge agents, we propose PRO-V a fully program generation multi-agent system for robust RTL verification. Pro-V incorporates an efficient best-of-n iterative sampling strategy to enhance the correctness of generated testbenches. Moreover, it introduces an LLM-as-a-judge aid validation framework featuring an automated prompt generation pipeline. By converting rule-based static analysis from the compiler into natural language through in-context learning, this pipeline enables LLMs to assist the compiler in determining whether verification failures stem from errors in the RTL design or the testbench. PRO-V attains a verification accuracy of 87.17% on golden RTL implementations and 76.28% on RTL mutants. Our code is open-sourced at https://github.com/stable-lab/Pro-V.
Hybrid-NL2SVA: Integrating RAG and Finetuning for LLM-based NL2SVA
Paper ↗
Abstract
SystemVerilog Assertions (SVAs) are critical for verifying the correctness of hardware designs, but manually writing them from natural language property descriptions, i.e., NL2SVA, remains a labor-intensive and error-prone task. Recent advances in large language models (LLMs) offer opportunities to automate this translation. However, existing models still struggle with understanding domain-specific syntax and semantics. To enhance LLM performance in NL2SVA, we propose a customized retrieval-augmented generation (RAG) framework and a synthetic fine-tuning dataset that together improve LLM's performance. To further improve lightweight models over NL2SVA, our fine-tuning dataset provides prompt-guided explanations that teach LLMs the layer-by-layer construction process of concurrent SVAs, enabling supervised fine-tuning that greatly improves syntax and functionality accuracy. To evaluate the performance of LLMs over NL2SVA, we construct the largest evaluation dataset for NL2SVA, comprising 40 Verilog designs and 229 formally verified SVAs with detailed annotations. Experimental results show that our customized RAG framework increases the number of functionality matched SVAs by 58.42% over GPT-4o-mini, while Qwen2.5-Coder-7B-Instruct fine-tuned on our fine-tuning dataset and integrated with HybridRetrieval achieves a 59.05% over the base Qwen model.
BugGen: A Self-Correcting Multi-Agent LLM Pipeline for Realistic RTL Bug Synthesis
Paper ↗
Abstract
Hardware complexity continues to strain verification resources, motivating the adoption of machine learning (ML) methods to improve debug efficiency. However, ML-assisted debugging critically depends on diverse and scalable bug datasets, which existing manual or automated bug insertion methods fail to reliably produce. We introduce BugGen, a first of its kind, fully autonomous, multi-agent pipeline leveraging Large Language Models (LLMs) to systematically generate, insert, and validate realistic functional bugs in RTL. BugGen partitions modules, selects mutation targets via a closed-loop agentic architecture, and employs iterative refinement and rollback mechanisms to ensure syntactic correctness and functional detectability. Evaluated across five OpenTitan IP blocks, BugGen produced 500 unique bugs with 94% functional accuracy and achieved a throughput of 17.7 validated bugs per hour-over five times faster than typical manual expert insertion. Additionally, BugGen identified 104 previously undetected bugs in OpenTitan regressions, highlighting its utility in exposing verification coverage gaps. Compared against Certitude, BugGen demonstrated over twice the syntactic accuracy, deeper exposure of testbench blind spots, and more functionally meaningful and complex bug scenarios. Furthermore, when these BugGen-generated datasets were employed to train ML-based failure triage models, we achieved high classification accuracy (88.1%-93.2%) across different IP blocks, confirming the practical utility and realism of generated bugs. BugGen thus provides a scalable solution for generating high-quality bug datasets, significantly enhancing verification efficiency and ML-assisted debugging.
Efficient nanophotonic devices optimization using deep neural network trained with physics-based transfer learning (PBTL) methodology
Paper ↗
Abstract
We propose a neural network(NN)-based surrogate modeling framework for photonic device optimization, especially in domains with imbalanced feature importance and high data generation costs. Our framework, which comprises physics-based transfer learning (PBTL)-enhanced surrogate modeling and scalarized multi-objective genetic algorithms (GAs), offers a generalizable solution for photonic design automation with minimal data resources.To validate the framework, we optimize mid-infrared quantum cascade laser (QCL) structures consisting of two regions, active and injection, which have different levels of feature importance. The optimization targets include five key QCL performance metrics such as modal gain, emission wavelength, linewidth, and effective injection, extraction energies. To address the challenge of multiple local optima in the output latent space, we integrate a deep neural network total predictor (DNN-TP) with a GA, enabling scalable and nature-inspired optimization. By replacing computationally expensive numerical simulations with the DNN-TP surrogate model, the optimization achieves a speed-up of over 80,000 times, allowing large-scale exploration of the QCL design space.To improve model generalization with limited data, we introduce PBTL, which transfers knowledge from a DNN core predictor (DNN-CP) trained on active-region structures. This approach yields a 0.69 percentage increase in prediction accuracy, equivalent to a 50 percentage reduction in training data requirements, and leads to generate more feasible device structure with 60 percentage improvement in evaluation metric during optimization.
HPCTransCompile: An AI Compiler Generated Dataset for High-Performance CUDA Transpilation and LLM Preliminary Exploration
Paper ↗
Abstract
The rapid growth of deep learning has driven exponential increases in model parameters and computational demands. NVIDIA GPUs and their CUDA-based software ecosystem provide robust support for parallel computing, significantly alleviating computational bottlenecks. Meanwhile, due to the cultivation of user programming habits and the high performance of GPUs, the CUDA ecosystem has established a dominant position in the field of parallel software. This dominance requires other hardware platforms to support CUDA-based software with performance portability. However, translating CUDA code to other platforms poses significant challenges due to differences in parallel programming paradigms and hardware architectures. Existing approaches rely on language extensions, domain-specific languages (DSLs), or compilers but face limitations in workload coverage and generalizability. Moreover, these methods often incur substantial development costs. Recently, LLMs have demonstrated extraordinary potential in various vertical domains, especially in code-related tasks. However, the performance of existing LLMs in CUDA transpilation, particularly for high-performance code, remains suboptimal. To address these challenges, we propose a novel framework for generating high-performance CUDA and corresponding platform code pairs, leveraging AI compiler and automatic optimization technology. We further enhance the framework with a graph-based data augmentation method and introduce HPCTransEval, a benchmark for evaluating LLM performance on CUDA transpilation. We conduct experiments using CUDA-to-CPU transpilation as a case study on leading LLMs. The speedup ratio of the CPU operators has an average improvemnet of 43.8\%, highlighting the potential of LLMs to address compatibility challenges within the CUDA ecosystem. Our code is available at https://github.com/PJLAB-CHIP/HPCTransCompile.
D-LiFT: Improving LLM-based Decompiler Backend via Code Quality-driven Fine-tuning
Paper ↗
Abstract
Decompilers, which reconstruct human-readable source code from binary executables, are vital to many security tasks. Yet, despite recent advances, their output often suffers from syntactic and semantic errors and remains difficult to read. Recently, with the advent of large language models (LLMs), researchers began to explore the potential of LLMs to refine decompiler output. Nevertheless, our study of these approaches reveals significant limitations, such as introducing new errors and relying on unreliable accuracy validation. In this paper, we present D-LiFT, an automated decompiler backend that harnesses and further trains LLMs to improve the quality of decompiled code via reinforcement learning (RL). Unlike prior work that overlooks preserving accuracy, D-LiFT adheres to a key principle for enhancing the quality of decompiled code: \textit{preserving accuracy while improving readability}. Central to D-LiFT, we propose D-SCORE, an integrated quality assessment system to score the decompiled code from multiple aspects. In line with our principle, D-SCORE assigns low scores to any inaccurate output and only awards higher scores for readability to code that passes the accuracy check. Specifically, D-SCORE first verifies the syntactic and semantic correctness via the compiler and symbolic execution; only if a candidate is deemed accurate, it then evaluates readability using established metrics to compare the LLM output with the original decompiled code. The score will then be fed back to the LLM for fine-tuning. Our implementation, based on Ghidra and a range of LLMs, demonstrates significant improvements for the accurate decompiled code from the coreutils and util-linux projects. Compared to baseline LLMs without D-SCORE-driven fine-tuning, D-LiFT produces 55.3% more improved decompiled functions, as measured by D-SCORE.
SANGAM: SystemVerilog Assertion Generation via Monte Carlo Tree Self-Refine
Paper ↗
Abstract
Recent advancements in the field of reasoning using Large Language Models (LLMs) have created new possibilities for more complex and automatic Hardware Assertion Generation techniques. This paper introduces SANGAM, a SystemVerilog Assertion Generation framework using LLM-guided Monte Carlo Tree Search for the automatic generation of SVAs from industry-level specifications. The proposed framework utilizes a three-stage approach: Stage 1 consists of multi-modal Specification Processing using Signal Mapper, SPEC Analyzer, and Waveform Analyzer LLM Agents. Stage 2 consists of using the Monte Carlo Tree Self-Refine (MCTSr) algorithm for automatic reasoning about SVAs for each signal, and finally, Stage 3 combines the MCTSr-generated reasoning traces to generate SVA assertions for each signal. The results demonstrated that our framework, SANGAM, can generate a robust set of SVAs, performing better in the evaluation process in comparison to the recent methods.
TrioXpert: An automated incident management framework for microservice system
Paper ↗
Abstract
Automated incident management plays a pivotal role in large-scale microservice systems. However, many existing methods rely solely on single-modal data (e.g., metrics, logs, and traces) and struggle to simultaneously address multiple downstream tasks, including anomaly detection (AD), failure triage (FT), and root cause localization (RCL). Moreover, the lack of clear reasoning evidence in current techniques often leads to insufficient interpretability. To address these limitations, we propose TrioXpert, an end-to-end incident management framework capable of fully leveraging multimodal data. TrioXpert designs three independent data processing pipelines based on the inherent characteristics of different modalities, comprehensively characterizing the operational status of microservice systems from both numerical and textual dimensions. It employs a collaborative reasoning mechanism using large language models (LLMs) to simultaneously handle multiple tasks while providing clear reasoning evidence to ensure strong interpretability. We conducted extensive evaluations on two popular microservice system datasets, and the experimental results demonstrate that TrioXpert achieves outstanding performance in AD (improving by 4.7% to 57.7%), FT (improving by 2.1% to 40.6%), and RCL (improving by 1.6% to 163.1%) tasks.
Toward Scalable Quantum Compilation for Modular Architecture: Qubit Mapping and Reuse via Deep Reinforcement Learning
Paper ↗
Abstract
Modular quantum architectures have emerged as a promising approach for scaling quantum computing systems by connecting multiple Quantum Processing Units (QPUs). However, this approach introduces significant challenges due to costly inter-core operations between chips and quantum state transfers, which contribute to noise and quantum decoherence. This paper presents QARMA, a novel Qubit mapping using Attention-based deep Reinforcement learning (DRL) for Modular quantum Architectures, along with its extension QARMA-R that incorporates dynamic qubit reuse capabilities. Our approach combines an attention-based mechanism with Graph Neural Networks (GNN) to learn optimal qubit allocation, routing, and reuse strategies that minimize inter-core communications. We introduce two key innovations: (1) a transformer-based encoder that captures both the global circuit structure and local qubit interactions and (2) a dynamic qubit reuse compilation mechanism that leverages mid-circuit measurement and reset operations to reduce inter-operation and qubit requirements. Our experimental results show significant improvements over state-of-the-art approaches. Compared to highly-optimized Qiskit with modular architecture configuration, QARMA-R reduces inter-core communications by up to 100% (on average 85%), while QARMA maintains 15-40% improvement for larger circuits without reuse. Against traditional modular qubit mapping, our approach achieves 96.4-100% reduction in inter-core operation. The proposed methods advance quantum circuit compilation techniques and enable the execution of more extensive quantum algorithms on resource-constrained modular quantum systems, contributing to the growing body of research on scalable quantum computing architectures.
Toward Scalable Quantum Compilation for Modular Architecture: Qubit Mapping and Reuse via Deep Reinforcement Learning
Paper ↗
Abstract
Modular quantum architectures have emerged as a promising approach for scaling quantum computing systems by connecting multiple Quantum Processing Units (QPUs). However, this approach introduces significant challenges due to costly inter-core operations between chips and quantum state transfers, which contribute to noise and quantum decoherence. This paper presents QARMA, a novel Qubit mapping using Attention-based deep Reinforcement learning (DRL) for Modular quantum Architectures, along with its extension QARMA-R that incorporates dynamic qubit reuse capabilities. Our approach combines an attention-based mechanism with Graph Neural Networks (GNN) to learn optimal qubit allocation, routing, and reuse strategies that minimize inter-core communications. We introduce two key innovations: (1) a transformer-based encoder that captures both the global circuit structure and local qubit interactions and (2) a dynamic qubit reuse compilation mechanism that leverages mid-circuit measurement and reset operations to reduce inter-operation and qubit requirements. Our experimental results show significant improvements over state-of-the-art approaches. Compared to highly-optimized Qiskit with modular architecture configuration, QARMA-R reduces inter-core communications by up to 100% (on average 86%), while QARMA maintains 15-40% improvement for larger circuits without reuse. Against traditional modular qubit mapping, our approach achieves 97-100% reduction in inter-core operation. The proposed methods advance quantum circuit compilation techniques and enable the execution of more extensive quantum algorithms on resource-constrained modular quantum systems, contributing to the growing body of research on scalable quantum computing architectures.
CUDA-LLM: LLMs Can Write Efficient CUDA Kernels
Paper ↗
Abstract
Large Language Models (LLMs) have demonstrated strong capabilities in general-purpose code generation. However, generating the code which is deeply hardware-specific, architecture-aware, and performance-critical, especially for massively parallel GPUs, remains a complex challenge. In this work, we explore the use of LLMs for the automated generation and optimization of CUDA programs, with the goal of producing high-performance GPU kernels that fully exploit the underlying hardware. To address this challenge, we propose a novel framework called \textbf{Feature Search and Reinforcement (FSR)}. FSR jointly optimizes compilation and functional correctness, as well as the runtime performance, which are validated through extensive and diverse test cases, and measured by actual kernel execution latency on the target GPU, respectively. This approach enables LLMs not only to generate syntactically and semantically correct CUDA code but also to iteratively refine it for efficiency, tailored to the characteristics of the GPU architecture. We evaluate FSR on representative CUDA kernels, covering AI workloads and computational intensive algorithms. Our results show that LLMs augmented with FSR consistently guarantee correctness rates. Meanwhile, the automatically generated kernels can outperform general human-written code by a factor of up to 179$\times$ in execution speeds. These findings highlight the potential of combining LLMs with performance reinforcement to automate GPU programming for hardware-specific, architecture-sensitive, and performance-critical applications.
ORFS-agent: Tool-Using Agents for Chip Design Optimization
Paper ↗
Abstract
Machine learning has been widely used to optimize complex engineering workflows across numerous domains. In the context of integrated circuit design, modern flows (e.g., going from a register-transfer level netlist to physical layouts) involve extensive configuration via thousands of parameters, and small changes to these parameters can have large downstream impacts on desired outcomes - namely design performance, power, and area. Recent advances in Large Language Models (LLMs) offer new opportunities for learning and reasoning within such high-dimensional optimization tasks. In this work, we introduce ORFS-agent, an LLM-based iterative optimization agent that automates parameter tuning in an open-source hardware design flow. ORFS-agent adaptively explores parameter configurations, demonstrating clear improvements over standard Bayesian optimization approaches in terms of resource efficiency and final design metrics. Our empirical evaluations on two different technology nodes and a range of circuit benchmarks indicate that ORFS-agent can improve both routed wirelength and effective clock period by over 13%, all while using 40% fewer optimization iterations. Moreover, by following natural language objectives to trade off certain metrics for others, ORFS-agent demonstrates a flexible and interpretable framework for multi-objective optimization. Crucially, RFS-agent is modular and model-agnostic, and can be plugged in to any frontier LLM without any further fine-tuning.
ORFS-agent: Tool-Using Agents for Chip Design Optimization
Paper ↗
Abstract
Machine learning has been widely used to optimize complex engineering workflows across numerous domains. In the context of integrated circuit design, modern flows (e.g., going from a register-transfer level netlist to physical layouts) involve extensive configuration via thousands of parameters, and small changes to these parameters can have large downstream impacts on desired outcomes - namely design performance, power, and area. Recent advances in Large Language Models (LLMs) offer new opportunities for learning and reasoning within such high-dimensional optimization tasks. In this work, we introduce ORFS-agent, an LLM-based iterative optimization agent that automates parameter tuning in an open-source hardware design flow. ORFS-agent adaptively explores parameter configurations, demonstrating clear improvements over standard Bayesian optimization approaches in terms of resource efficiency and final design metrics. Our empirical evaluations on two different technology nodes and a range of circuit benchmarks indicate that ORFS-agent can improve both routed wirelength and effective clock period by over 13%, all while using 40% fewer optimization iterations. Moreover, by following natural language objectives to trade off certain metrics for others, ORFS-agent demonstrates a flexible and interpretable framework for multi-objective optimization. Crucially, RFS-agent is modular and model-agnostic, and can be plugged in to any frontier LLM without any further fine-tuning.
ProtocolLLM: RTL Benchmark for SystemVerilog Generation of Communication Protocols
Paper ↗
Abstract
Recent advances in large language models (LLMs) have demonstrated strong performance in generating code for general-purpose programming languages. However, their potential for hardware description languages (HDLs), such as SystemVerilog, remains largely unexplored. HDL code generation poses unique challenges due to strict timing semantics, concurrency, and synthesizability constraints essential for correct hardware functionality. Further, HDL-based design flows encompass a broad set of tasks beyond structural code generation, including testbench development, assertion-based verification, timing closure, and protocol-level integration for on-chip communication. In this work, we evaluate the capabilities of both open-source and state-of-the-art LLMs in generating synthesizable and functionally accurate SystemVerilog implementations of widely used communication protocols that are critical components of embedded and System-on-Chip (SoC) systems. We introduce ProtocolLLM, the first benchmark suite specifically targeting these protocols with tasks spanning multiple design abstraction levels and varying prompt specificity. Our evaluation method also focuses on timing correctness in addition to synthesizability and syntactic correctness. We observe that most of the models fail to generate SystemVerilog code for communication protocols that follow timing constrains.
An Intelligent Fault Self-Healing Mechanism for Cloud AI Systems via Integration of Large Language Models and Deep Reinforcement Learning
Paper ↗
Abstract
As the scale and complexity of cloud-based AI systems continue to increase, the detection and adaptive recovery of system faults have become the core challenges to ensure service reliability and continuity. In this paper, we propose an Intelligent Fault Self-Healing Mechanism (IFSHM) that integrates Large Language Model (LLM) and Deep Reinforcement Learning (DRL), aiming to realize a fault recovery framework with semantic understanding and policy optimization capabilities in cloud AI systems. On the basis of the traditional DRL-based control model, the proposed method constructs a two-stage hybrid architecture: (1) an LLM-driven fault semantic interpretation module, which can dynamically extract deep contextual semantics from multi-source logs and system indicators to accurately identify potential fault modes; (2) DRL recovery strategy optimizer, based on reinforcement learning, learns the dynamic matching of fault types and response behaviors in the cloud environment. The innovation of this method lies in the introduction of LLM for environment modeling and action space abstraction, which greatly improves the exploration efficiency and generalization ability of reinforcement learning. At the same time, a memory-guided meta-controller is introduced, combined with reinforcement learning playback and LLM prompt fine-tuning strategy, to achieve continuous adaptation to new failure modes and avoid catastrophic forgetting. Experimental results on the cloud fault injection platform show that compared with the existing DRL and rule methods, the IFSHM framework shortens the system recovery time by 37% with unknown fault scenarios.
VeriLoC: Line-of-Code Level Prediction of Hardware Design Quality from Verilog Code
Paper ↗
Abstract
Modern chip design is complex, and there is a crucial need for early-stage prediction of key design-quality metrics like timing and routing congestion directly from Verilog code (a commonly used programming language for hardware design). It is especially important yet complex to predict individual lines of code that cause timing violations or downstream routing congestion. Prior works have tried approaches like converting Verilog into an intermediate graph representation and using LLM embeddings alongside other features to predict module-level quality, but did not consider line-level quality prediction. We propose VeriLoC, the first method that predicts design quality directly from Verilog at both the line- and module-level. To this end, VeriLoC leverages recent Verilog code-generation LLMs to extract local line-level and module-level embeddings, and train downstream classifiers/regressors on concatenations of these embeddings. VeriLoC achieves high F1-scores of 0.86-0.95 for line-level congestion and timing prediction, and reduces the mean average percentage error from 14% - 18% for SOTA methods down to only 4%. We believe that VeriLoC embeddings and insights from our work will also be of value for other predictive and optimization tasks for complex hardware design.
MAGNet: A Multi-Scale Attention-Guided Graph Fusion Network for DRC Violation Detection
Paper ↗
Abstract
Design rule checking (DRC) is of great significance for cost reduction and design efficiency improvement in integrated circuit (IC) designs. Machine-learning-based DRC has become an important approach in computer-aided design (CAD). In this paper, we propose MAGNet, a hybrid deep learning model that integrates an improved U-Net with a graph neural network for DRC violation prediction. The U-Net backbone is enhanced with a Dynamic Attention Module (DAM) and a Multi-Scale Convolution Module (MSCM) to strengthen its capability in extracting fine-grained and multi-scale spatial features. In parallel, we construct a pixel-aligned graph structure based on chip layout tiles, and apply a specialized GNN to model the topological relationships among pins. During graph construction, a graph-to-grid mapping is generated to align GNN features with the layout image. In addition, a label amplification strategy is adopted during training to enhance the model's sensitivity to sparse violation patterns. Overall, MAGNet effectively combines spatial, semantic, and structural information, achieving improved prediction accuracy and reduced false positive rates in DRC hotspot detection. Subsequently, through incremental training, we achieve a more sensitive discrimination ability for hotspots. The results demonstrate that, in comparison with ibUnet, RouteNet, and J-Net, MAGnet significantly outperforms these models, achieving substantial improvements in overall performance.
PGR-DRC: Pre-Global Routing DRC Violation Prediction Using Unsupervised Learning
Paper ↗
Abstract
Leveraging artificial intelligence (AI)-driven electronic design and automation (EDA) tools, high-performance computing, and parallelized algorithms are essential for next-generation microprocessor innovation, ensuring continued progress in computing, AI, and semiconductor technology. Machine learning-based design rule checking (DRC) and lithography hotspot detection can improve first-pass silicon success. However, conventional ML and neural network (NN)-based models use supervised learning and require a large balanced dataset (in terms of positive and negative classes) and training time. This research addresses those key challenges by proposing the first-ever unsupervised DRC violation prediction methodology. The proposed model can be built using any unbalanced dataset using only one class and set a threshold for it, then fitting any new data querying if they are within the boundary of the model for classification. This research verified the proposed model by implementing different computational cores using CMOS 28 nm technology and Synopsys Design Compiler and IC Compiler II tools. Then, layouts were divided into virtual grids to collect about 60k data for analysis and verification. The proposed method has 99.95% prediction test accuracy, while the existing support vector machine (SVM) and neural network (NN) models have 85.44\% and 98.74\% accuracy, respectively. In addition, the proposed methodology has about 26.3x and up to 6003x lower training times compared to SVM and NN-models, respectively.
Recursive Learning-Based Virtual Buffering for Analytical Global Placement
Paper ↗
Abstract
Due to the skewed scaling of interconnect versus cell delay in modern technology nodes, placement with buffer porosity (i.e., cell density) awareness is essential for timing closure in physical synthesis flows. However, existing approaches face two key challenges: (i) traditional van Ginneken-Lillis-style buffering approaches are computationally expensive during global placement; and (ii) machine learning-based approaches, such as BufFormer, lack a thorough consideration of Electrical Rule Check (ERC) violations and fail to "close the loop" back into the physical design flow. In this work, we propose MLBuf-RePlAce, the first open-source learning-driven virtual buffering-aware analytical global placement framework, built on top of the OpenROAD infrastructure. MLBuf-RePlAce adopts an efficient recursive learning-based generative buffering approach to predict buffer types and locations, addressing ERC violations during global placement. We compare MLBuf-RePlAce against the default virtual buffering-based timing-driven global placer in OpenROAD, using open-source testcases from the TILOS MacroPlacement and OpenROAD-flow-scripts repositories. Without degradation of post-route power, MLBuf-RePlAce achieves (maximum, average) improvements of (56%, 31%) in total negative slack (TNS) within the open-source OpenROAD flow. When evaluated by completion in a commercial flow, MLBuf-RePlAce achieves (maximum, average) improvements of (53%, 28%) in TNS with an average of 0.2% improvement in post-route power.
Recursive Learning-Based Virtual Buffering for Analytical Global Placement
Paper ↗
Abstract
Due to the skewed scaling of interconnect versus cell delay in modern technology nodes, placement with buffer porosity (i.e., cell density) awareness is essential for timing closure in physical synthesis flows. However, existing approaches face two key challenges: (i) traditional van Ginneken-Lillis-style buffering approaches are computationally expensive during global placement; and (ii) machine learning-based approaches, such as BufFormer, lack a thorough consideration of Electrical Rule Check (ERC) violations and fail to "close the loop" back into the physical design flow. In this work, we propose MLBuf-RePlAce, the first open-source learning-driven virtual buffering-aware analytical global placement framework, built on top of the OpenROAD infrastructure. MLBuf-RePlAce adopts an efficient recursive learning-based generative buffering approach to predict buffer types and locations, addressing ERC violations during global placement. We compare MLBuf-RePlAce against the default virtual buffering-based timing-driven global placer in OpenROAD, using open-source testcases from the TILOS MacroPlacement and OpenROAD-flow-scripts repositories. Without degradation of post-route power, MLBuf-RePlAce achieves (maximum, average) improvements of (56%, 31%) in total negative slack (TNS) within the open-source OpenROAD flow. When evaluated by completion in a commercial flow, MLBuf-RePlAce achieves (maximum, average) improvements of (53%, 28%) in TNS with an average of 0.2% improvement in post-route power.
FuncGNN: Learning Functional Semantics of Logic Circuits with Graph Neural Networks
Paper ↗
Abstract
As integrated circuit scale grows and design complexity rises, effective circuit representation helps support logic synthesis, formal verification, and other automated processes in electronic design automation. And-Inverter Graphs (AIGs), as a compact and canonical structure, are widely adopted for representing Boolean logic in these workflows. However, the increasing complexity and integration density of modern circuits introduce structural heterogeneity and global logic information loss in AIGs, posing significant challenges to accurate circuit modeling. To address these issues, we propose FuncGNN, which integrates hybrid feature aggregation to extract multi-granularity topological patterns, thereby mitigating structural heterogeneity and enhancing logic circuit representations. FuncGNN further introduces gate-aware normalization that adapts to circuit-specific gate distributions, improving robustness to structural heterogeneity. Finally, FuncGNN employs multi-layer integration to merge intermediate features across layers, effectively synthesizing local and global semantic information for comprehensive logic representations. Experimental results on two logic-level analysis tasks (i.e., signal probability prediction and truth-table distance prediction) demonstrate that FuncGNN outperforms existing state-of-the-art methods, achieving improvements of 2.06% and 18.71%, respectively, while reducing training time by approximately 50.6% and GPU memory usage by about 32.8%.
Improving LLM-Powered EDA Assistants with RAFT
Paper ↗
Abstract
Electronic design engineers often struggle to efficiently access relevant information for tasks like design verification and technology development. While large language models (LLMs) can enhance productivity as conversational agents, pre-trained open-source LLMs lack domain-specific knowledge for Electronic Design Automation (EDA). In a Retrieval-Augmented Generation (RAG) context, LLMs rely on external context but may still produce inaccurate responses. Retrieval-Augmented Fine-Tuning (RAFT) improves LLM performance, but acquiring labeled question/answer (Q/A) data in EDA is difficult. To address this, we propose using synthetic Q/A datasets to enhance LLMs with RAFT. Our results show that RAFT with synthetic data significantly boosts LLM performance for RAG-based EDA tasks. We also investigate the impact of using real user questions as Retrieval-Augmented Few-Shot (RAFS) examples for synthetic data generation. Additionally, we implement secure access control to ensure sensitive information is only accessible to authorized personnel. Finally, we assess the risk of data leakage and unintended memorization during fine-tuning with synthetic data, providing practical insights.
CompilerGPT: Leveraging Large Language Models for Analyzing and Acting on Compiler Optimization Reports
Paper ↗
Abstract
Current compiler optimization reports often present complex, technical information that is difficult for programmers to interpret and act upon effectively. This paper assesses the capability of large language models (LLM) to understand compiler optimization reports and automatically rewrite the code accordingly. To this end, the paper introduces CompilerGPT, a novel framework that automates the interaction between compilers, LLMs, and user defined test and evaluation harness. CompilerGPT's workflow runs several iterations and reports on the obtained results. Experiments with two leading LLM models (GPT-4o and Claude Sonnet), optimization reports from two compilers (Clang and GCC), and five benchmark codes demonstrate the potential of this approach. Speedups of up to 6.5x were obtained, though not consistently in every test. This method holds promise for improving compiler usability and streamlining the software optimization process.
QiMeng: Fully Automated Hardware and Software Design for Processor Chip
Paper ↗
Abstract
Processor chip design technology serves as a key frontier driving breakthroughs in computer science and related fields. With the rapid advancement of information technology, conventional design paradigms face three major challenges: the physical constraints of fabrication technologies, the escalating demands for design resources, and the increasing diversity of ecosystems. Automated processor chip design has emerged as a transformative solution to address these challenges. While recent breakthroughs in Artificial Intelligence (AI), particularly Large Language Models (LLMs) techniques, have opened new possibilities for fully automated processor chip design, substantial challenges remain in establishing domain-specific LLMs for processor chip design. In this paper, we propose QiMeng, a novel system for fully automated hardware and software design of processor chips. QiMeng comprises three hierarchical layers. In the bottom-layer, we construct a domain-specific Large Processor Chip Model (LPCM) that introduces novel designs in architecture, training, and inference, to address key challenges such as knowledge representation gap, data scarcity, correctness assurance, and enormous solution space. In the middle-layer, leveraging the LPCM's knowledge representation and inference capabilities, we develop the Hardware Design Agent and the Software Design Agent to automate the design of hardware and software for processor chips. Currently, several components of QiMeng have been completed and successfully applied in various top-layer applications, demonstrating significant advantages and providing a feasible solution for efficient, fully automated hardware/software design of processor chips. Future research will focus on integrating all components and performing iterative top-down and bottom-up design processes to establish a comprehensive QiMeng system.
hdl2v: A Code Translation Dataset for Enhanced LLM Verilog Generation
Paper ↗
Abstract
Large language models (LLMs) are playing an increasingly large role in domains such as code generation, including hardware code generation, where Verilog is the key language. However, the amount of publicly available Verilog code pales in comparison to the amount of code available for software languages like Python. In this work, we present hdl2v ("HDL-to-Verilog"), a dataset which seeks to increase the amount of available human-written Verilog data by translating or compiling three other hardware description languages - VHDL, Chisel, and PyMTL3 - to Verilog. Furthermore, we demonstrate the value of hdl2v in enhancing LLM Verilog generation by improving performance of a 32 billion-parameter open-weight model by up to 23% (pass@10) in VerilogEvalV2, without utilizing any data augmentation or knowledge distillation from larger models. We also show hdl2v's ability to boost the performance of a data augmentation-based fine-tuning approach by 63%. Finally, we characterize and analyze our dataset to better understand which characteristics of HDL-to-Verilog datasets can be expanded upon in future work for even better performance.
A Framework Leveraging Large Language Models for Autonomous UAV Control in Flying Networks
Paper ↗
Abstract
This paper proposes FLUC, a modular framework that integrates open-source Large Language Models (LLMs) with Unmanned Aerial Vehicle (UAV) autopilot systems to enable autonomous control in Flying Networks (FNs). FLUC translates high-level natural language commands into executable UAV mission code, bridging the gap between operator intent and UAV behaviour. FLUC is evaluated using three open-source LLMs - Qwen 2.5, Gemma 2, and LLaMA 3.2 - across scenarios involving code generation and mission planning. Results show that Qwen 2.5 excels in multi-step reasoning, Gemma 2 balances accuracy and latency, and LLaMA 3.2 offers faster responses with lower logical coherence. A case study on energy-aware UAV positioning confirms FLUC's ability to interpret structured prompts and autonomously execute domain-specific logic, showing its effectiveness in real-time, mission-driven control.
Generating Automotive Code: Large Language Models for Software Development and Verification in Safety-Critical Systems
Paper ↗
Abstract
Developing safety-critical automotive software presents significant challenges due to increasing system complexity and strict regulatory demands. This paper proposes a novel framework integrating Generative Artificial Intelligence (GenAI) into the Software Development Lifecycle (SDLC). The framework uses Large Language Models (LLMs) to automate code generation in languages such as C++, incorporating safety-focused practices such as static verification, test-driven development and iterative refinement. A feedback-driven pipeline ensures the integration of test, simulation and verification for compliance with safety standards. The framework is validated through the development of an Adaptive Cruise Control (ACC) system. Comparative benchmarking of LLMs ensures optimal model selection for accuracy and reliability. Results demonstrate that the framework enables automatic code generation while ensuring compliance with safety-critical requirements, systematically integrating GenAI into automotive software engineering. This work advances the use of AI in safety-critical domains, bridging the gap between state-of-the-art generative models and real-world safety requirements.
VCDiag: Classifying Erroneous Waveforms for Failure Triage Acceleration
Paper ↗
Abstract
Failure triage in design functional verification is critical but time-intensive, relying on manual specification reviews, log inspections, and waveform analyses. While machine learning (ML) has improved areas like stimulus generation and coverage closure, its application to RTL-level simulation failure triage, particularly for large designs, remains limited. VCDiag offers an efficient, adaptable approach using VCD data to classify failing waveforms and pinpoint likely failure locations. In the largest experiment, VCDiag achieves over 94% accuracy in identifying the top three most likely modules. The framework introduces a novel signal selection and statistical compression approach, achieving over 120x reduction in raw data size while preserving features essential for classification. It can also be integrated into diverse Verilog/SystemVerilog designs and testbenches.
VCDiag: Classifying Erroneous Waveforms for Failure Triage Acceleration
Paper ↗
Abstract
Failure triage in design functional verification is critical but time-intensive, relying on manual specification reviews, log inspections, and waveform analyses. While machine learning (ML) has improved areas like stimulus generation and coverage closure, its application to RTL-level simulation failure triage, particularly for large designs, remains limited. VCDiag offers an efficient, adaptable approach using VCD data to classify failing waveforms and pinpoint likely failure locations. In the largest experiment, VCDiag achieves over 94% accuracy in identifying the top three most likely modules. The framework introduces a novel signal selection and statistical compression approach, achieving over 120x reduction in raw data size while preserving features essential for classification. It can also be integrated into diverse Verilog/SystemVerilog designs and testbenches.
VCDiag: Classifying Erroneous Waveforms for Failure Triage Acceleration
Paper ↗
Abstract
Failure triage in design functional verification is critical but time-intensive, relying on manual specification reviews, log inspections, and waveform analyses. While machine learning (ML) has improved areas like stimulus generation and coverage closure, its application to RTL-level simulation failure triage, particularly for large designs, remains limited. VCDiag offers an efficient, adaptable approach using VCD data to classify failing waveforms and pinpoint likely failure locations. In the largest experiment, VCDiag achieves over 94% accuracy in identifying the top three most likely modules. The framework introduces a novel signal selection and statistical compression approach, achieving over 120x reduction in raw data size while preserving features essential for classification. It can also be integrated into diverse Verilog/SystemVerilog designs and testbenches.
VCDiag: Classifying Erroneous Waveforms for Failure Triage Acceleration
Paper ↗
Abstract
Failure triage in design functional verification is critical but time-intensive, relying on manual specification reviews, log inspections, and waveform analyses. While machine learning (ML) has improved areas like stimulus generation and coverage closure, its application to RTL-level simulation failure triage, particularly for large designs, remains limited. VCDiag offers an efficient, adaptable approach using VCD data to classify failing waveforms and pinpoint likely failure locations. In the largest experiment, VCDiag achieves over 94% accuracy in identifying the top three most likely modules. The framework introduces a novel signal selection and statistical compression approach, achieving over 120x reduction in raw data size while preserving features essential for classification. It can also be integrated into diverse Verilog/SystemVerilog designs and testbenches.
VCDiag: Classifying Erroneous Waveforms for Failure Triage Acceleration
Paper ↗
Abstract
Failure triage in design functional verification is critical but time-intensive, relying on manual specification reviews, log inspections, and waveform analyses. While machine learning (ML) has improved areas like stimulus generation and coverage closure, its application to RTL-level simulation failure triage, particularly for large designs, remains limited. VCDiag offers an efficient, adaptable approach using VCD data to classify failing waveforms and pinpoint likely failure locations. In the largest experiment, VCDiag achieves over 94% accuracy in identifying the top three most likely modules. The framework introduces a novel signal selection and statistical compression approach, achieving over 120x reduction in raw data size while preserving features essential for classification. It can also be integrated into diverse Verilog/SystemVerilog designs and testbenches.
DCE-LLM: Dead Code Elimination with Large Language Models
Paper ↗
Abstract
Dead code introduces several challenges in software development, such as increased binary size and maintenance difficulties. It can also obscure logical errors and be exploited for obfuscation in malware. For LLM-based code-related tasks, dead code introduces vulnerabilities that can mislead these models, raising security concerns. Although modern compilers and IDEs offer dead code elimination, sophisticated patterns can bypass these tools. A universal approach that includes classification, location, explanation, and correction is needed, yet current tools often require significant manual effort. We present DCE-LLM, a framework for automated dead code elimination using a small CodeBERT model with an attribution-based line selector to efficiently locate suspect code. LLMs then generate judgments and explanations, fine-tuned on a large-scale, annotated dead code dataset to provide detailed explanations and patches. DCE-LLM outperforms existing tools, with advanced unreachability detection, automated correction, and support for multiple programming languages. Experimental results show DCE-LLM achieves over 94% F1 scores for unused and unreachable code, significantly surpassing GPT-4o by 30%.
Fast Machine Learning for Quantum Control of Microwave Qudits on Edge Hardware
Paper ↗
Abstract
Quantum optimal control is a promising approach to improve the accuracy of quantum gates, but it relies on complex algorithms to determine the best control settings. CPU or GPU-based approaches often have delays that are too long to be applied in practice. It is paramount to have systems with extremely low delays to quickly and with high fidelity adjust quantum hardware settings, where fidelity is defined as overlap with a target quantum state. Here, we utilize machine learning (ML) models to determine control-pulse parameters for preparing Selective Number-dependent Arbitrary Phase (SNAP) gates in microwave cavity qudits, which are multi-level quantum systems that serve as elementary computation units for quantum computing. The methodology involves data generation using classical optimization techniques, ML model development, design space exploration, and quantization for hardware implementation. Our results demonstrate the efficacy of the proposed approach, with optimized models achieving low gate trace infidelity near $10^{-3}$ and efficient utilization of programmable logic resources.
AUTOCIRCUIT-RL: Reinforcement Learning-Driven LLM for Automated Circuit Topology Generation
Paper ↗
Abstract
Analog circuit topology synthesis is integral to Electronic Design Automation (EDA), enabling the automated creation of circuit structures tailored to specific design requirements. However, the vast design search space and strict constraint adherence make efficient synthesis challenging. Leveraging the versatility of Large Language Models (LLMs), we propose AUTOCIRCUIT-RL,a novel reinforcement learning (RL)-based framework for automated analog circuit synthesis. The framework operates in two phases: instruction tuning, where an LLM learns to generate circuit topologies from structured prompts encoding design constraints, and RL refinement, which further improves the instruction-tuned model using reward models that evaluate validity, efficiency, and output voltage. The refined model is then used directly to generate topologies that satisfy the design constraints. Empirical results show that AUTOCIRCUIT-RL generates ~12% more valid circuits and improves efficiency by ~14% compared to the best baselines, while reducing duplicate generation rates by ~38%. It achieves over 60% success in synthesizing valid circuits with limited training data, demonstrating strong generalization. These findings highlight the framework's effectiveness in scaling to complex circuits while maintaining efficiency and constraint adherence, marking a significant advancement in AI-driven circuit design.
Large Processor Chip Model
Paper ↗
Abstract
Computer System Architecture serves as a crucial bridge between software applications and the underlying hardware, encompassing components like compilers, CPUs, coprocessors, and RTL designs. Its development, from early mainframes to modern domain-specific architectures, has been driven by rising computational demands and advancements in semiconductor technology. However, traditional paradigms in computer system architecture design are confronting significant challenges, including a reliance on manual expertise, fragmented optimization across software and hardware layers, and high costs associated with exploring expansive design spaces. While automated methods leveraging optimization algorithms and machine learning have improved efficiency, they remain constrained by a single-stage focus, limited data availability, and a lack of comprehensive human domain knowledge. The emergence of large language models offers transformative opportunities for the design of computer system architecture. By leveraging the capabilities of LLMs in areas such as code generation, data analysis, and performance modeling, the traditional manual design process can be transitioned to a machine-based automated design approach. To harness this potential, we present the Large Processor Chip Model (LPCM), an LLM-driven framework aimed at achieving end-to-end automated computer architecture design. The LPCM is structured into three levels: Human-Centric; Agent-Orchestrated; and Model-Governed. This paper utilizes 3D Gaussian Splatting as a representative workload and employs the concept of software-hardware collaborative design to examine the implementation of the LPCM at Level 1, demonstrating the effectiveness of the proposed approach. Furthermore, this paper provides an in-depth discussion on the pathway to implementing Level 2 and Level 3 of the LPCM, along with an analysis of the existing challenges.
Simplifying Root Cause Analysis in Kubernetes with StateGraph and LLM
Paper ↗
Abstract
Kubernetes, a notably complex and distributed system, utilizes an array of controllers to uphold cluster management logic through state reconciliation. Nevertheless, maintaining state consistency presents significant challenges due to unexpected failures, network disruptions, and asynchronous issues, especially within dynamic cloud environments. These challenges result in operational disruptions and economic losses, underscoring the necessity for robust root cause analysis (RCA) to enhance Kubernetes reliability. The development of large language models (LLMs) presents a promising direction for RCA. However, existing methodologies encounter several obstacles, including the diverse and evolving nature of Kubernetes incidents, the intricate context of incidents, and the polymorphic nature of these incidents. In this paper, we introduce SynergyRCA, an innovative tool that leverages LLMs with retrieval augmentation from graph databases and enhancement with expert prompts. SynergyRCA constructs a StateGraph to capture spatial and temporal relationships and utilizes a MetaGraph to outline entity connections. Upon the occurrence of an incident, an LLM predicts the most pertinent resource, and SynergyRCA queries the MetaGraph and StateGraph to deliver context-specific insights for RCA. We evaluate SynergyRCA using datasets from two production Kubernetes clusters, highlighting its capacity to identify numerous root causes, including novel ones, with high efficiency and precision. SynergyRCA demonstrates the ability to identify root causes in an average time of about two minutes and achieves an impressive precision of approximately 0.90.
SALAD: Systematic Assessment of Machine Unlearing on LLM-Aided Hardware Design
Paper ↗
Abstract
Large Language Models (LLMs) offer transformative capabilities for hardware design automation, particularly in Verilog code generation. However, they also pose significant data security challenges, including Verilog evaluation data contamination, intellectual property (IP) design leakage, and the risk of malicious Verilog generation. We introduce SALAD, a comprehensive assessment that leverages machine unlearning to mitigate these threats. Our approach enables the selective removal of contaminated benchmarks, sensitive IP and design artifacts, or malicious code patterns from pre-trained LLMs, all without requiring full retraining. Through detailed case studies, we demonstrate how machine unlearning techniques effectively reduce data security risks in LLM-aided hardware design.
SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design
Paper ↗
Abstract
Large Language Models (LLMs) offer transformative capabilities for hardware design automation, particularly in Verilog code generation. However, they also pose significant data security challenges, including Verilog evaluation data contamination, intellectual property (IP) design leakage, and the risk of malicious Verilog generation. We introduce SALAD, a comprehensive assessment that leverages machine unlearning to mitigate these threats. Our approach enables the selective removal of contaminated benchmarks, sensitive IP and design artifacts, or malicious code patterns from pre-trained LLMs, all without requiring full retraining. Through detailed case studies, we demonstrate how machine unlearning techniques effectively reduce data security risks in LLM-aided hardware design.
SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design
Paper ↗
Abstract
Large Language Models (LLMs) offer transformative capabilities for hardware design automation, particularly in Verilog code generation. However, they also pose significant data security challenges, including Verilog evaluation data contamination, intellectual property (IP) design leakage, and the risk of malicious Verilog generation. We introduce SALAD, a comprehensive assessment that leverages machine unlearning to mitigate these threats. Our approach enables the selective removal of contaminated benchmarks, sensitive IP and design artifacts, or malicious code patterns from pre-trained LLMs, all without requiring full retraining. Through detailed case studies, we demonstrate how machine unlearning techniques effectively reduce data security risks in LLM-aided hardware design.
Compiler Optimization via LLM Reasoning for Efficient Model Serving
Paper ↗
Abstract
While model serving has unlocked unprecedented capabilities, the high cost of serving large-scale models continues to be a significant barrier to widespread accessibility and rapid innovation. Compiler optimizations have long driven substantial performance improvements, but existing compilers struggle with neural workloads due to the exponentially large and highly interdependent space of possible transformations. Although existing stochastic search techniques can be effective, they are often sample-inefficient and fail to leverage the structural context underlying compilation decisions. We set out to investigate the research question of whether reasoning with large language models (LLMs), without any retraining, can leverage the context-aware decision space of compiler optimization to significantly improve sample efficiency. To that end, we introduce a novel compilation framework (dubbed REASONING COMPILER) that formulates optimization as a sequential, context-aware decision process, guided by a large language model and structured Monte Carlo tree search (MCTS). The LLM acts as a proposal mechanism, suggesting hardware-aware transformations that reflect the current program state and accumulated performance feedback. Monte Carlo tree search (MCTS) incorporates the LLM-generated proposals to balance exploration and exploitation, facilitating structured, context-sensitive traversal of the expansive compiler optimization space. By achieving substantial speedups with markedly fewer samples than leading neural compilers, our approach demonstrates the potential of LLM-guided reasoning to transform the landscape of compiler optimization.
Inverse Design in Distributed Circuits Using Single-Step Reinforcement Learning
Paper ↗
Abstract
The goal of inverse design in distributed circuits is to generate near-optimal designs that meet a desirable transfer function specification. Existing design exploration methods use some combination of strategies involving artificial grids, differentiable evaluation procedures, and specific template topologies. However, real-world design practices often require non-differentiable evaluation procedures, varying topologies, and near-continuous placement spaces. In this paper, we propose DCIDA, a design exploration framework that learns a near-optimal design sampling policy for a target transfer function. DCIDA decides all design factors in a compound single-step action by sampling from a set of jointly-trained conditional distributions generated by the policy. Utilizing an injective interdependent ``map", DCIDA transforms raw sampled design ``actions" into uniquely equivalent physical representations, enabling the framework to learn the conditional dependencies among joint ``raw'' design decisions. Our experiments demonstrate DCIDA's Transformer-based policy network achieves significant reductions in design error compared to state-of-the-art approaches, with significantly better fit in cases involving more complex transfer functions.
SysLLMatic: Large Language Models are Software System Optimizers
Paper ↗
Abstract
Automatic software system optimization can improve software speed, reduce operating costs, and save energy. Traditional approaches to optimization rely on manual tuning and compiler heuristics, limiting their ability to generalize across diverse codebases and system contexts. Recent methods using Large Language Models (LLMs) offer automation to address these limitations, but often fail to scale to the complexity of real-world software systems and applications. We present SysLLMatic, a system that integrates LLMs with profiling-guided feedback and system performance insights to automatically optimize software code. We evaluate it on three benchmark suites: HumanEval_CPP (competitive programming in C++), SciMark2 (scientific kernels in Java), and DaCapoBench (large-scale software systems in Java). Results show that SysLLMatic can improve system performance, including latency, throughput, energy efficiency, memory usage, and CPU utilization. It consistently outperforms state-of-the-art LLM baselines on microbenchmarks. On large-scale application codes, it surpasses traditional compiler optimizations, achieving average relative improvements of 1.85x in latency and 2.24x in throughput. Our findings demonstrate that LLMs, guided by principled systems thinking and appropriate performance diagnostics, can serve as viable software system optimizers. We further identify limitations of our approach and the challenges involved in handling complex applications. This work provides a foundation for generating optimized code across various languages, benchmarks, and program sizes in a principled manner.
iVAMS 3.0: Hierarchical-Machine-Learning-Metamodel-Integrated Intelligent Verilog-AMS for Ultra-Fast, Accurate Mixed-Signal Design Optimization
Paper ↗
Abstract
Analog/Mixed-Signal (AMS) circuits and systems continually present significant challenges to designers with the increase of design complexity and aggressive technology scaling. This is due to the large number of design factors and parameters that must be taken into account as well as the process variations which are prominent in nano-CMOS circuits. Design optimization techniques while presenting an accurate and fast design flow which can perform design optimization in reasonable time are still lacking. Even with techniques such as metamodeling that aid the design phase, there is still the need to improve them for accuracy and time cost. As a trade-off of the accuracy and speed, this paper presents a design flow for ultra-fast variability-aware optimization of nano-CMOS based physical design of analog circuits. It combines a Kriging bootstrapped Artificial Neural Network (ANN) metamodel with a Particle Swarm Optimization (PSO) based algorithm in the design optimization flow. The Kriging bootstrapped ANN metamodel provides a trade-off between analog-quality accuracy and scalability and can be effectively used for large and complex AMS circuits. The proposed technique uses Kriging to bootstrap target samples used for the ANN training. This introduces Kriging characteristics, which account for correlation effects between design parameters, to the ANN. The effectiveness of the design flow is demonstrated using a PLL as a case study with as many as 21 design parameters. It is observed that the bootstrapped Kriging metamodeling is 24X faster than simple ANN metamodeling. The layout optimization for such a complex circuit can be performed effectively in a short time using this approach. The optimization flow could achieve significant reductions in the mean and standard deviation of the PLL characteristics. Thus, the proposed research is a major contribution to design for cost.
Supporting architecture evaluation for ATAM scenarios with LLMs
Paper ↗
Abstract
Architecture evaluation methods have long been used to evaluate software designs. Several evaluation methods have been proposed and used to analyze tradeoffs between different quality attributes. Having competing qualities leads to conflicts for selecting which quality-attribute scenarios are the most suitable ones that an architecture should tackle and for prioritizing the scenarios required by the stakeholders. In this context, architecture evaluation is carried out manually, often involving long brainstorming sessions to decide which are the most adequate quality scenarios. To reduce this effort and make the assessment and selection of scenarios more efficient, we suggest the usage of LLMs to partially automate evaluation activities. As a first step to validate this hypothesis, this work studies MS Copilot as an LLM tool to analyze quality scenarios suggested by students in a software architecture course and compares the students' results with the assessment provided by the LLM. Our initial study reveals that the LLM produces in most cases better and more accurate results regarding the risks, sensitivity points and tradeoff analysis of the quality scenarios. Overall, the use of generative AI has the potential to partially automate and support the architecture evaluation tasks, improving the human decision-making process.
CodeV-R1: Reasoning-Enhanced Verilog Generation
Paper ↗
Abstract
Large language models (LLMs) trained via reinforcement learning with verifiable reward (RLVR) have achieved breakthroughs on tasks with explicit, automatable verification, such as software programming and mathematical problems. Extending RLVR to electronic design automation (EDA), especially automatically generating hardware description languages (HDLs) like Verilog from natural-language (NL) specifications, however, poses three key challenges: the lack of automated and accurate verification environments, the scarcity of high-quality NL-code pairs, and the prohibitive computation cost of RLVR. To this end, we introduce CodeV-R1, an RLVR framework for training Verilog generation LLMs. First, we develop a rule-based testbench generator that performs robust equivalence checking against golden references. Second, we propose a round-trip data synthesis method that pairs open-source Verilog snippets with LLM-generated NL descriptions, verifies code-NL-code consistency via the generated testbench, and filters out inequivalent examples to yield a high-quality dataset. Third, we employ a two-stage "distill-then-RL" training pipeline: distillation for the cold start of reasoning abilities, followed by adaptive DAPO, our novel RLVR algorithm that can reduce training cost by adaptively adjusting sampling rate. The resulting model, CodeV-R1-7B, achieves 68.6% and 72.9% pass@1 on VerilogEval v2 and RTLLM v1.1, respectively, surpassing prior state-of-the-art by 12~20%, while matching or even exceeding the performance of 671B DeepSeek-R1. We will release our model, training pipeline, and dataset to facilitate research in EDA and LLM communities.
QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation
Paper ↗
Abstract
Large language models (LLMs) trained via reinforcement learning with verifiable reward (RLVR) have achieved breakthroughs on tasks with explicit, automatable verification, such as software programming and mathematical problems. Extending RLVR to electronic design automation (EDA), especially automatically generating hardware description languages (HDLs) like Verilog from natural-language (NL) specifications, however, poses three key challenges: the lack of automated and accurate verification environments, the scarcity of high-quality NL-code pairs, and the prohibitive computation cost of RLVR. To this end, we introduce CodeV-R1, an RLVR framework for training Verilog generation LLMs. First, we develop a rule-based testbench generator that performs robust equivalence checking against golden references. Second, we propose a round-trip data synthesis method that pairs open-source Verilog snippets with LLM-generated NL descriptions, verifies code-NL-code consistency via the generated testbench, and filters out inequivalent examples to yield a high-quality dataset. Third, we employ a two-stage "distill-then-RL" training pipeline: distillation for the cold start of reasoning abilities, followed by adaptive DAPO, our novel RLVR algorithm that can reduce training cost by adaptively adjusting sampling rate. The resulting model, CodeV-R1-7B, achieves 68.6% and 72.9% pass@1 on VerilogEval v2 and RTLLM v1.1, respectively, surpassing prior state-of-the-art by 12~20%, while even exceeding the performance of 671B DeepSeek-R1 on RTLLM. We have released our model, training code, and dataset to facilitate research in EDA and LLM communities.
Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning
Paper ↗
Abstract
Compiler auto-tuning optimizes pass sequences to improve performance metrics such as Intermediate Representation (IR) instruction count. Although recent advances leveraging Large Language Models (LLMs) have shown promise in automating compiler tuning, two significant challenges still remain: the absence of high-quality reasoning datasets for agents training, and limited effective interactions with the compilation environment. In this work, we introduce Compiler-R1, the first reinforcement learning (RL)-driven framework specifically augmenting LLM capabilities for compiler auto-tuning. Compiler-R1 features a curated, high-quality reasoning dataset and a novel two-stage end-to-end RL training pipeline, enabling efficient environment exploration and learning through an outcome-based reward. Extensive experiments across seven datasets demonstrate Compiler-R1 achieving an average 8.46% IR instruction count reduction compared to opt -Oz, showcasing the strong potential of RL-trained LLMs for compiler optimization. Our code and datasets are publicly available at https://github.com/Panhaolin2001/Compiler-R1.
LLM-based Property-based Test Generation for Guardrailing Cyber-Physical Systems
Paper ↗
Abstract
Cyber-physical systems (CPSs) are complex systems that integrate physical, computational, and communication subsystems. The heterogeneous nature of these systems makes their safety assurance challenging. In this paper, we propose a novel automated approach for guardrailing cyber-physical systems using property-based tests (PBTs) generated by Large Language Models (LLMs). Our approach employs an LLM to extract properties from the code and documentation of CPSs. Next, we use the LLM to generate PBTs that verify the extracted properties on the CPS. The generated PBTs have two uses. First, they are used to test the CPS before it is deployed, i.e., at design time. Secondly, these PBTs can be used after deployment, i.e., at run time, to monitor the behavior of the system and guardrail it against unsafe states. We implement our approach in ChekProp and conduct preliminary experiments to evaluate the generated PBTs in terms of their relevance (how well they match manually crafted properties), executability (how many run with minimal manual modification), and effectiveness (coverage of the input space partitions). The results of our experiments and evaluation demonstrate a promising path forward for creating guardrails for CPSs using LLM-generated property-based tests.
Synthesizing Performance Constraints for Evaluating and Improving Code Efficiency
Paper ↗
Abstract
Large Language Models (LLMs) have been increasingly used to optimize code efficiency. Evaluating their effectiveness and further suggesting optimization opportunities often rely on high-quality tests to demonstrate the performance bottlenecks presented in the program. However, existing approaches rely on a limited set of hand-curated inputs or LLM-generated uninteresting length-stressing tests, failing to reveal more nuanced optimization opportunities. We present WEDGE, a framework for generating performance-stressing input given the program under test. WEDGE synthesizes explicit performance-characterizing constraints in the form of branch conditions to partition the programs' execution space into performance-specific regions. When integrated with the coverage-guided fuzzer, reaching different regions introduces explicit rewards for test generation to explore inefficient implementations. Our evaluation shows that WEDGE introduces a significant slowdown compared to the tests in CodeContests and those claimed to be optimized by existing approaches. From the utility perspective, integrating our tests substantially improves the existing code optimization approaches that rely on test-driven execution feedback. We release PERFFORGE, the performance tests generated by WEDGE, to benchmark future approaches for efficient code generation at https://github.com/UChiSeclab/perfforge.
MemAscend: System Memory Optimization for SSD-Offloaded LLM Fine-Tuning
Paper ↗
Abstract
Owing to the huge success of generative artificial intelligence (AI), large language models (LLMs) have emerged as a core subclass, underpinning applications such as question answering, text generation, and code completion. While fine-tuning these models on domain-specific data can yield significant performance gains, it also poses daunting computational challenges, especially for researchers and small organizations with limited hardware resources. Although SSD offloading (i.e., ZeRO-Infinity) has emerged as a viable strategy to overcome the GPU memory barrier via leveraging both system memory (i.e., CPU DRAM) and storage space (i.e., solid-state devices, SSDs), its design primarily targets model-centric performance issues. As a result, key system-level issues, including system memory fragmentation, inefficient pinned buffer allocation, peak CPU usage spikes, and file system overhead, remain unaddressed, stifling scalability and inflating costs. Such an observation motivates this paper to introduce MemAscend, a framework that systematically tackles the underexplored system memory bottlenecks in SSD-offloaded LLM training, with a focus on resource-constrained environments. By streamlining pinned-memory allocation, eradicating fragmentation, and mitigating peak overhead, MemAscend reclaims a substantial system memory budget, enabling larger models, longer context windows, and higher batch sizes without exceeding modest hardware limits. Across diverse LLM benchmarks, MemAscend reduces peak system-memory consumption by an average of 55.7% compared with standard SSD offloading techniques, lowering the hardware barrier for fine-tuning and unlocking new possibilities for cost-effective large-scale training on limited-resource machines.
MemAscend: System Memory Optimization for SSD-Offloaded LLM Fine-Tuning
Paper ↗
Abstract
Owing to the huge success of generative artificial intelligence (AI), large language models (LLMs) have emerged as a core subclass, underpinning applications such as question answering, text generation, and code completion. While fine-tuning these models on domain-specific data can yield significant performance gains, it also poses daunting computational challenges, especially for researchers and small organizations with limited hardware resources. Although SSD offloading (i.e., ZeRO-Infinity) has emerged as a viable strategy to overcome the GPU memory barrier via leveraging both system memory (i.e., CPU DRAM) and storage space (i.e., solid-state devices, SSDs), its design primarily targets model-centric performance issues. As a result, key system-level issues, including system memory fragmentation, inefficient pinned buffer allocation, peak CPU usage spikes, and file system overhead, remain unaddressed, stifling scalability and inflating costs. Such an observation motivates this paper to introduce MemAscend, a framework that systematically tackles the underexplored system memory bottlenecks in SSD-offloaded LLM training, with a focus on resource-constrained environments. By streamlining pinned-memory allocation, eradicating fragmentation, and mitigating peak overhead, MemAscend reclaims a substantial system memory budget, enabling larger models, longer context windows, and higher batch sizes without exceeding modest hardware limits. Across diverse LLM benchmarks, MemAscend reduces peak system-memory consumption by an average of 55.7% compared with standard SSD offloading techniques, lowering the hardware barrier for fine-tuning and unlocking new possibilities for cost-effective large-scale training on limited-resource machines.
BugWhisperer: Fine-Tuning LLMs for SoC Hardware Vulnerability Detection
Paper ↗
Abstract
The current landscape of system-on-chips (SoCs) security verification faces challenges due to manual, labor-intensive, and inflexible methodologies. These issues limit the scalability and effectiveness of security protocols, making bug detection at the Register-Transfer Level (RTL) difficult. This paper proposes a new framework named BugWhisperer that utilizes a specialized, fine-tuned Large Language Model (LLM) to address these challenges. By enhancing the LLM's hardware security knowledge and leveraging its capabilities for text inference and knowledge transfer, this approach automates and improves the adaptability and reusability of the verification process. We introduce an open-source, fine-tuned LLM specifically designed for detecting security vulnerabilities in SoC designs. Our findings demonstrate that this tailored LLM effectively enhances the efficiency and flexibility of the security verification process. Additionally, we introduce a comprehensive hardware vulnerability database that supports this work and will further assist the research community in enhancing the security verification process.
CPINN-ABPI: Physics-Informed Neural Networks for Accurate Power Estimation in MPSoCs
Paper ↗
Abstract
Efficient thermal and power management in modern multiprocessor systems-on-chip (MPSoCs) demands accurate power consumption estimation. One of the state-of-the-art approaches, Alternative Blind Power Identification (ABPI), theoretically eliminates the dependence on steady-state temperatures, addressing a major shortcoming of previous approaches. However, ABPI performance has remained unverified in actual hardware implementations. In this study, we conduct the first empirical validation of ABPI on commercial hardware using the NVIDIA Jetson Xavier AGX platform. Our findings reveal that, while ABPI provides computational efficiency and independence from steady-state temperature, it exhibits considerable accuracy deficiencies in real-world scenarios. To overcome these limitations, we introduce a novel approach that integrates Custom Physics-Informed Neural Networks (CPINNs) with the underlying thermal model of ABPI. Our approach employs a specialized loss function that harmonizes physical principles with data-driven learning, complemented by multi-objective genetic algorithm optimization to balance estimation accuracy and computational cost. In experimental validation, CPINN-ABPI achieves a reduction of 84.7\% CPU and 73.9\% GPU in the mean absolute error (MAE) relative to ABPI, with the weighted mean absolute percentage error (WMAPE) improving from 47\%--81\% to $\sim$12\%. The method maintains real-time performance with 195.3~$\mu$s of inference time, with similar 85\%--99\% accuracy gains across heterogeneous SoCs.
DeepRTL2: A Versatile Model for RTL-Related Tasks
Paper ↗
Abstract
The integration of large language models (LLMs) into electronic design automation (EDA) has significantly advanced the field, offering transformative benefits, particularly in register transfer level (RTL) code generation and understanding. While previous studies have demonstrated the efficacy of fine-tuning LLMs for these generation-based tasks, embedding-based tasks, which are equally critical to EDA workflows, have been largely overlooked. These tasks, including natural language code search, RTL code functionality equivalence checking, and performance prediction, are essential for accelerating and optimizing the hardware design process. To address this gap, we present DeepRTL2, a family of versatile LLMs that unifies both generation- and embedding-based tasks related to RTL. By simultaneously tackling a broad range of tasks, DeepRTL2 represents the first model to provide a comprehensive solution to the diverse challenges in EDA. Through extensive experiments, we show that DeepRTL2 achieves state-of-the-art performance across all evaluated tasks.
iDSE: Navigating Design Space Exploration in High-Level Synthesis Using LLMs
Paper ↗
Abstract
High-Level Synthesis (HLS) serves as an agile hardware development tool that streamlines the circuit design by abstracting the register transfer level into behavioral descriptions, while allowing designers to customize the generated microarchitectures through optimization directives. However, the combinatorial explosion of possible directive configurations yields an intractable design space. Traditional design space exploration (DSE) methods, despite adopting heuristics or constructing predictive models to accelerate Pareto-optimal design acquisition, still suffer from prohibitive exploration costs and suboptimal results. Addressing these concerns, we introduce iDSE, the first LLM-aided DSE framework that leverages HLS design quality perception to effectively navigate the design space. iDSE intelligently pruns the design space to guide LLMs in calibrating representative initial sampling designs, expediting convergence toward the Pareto front. By exploiting the convergent and divergent thinking patterns inherent in LLMs for hardware optimization, iDSE achieves multi-path refinement of the design quality and diversity. Extensive experiments demonstrate that iDSE outperforms heuristic-based DSE methods by 5.1$\times$$\sim$16.6$\times$ in proximity to the reference Pareto front, matching NSGA-II with only 4.6% of the explored designs. Our work demonstrates the transformative potential of LLMs in scalable and efficient HLS design optimization, offering new insights into multiobjective optimization challenges.
Functional Matching of Logic Subgraphs: Beyond Structural Isomorphism
Paper ↗
Abstract
Subgraph matching in logic circuits is foundational for numerous Electronic Design Automation (EDA) applications, including datapath optimization, arithmetic verification, and hardware trojan detection. However, existing techniques rely primarily on structural graph isomorphism and thus fail to identify function-related subgraphs when synthesis transformations substantially alter circuit topology. To overcome this critical limitation, we introduce the concept of functional subgraph matching, a novel approach that identifies whether a given logic function is implicitly present within a larger circuit, irrespective of structural variations induced by synthesis or technology mapping. Specifically, we propose a two-stage multi-modal framework: (1) learning robust functional embeddings across AIG and post-mapping netlists for functional subgraph detection, and (2) identifying fuzzy boundaries using a graph segmentation approach. Evaluations on standard benchmarks (ITC99, OpenABCD, ForgeEDA) demonstrate significant performance improvements over existing structural methods, with average $93.8\%$ accuracy in functional subgraph detection and a dice score of $91.3\%$ in fuzzy boundary identification.
FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design
Paper ↗
Abstract
Designing analog circuits from performance specifications is a complex, multi-stage process encompassing topology selection, parameter inference, and layout feasibility. We introduce FALCON, a unified machine learning framework that enables fully automated, specification-driven analog circuit synthesis through topology selection and layout-constrained optimization. Given a target performance, FALCON first selects an appropriate circuit topology using a performance-driven classifier guided by human design heuristics. Next, it employs a custom, edge-centric graph neural network trained to map circuit topology and parameters to performance, enabling gradient-based parameter inference through the learned forward model. This inference is guided by a differentiable layout cost, derived from analytical equations capturing parasitic and frequency-dependent effects, and constrained by design rules. We train and evaluate FALCON on a large-scale custom dataset of 1M analog mm-wave circuits, generated and simulated using Cadence Spectre across 20 expert-designed topologies. Through this evaluation, FALCON demonstrates >99\% accuracy in topology inference, <10\% relative error in performance prediction, and efficient layout-aware design that completes in under 1 second per instance. Together, these results position FALCON as a practical and extensible foundation model for end-to-end analog circuit design automation.
SimuGen: Multi-modal Agentic Framework for Constructing Block Diagram-Based Simulation Models
Paper ↗
Abstract
Recent advances in large language models (LLMs) have shown impressive performance in mathematical reasoning and code generation. However, LLMs still struggle in the simulation domain, particularly in generating Simulink models, which are essential tools in engineering and scientific research. Our preliminary experiments indicate that LLM agents often fail to produce reliable and complete Simulink simulation code from text-only inputs, likely due to the lack of Simulink-specific data in their pretraining. To address this challenge, we propose SimuGen, a multimodal agent-based framework that automatically generates accurate Simulink simulation code by leveraging both the visual Simulink diagram and domain knowledge. SimuGen coordinates several specialized agents, including an investigator, unit test reviewer, code generator, executor, debug locator, and report writer, supported by a domain-specific knowledge base. This collaborative and modular design enables interpretable, robust, and reproducible Simulink simulation generation. Our source code is publicly available at https://github.com/renxinxing123/SimuGen_beta.
STRATUS: A Multi-agent System for Autonomous Reliability Engineering of Modern Clouds
Paper ↗
Abstract
In cloud-scale systems, failures are the norm. A distributed computing cluster exhibits hundreds of machine failures and thousands of disk failures; software bugs and misconfigurations are reported to be more frequent. The demand for autonomous, AI-driven reliability engineering continues to grow, as existing humanin-the-loop practices can hardly keep up with the scale of modern clouds. This paper presents STRATUS, an LLM-based multi-agent system for realizing autonomous Site Reliability Engineering (SRE) of cloud services. STRATUS consists of multiple specialized agents (e.g., for failure detection, diagnosis, mitigation), organized in a state machine to assist system-level safety reasoning and enforcement. We formalize a key safety specification of agentic SRE systems like STRATUS, termed Transactional No-Regression (TNR), which enables safe exploration and iteration. We show that TNR can effectively improve autonomous failure mitigation. STRATUS significantly outperforms state-of-the-art SRE agents in terms of success rate of failure mitigation problems in AIOpsLab and ITBench (two SRE benchmark suites), by at least 1.5 times across various models. STRATUS shows a promising path toward practical deployment of agentic systems for cloud reliability.
CXXCrafter: An LLM-Based Agent for Automated C/C++ Open Source Software Building
Paper ↗
Abstract
Project building is pivotal to support various program analysis tasks, such as generating intermediate rep- resentation code for static analysis and preparing binary code for vulnerability reproduction. However, automating the building process for C/C++ projects is a highly complex endeavor, involving tremendous technical challenges, such as intricate dependency management, diverse build systems, varied toolchains, and multifaceted error handling mechanisms. Consequently, building C/C++ projects often proves to be difficult in practice, hindering the progress of downstream applications. Unfortunately, research on facilitating the building of C/C++ projects remains to be inadequate. The emergence of Large Language Models (LLMs) offers promising solutions to automated software building. Trained on extensive corpora, LLMs can help unify diverse build systems through their comprehension capabilities and address complex errors by leveraging tacit knowledge storage. Moreover, LLM-based agents can be systematically designed to dynamically interact with the environment, effectively managing dynamic building issues. Motivated by these opportunities, we first conduct an empirical study to systematically analyze the current challenges in the C/C++ project building process. Particularly, we observe that most popular C/C++ projects encounter an average of five errors when relying solely on the default build systems. Based on our study, we develop an automated build system called CXXCrafter to specifically address the above-mentioned challenges, such as dependency resolution. Our evaluation on open-source software demonstrates that CXXCrafter achieves a success rate of 78% in project building. Specifically, among the Top100 dataset, 72 projects are built successfully by both CXXCrafter and manual efforts, 3 by CXXCrafter only, and 14 manually only. ...
Code Researcher: Deep Research Agent for Large Systems Code and Commit History
Paper ↗
Abstract
Large Language Model (LLM)-based coding agents have shown promising results on coding benchmarks, but their effectiveness on systems code remains underexplored. Due to the size and complexities of systems code, making changes to a systems codebase is a daunting task, even for humans. It requires researching about many pieces of context, derived from the large codebase and its massive commit history, before making changes. Inspired by the recent progress on deep research agents, we design the first deep research agent for code, called Code Researcher, and apply it to the problem of generating patches for mitigating crashes reported in systems code. Code Researcher performs multi-step reasoning about semantics, patterns, and commit history of code to gather sufficient context. The context is stored in a structured memory which is used for synthesizing a patch. We evaluate Code Researcher on kBenchSyz, a benchmark of Linux kernel crashes, and show that it significantly outperforms strong baselines, achieving a crash-resolution rate of 58%, compared to 37.5% by SWE-agent. On an average, Code Researcher explores 10 files in each trajectory whereas SWE-agent explores only 1.33 files, highlighting Code Researcher's ability to deeply explore the codebase. Through another experiment on an open-source multimedia software, we show the generalizability of Code Researcher. Our experiments highlight the importance of global context gathering and multi-faceted reasoning for large codebases.
ReChisel: Effective Automatic Chisel Code Generation by LLM with Reflection
Paper ↗
Abstract
Coding with hardware description languages (HDLs) such as Verilog is a time-intensive and laborious task. With the rapid advancement of large language models (LLMs), there is increasing interest in applying LLMs to assist with HDL coding. Recent efforts have demonstrated the potential of LLMs in translating natural language to traditional HDL Verilog. Chisel, a next-generation HDL based on Scala, introduces higher-level abstractions, facilitating more concise, maintainable, and scalable hardware designs. However, the potential of using LLMs for Chisel code generation remains largely unexplored. This work proposes ReChisel, an LLM-based agentic system designed to enhance the effectiveness of Chisel code generation. ReChisel incorporates a reflection mechanism to iteratively refine the quality of generated code using feedback from compilation and simulation processes, and introduces an escape mechanism to break free from non-progress loops. Experiments demonstrate that ReChisel significantly improves the success rate of Chisel code generation, achieving performance comparable to state-of-the-art LLM-based agentic systems for Verilog code generation.
LEGO-Compiler: Enhancing Neural Compilation Through Translation Composability
Paper ↗
Abstract
Large language models (LLMs) have the potential to revolutionize how we design and implement compilers and code translation tools. However, existing LLMs struggle to handle long and complex programs. We introduce LEGO-Compiler, a novel neural compilation system that leverages LLMs to translate high-level languages into assembly code. Our approach centers on three key innovations: LEGO translation, which decomposes the input program into manageable blocks; breaking down the complex compilation process into smaller, simpler verifiable steps by organizing it as a verifiable LLM workflow by external tests; and a feedback mechanism for self-correction. Supported by formal proofs of translation composability, LEGO-Compiler demonstrates high accuracy on multiple datasets, including over 99% on ExeBench and 97.9% on industrial-grade AnsiBench. Additionally, LEGO-Compiler has also acheived near one order-of-magnitude improvement on compilable code size scalability. This work opens new avenues for applying LLMs to system-level tasks, complementing traditional compiler technologies.
Autocomp: LLM-Driven Code Optimization for Tensor Accelerators
Paper ↗
Abstract
Hardware accelerators, especially those designed for tensor processing, have become ubiquitous in today's computing landscape. However, even with significant efforts in building compilers, programming these tensor accelerators remains challenging, leaving much of their potential underutilized. Recently, large language models (LLMs), trained on large amounts of code, have shown significant promise in code generation and optimization tasks, but generating low-resource languages like specialized tensor accelerator code still poses a significant challenge. We tackle this challenge with Autocomp, an approach that empowers accelerator programmers to leverage domain knowledge and hardware feedback to optimize code via an automated LLM-driven search. We accomplish this by: 1) formulating each optimization pass as a structured two-phase prompt, divided into planning and code generation phases, 2) inserting domain knowledge during planning via a concise and adaptable optimization menu, and 3) integrating correctness and performance metrics from hardware as feedback at each search iteration. Across three categories of representative workloads and two different accelerators, we demonstrate that Autocomp-optimized code runs 5.6x (GEMM) and 2.7x (convolution) faster than the vendor-provided library, and outperforms expert-level hand-tuned code by 1.4x (GEMM), 1.1x (convolution), and 1.3x (fine-grained linear algebra). Additionally, we demonstrate that optimization schedules generated from Autocomp can be reused across similar tensor operations, improving speedups by up to 24% under a fixed sample budget.
ALLSTaR: Automated LLM-Driven Scheduler Generation and Testing for Intent-Based RAN
Paper ↗
Abstract
The evolution toward open, programmable O-RAN and AI-RAN 6G networks creates unprecedented opportunities for Intent-Based Networking (IBN) to dynamically optimize RAN[...]. However, applying IBN effectively to the RAN scheduler [...] remains a significant challenge. Current approaches predominantly rely on coarse-grained network slicing, lacking the granularity for dynamic adaptation to individual user conditions and traffic patterns. Despite the existence of a vast body of scheduling algorithms [...], their practical utilization is hindered by implementation heterogeneity, insufficient systematic evaluation in production environments, and the complexity of developing high-performance scheduler implementations.[...] To address these limitations, we propose ALLSTaR (Automated LLm-driven Scheduler generation and Testing for intent-based RAN), a novel framework leveraging LLMs for automated, intent-driven scheduler design, implementation, and evaluation. ALLSTaR interprets NL intents, automatically generates functional scheduler code from the research literature using OCR and LLMs, and intelligently matches operator intents to the most suitable scheduler(s). Our implementation deploys these schedulers as O-RAN dApps, enabling on-the-fly deployment and testing on a production-grade, 5G-compliant testbed. This approach has enabled the largest-scale OTA experimental comparison of 18 scheduling algorithms automatically synthesized from the academic literature. The resulting performance profiles serve as the input for our Intent-Based Scheduling (IBS) framework, which dynamically selects and deploys appropriate schedulers that optimally satisfy operator intents. We validate our approach through multiple use cases unattainable with current slicing-based optimization techniques, demonstrating fine-grained control based on buffer status, physical layer conditions, and heterogeneous traffic types
Controlled Agentic Planning & Reasoning for Mechanism Synthesis
Paper ↗
Abstract
This work presents a dual-agent Large Language Model (LLM)-based reasoning method for mechanism synthesis, capable of reasoning at both linguistic and symbolic levels to generate geometrical and dynamic outcomes. The model consists of a composition of well-defined functions that, starting from a natural language specification, references abstract properties through supporting equations, generates and parametrizes simulation code, and elicits feedback anchor points using symbolic regression and distance functions. This process closes an actionable refinement loop at the linguistic and symbolic layers. The approach is shown to be both effective and convergent in the context of planar mechanisms. Additionally, we introduce MSynth, a novel benchmark for planar mechanism synthesis, and perform a comprehensive analysis of the impact of the model components. We further demonstrate that symbolic regression prompts unlock mechanistic insights only when applied to sufficiently large architectures.
CASS: Nvidia to AMD Transpilation with Data, Models, and Benchmark
Paper ↗
Abstract
We introduce CASS, the first large-scale dataset and model suite for cross-architecture GPU code transpilation, targeting both source-level (CUDA <--> HIP) and assembly-level (Nvidia SASS <--> AMD RDNA3) translation. The dataset comprises 70k verified code pairs across host and device, addressing a critical gap in low-level GPU code portability. Leveraging this resource, we train the CASS family of domain-specific language models, achieving 95% source translation accuracy and 37.5% assembly translation accuracy, substantially outperforming commercial baselines such as GPT-4o, Claude, and Hipify. Our generated code matches native performance in over 85% of test cases, preserving runtime and memory behavior. To support rigorous evaluation, we introduce CASS-Bench, a curated benchmark spanning 16 GPU domains with ground-truth execution. All data, models, and evaluation tools are released as open source to foster progress in GPU compiler tooling, binary compatibility, and LLM-guided hardware translation.
HDLxGraph: Bridging Large Language Models and HDL Repositories via HDL Graph Databases
Paper ↗
Abstract
Large Language Models (LLMs) have demonstrated their potential in hardware design tasks, such as Hardware Description Language (HDL) generation and debugging. Yet, their performance in real-world, repository-level HDL projects with thousands or even tens of thousands of code lines is hindered. To this end, we propose HDLxGraph, a novel framework that integrates Graph Retrieval Augmented Generation (Graph RAG) with LLMs, introducing HDL-specific graph representations by incorporating Abstract Syntax Trees (ASTs) and Data Flow Graphs (DFGs) to capture both code graph view and hardware graph view. HDLxGraph utilizes a dual-retrieval mechanism that not only mitigates the limited recall issues inherent in similarity-based semantic retrieval by incorporating structural information, but also enhances its extensibility to various real-world tasks by a task-specific retrieval finetuning. Additionally, to address the lack of comprehensive HDL search benchmarks, we introduce HDLSearch, a multi-granularity evaluation dataset derived from real-world repository-level projects. Experimental results demonstrate that HDLxGraph significantly improves average search accuracy, debugging efficiency and completion quality by 12.04%, 12.22% and 5.04% compared to similarity-based RAG, respectively. The code of HDLxGraph and collected HDLSearch benchmark are available at https://github.com/Nick-Zheng-Q/HDLxGraph.
Abstractions-of-Thought: Intermediate Representations for LLM Reasoning in Hardware Design
Paper ↗
Abstract
Large language models (LLMs) have achieved impressive proficiency on logic and programming tasks, often rivaling expert-level performance. However, generating functionally correct hardware description language (HDL) code from natural language specifications remains challenging, primarily in data-scarce domains. Therefore, we present Abstractions-of-Thought (AoT) - a training-free, inference-only prompting framework to mitigate misinterpretations and reasoning pitfalls of LLMs through a series of task-based abstractions within the prompting procedure, assisting in the transition from high-level to low-level representations of hardware. Furthermore, AoT consists of the following stages: (1) an LLM-based classification of hardware design patterns, (2) a structured intermediate representation (IR) to separate functional decomposition from code syntax, and (3) a line-by-line pseudocode solution enabling a more direct mapping to the final Verilog implementation. Experimental results on the VerilogEval benchmark depict that AoT demonstrates improvements in functionality when applied to large non-reasoning models (such as GPT-4o, outperforming all baseline techniques (including 1-shot, Chain-of-Thought, and Tree-of-Thought) while significantly reducing the generated tokens by 1.8-5.2x compared to popular Tree-of-Thought prompting.
JARVIS: A Multi-Agent Code Assistant for High-Quality EDA Script Generation
Paper ↗
Abstract
This paper presents JARVIS, a novel multi-agent framework that leverages Large Language Models (LLMs) and domain expertise to generate high-quality scripts for specialized Electronic Design Automation (EDA) tasks. By combining a domain-specific LLM trained with synthetically generated data, a custom compiler for structural verification, rule enforcement, code fixing capabilities, and advanced retrieval mechanisms, our approach achieves significant improvements over state-of-the-art domain-specific models. Our framework addresses the challenges of data scarcity and hallucination errors in LLMs, demonstrating the potential of LLMs in specialized engineering domains. We evaluate our framework on multiple benchmarks and show that it outperforms existing models in terms of accuracy and reliability. Our work sets a new precedent for the application of LLMs in EDA and paves the way for future innovations in this field.
JARVIS: A Multi-Agent Code Assistant for High-Quality EDA Script Generation
Paper ↗
Abstract
This paper presents JARVIS, a novel multi-agent framework that leverages Large Language Models (LLMs) and domain expertise to generate high-quality scripts for specialized Electronic Design Automation (EDA) tasks. By combining a domain-specific LLM trained with synthetically generated data, a custom compiler for structural verification, rule enforcement, code fixing capabilities, and advanced retrieval mechanisms, our approach achieves significant improvements over state-of-the-art domain-specific models. Our framework addresses the challenges of data scarcity and hallucination errors in LLMs, demonstrating the potential of LLMs in specialized engineering domains. We evaluate our framework on multiple benchmarks and show that it outperforms existing models in terms of accuracy and reliability. Our work sets a new precedent for the application of LLMs in EDA and paves the way for future innovations in this field.
Topology-aware Detection and Localization of Distributed Denial-of-Service Attacks in Network-on-Chips
Paper ↗
Abstract
Network-on-Chip (NoC) enables on-chip communication between diverse cores in modern System-on-Chip (SoC) designs. With its shared communication fabric, NoC has become a focal point for various security threats, especially in heterogeneous and high-performance computing platforms. Among these attacks, Distributed Denial of Service (DDoS) attacks occur when multiple malicious entities collaborate to overwhelm and disrupt access to critical system components, potentially causing severe performance degradation or complete disruption of services. These attacks are particularly challenging to detect due to their distributed nature and dynamic traffic patterns in NoC, which often evade static detection rules or simple profiling. This paper presents a framework to conduct topology-aware detection and localization of DDoS attacks using Graph Neural Networks (GNNs) by analyzing NoC traffic patterns. Specifically, by modeling the NoC as a graph, our method utilizes spatiotemporal traffic features to effectively identify and localize DDoS attacks. Unlike prior works that rely on handcrafted features or threshold-based detection, our GNN-based approach operates directly on raw inter-flit delay data, learning complex traffic dependencies without manual intervention. Experimental results demonstrate that our approach can detect and localize DDoS attacks with high accuracy (up to 99\%) while maintaining consistent performance under diverse attack strategies. Furthermore, the proposed method exhibits strong robustness across varying numbers and placements of malicious IPs, different packet injection rates, application workloads, and architectural configurations, including both 2D mesh and 3D TSV-based NoCs. Our work provides a scalable, flexible, and architecture-agnostic defense mechanism, significantly improving the availability and trustworthiness of on-chip communication in future SoC designs.
LLM-DSE: Searching Accelerator Parameters with LLM Agents
Paper ↗
Abstract
Even though high-level synthesis (HLS) tools mitigate the challenges of programming domain-specific accelerators (DSAs) by raising the abstraction level, optimizing hardware directive parameters remains a significant hurdle. Existing heuristic and learning-based methods struggle with adaptability and sample efficiency. We present LLM-DSE, a multi-agent framework designed specifically for optimizing HLS directives. Combining LLM with design space exploration (DSE), our explorer coordinates four agents: Router, Specialists, Arbitrator, and Critic. These multi-agent components interact with various tools to accelerate the optimization process. LLM-DSE leverages essential domain knowledge to identify efficient parameter combinations while maintaining adaptability through verbal learning from online interactions. Evaluations on the HLSyn dataset demonstrate that LLM-DSE achieves substantial $2.55\times$ performance gains over state-of-the-art methods, uncovering novel designs while reducing runtime. Ablation studies validate the effectiveness and necessity of the proposed agent interactions. Our code is open-sourced here: https://github.com/Nozidoali/LLM-DSE.
MARVEL: Multi-Agent RTL Vulnerability Extraction using Large Language Models
Paper ↗
Abstract
Hardware security verification is a challenging and time-consuming task. For this purpose, design engineers may utilize tools such as formal verification, linters, and functional simulation tests, coupled with analysis and a deep understanding of the hardware design being inspected. Large Language Models (LLMs) have been used to assist during this task, either directly or in conjunction with existing tools. We improve the state of the art by proposing MARVEL, a multi-agent LLM framework for a unified approach to decision-making, tool use, and reasoning. MARVEL mimics the cognitive process of a designer looking for security vulnerabilities in RTL code. It consists of a supervisor agent that devises the security policy of the system-on-chips (SoCs) using its security documentation. It delegates tasks to validate the security policy to individual executor agents. Each executor agent carries out its assigned task using a particular strategy. Each executor agent may use one or more tools to identify potential security bugs in the design and send the results back to the supervisor agent for further analysis and confirmation. MARVEL includes executor agents that leverage formal tools, linters, simulation tests, LLM-based detection schemes, and static analysis-based checks. We test our approach on a known buggy SoC based on OpenTitan from the Hack@DATE competition. We find that 20 of the 48 issues reported by MARVEL pose security vulnerabilities.
VeriReason: Reinforcement Learning with Testbench Feedback for Reasoning-Enhanced Verilog Generation
Paper ↗
Abstract
Automating Register Transfer Level (RTL) code generation using Large Language Models (LLMs) offers substantial promise for streamlining digital circuit design and reducing human effort. However, current LLM-based approaches face significant challenges with training data scarcity, poor specification-code alignment, lack of verification mechanisms, and balancing generalization with specialization. Inspired by DeepSeek-R1, we introduce VeriReason, a framework integrating supervised fine-tuning with Guided Reward Proximal Optimization (GRPO) reinforcement learning for RTL generation. Using curated training examples and a feedback-driven reward model, VeriReason combines testbench evaluations with structural heuristics while embedding self-checking capabilities for autonomous error correction. On the VerilogEval Benchmark, VeriReason delivers significant improvements: achieving 83.1% functional correctness on the VerilogEval Machine benchmark, substantially outperforming both comparable-sized models and much larger commercial systems like GPT-4 Turbo. Additionally, our approach demonstrates up to a 2.8X increase in first-attempt functional correctness compared to baseline methods and exhibits robust generalization to unseen designs. To our knowledge, VeriReason represents the first system to successfully integrate explicit reasoning capabilities with reinforcement learning for Verilog generation, establishing a new state-of-the-art for automated RTL synthesis. The models and datasets are available at: https://huggingface.co/collections/AI4EDA-CASE Code is Available at: https://github.com/NellyW8/VeriReason
GLOVA: Global and Local Variation-Aware Analog Circuit Design with Risk-Sensitive Reinforcement Learning
Paper ↗
Abstract
Analog/mixed-signal circuit design encounters significant challenges due to performance degradation from process, voltage, and temperature (PVT) variations. To achieve commercial-grade reliability, iterative manual design revisions and extensive statistical simulations are required. While several studies have aimed to automate variation aware analog design to reduce time-to-market, the substantial mismatches in real-world wafers have not been thoroughly addressed. In this paper, we present GLOVA, an analog circuit sizing framework that effectively manages the impact of diverse random mismatches to improve robustness against PVT variations. In the proposed approach, risk-sensitive reinforcement learning is leveraged to account for the reliability bound affected by PVT variations, and ensemble-based critic is introduced to achieve sample-efficient learning. For design verification, we also propose $\mu$-$\sigma$ evaluation and simulation reordering method to reduce simulation costs of identifying failed designs. GLOVA supports verification through industrial-level PVT variation evaluation methods, including corner simulation as well as global and local Monte Carlo (MC) simulations. Compared to previous state-of-the-art variation-aware analog sizing frameworks, GLOVA achieves up to 80.5$\times$ improvement in sample efficiency and 76.0$\times$ reduction in time.
Customizing a Large Language Model for VHDL Design of High-Performance Microprocessors
Paper ↗
Abstract
The use of Large Language Models (LLMs) in hardware design has taken off in recent years, principally through its incorporation in tools that increase chip designer productivity. There has been considerable discussion about the use of LLMs in RTL specifications of chip designs, for which the two most popular languages are Verilog and VHDL. LLMs and their use in Verilog design has received significant attention due to the higher popularity of the language, but little attention so far has been given to VHDL despite its continued popularity in the industry. There has also been little discussion about the unique needs of organizations that engage in high-performance processor design, and techniques to deploy AI solutions in these settings. In this paper, we describe our journey in developing a Large Language Model (LLM) specifically for the purpose of explaining VHDL code, a task that has particular importance in an organization with decades of experience and assets in high-performance processor design. We show how we developed test sets specific to our needs and used them for evaluating models as we performed extended pretraining (EPT) of a base LLM. Expert evaluation of the code explanations produced by the EPT model increased to 69% compared to a base model rating of 43%. We further show how we developed an LLM-as-a-judge to gauge models similar to expert evaluators. This led us to deriving and evaluating a host of new models, including an instruction-tuned version of the EPT model with an expected expert evaluator rating of 71%. Our experiments also indicate that with the potential use of newer base models, this rating can be pushed to 85% and beyond. We conclude with a discussion on further improving the quality of hardware design LLMs using exciting new developments in the Generative AI world.
Enhanced Photonic Chip Design via Interpretable Machine Learning Techniques
Paper ↗
Abstract
Photonic chip design has seen significant advancements with the adoption of inverse design methodologies, offering flexibility and efficiency in optimizing device performance. However, the black-box nature of the optimization approaches, such as those used in inverse design in order to minimize a loss function or maximize coupling efficiency, poses challenges in understanding the outputs. This challenge is prevalent in machine learning-based optimization methods, which can suffer from the same lack of transparency. To this end, interpretability techniques address the opacity of optimization models. In this work, we apply interpretability techniques from machine learning, with the aim of gaining understanding of inverse design optimization used in designing photonic components, specifically two-mode multiplexers. We base our methodology on the widespread interpretability technique known as local interpretable model-agnostic explanations, or LIME. As a result, LIME-informed insights point us to more effective initial conditions, directly improving device performance. This demonstrates that interpretability methods can do more than explain models -- they can actively guide and enhance the inverse-designed photonic components. Our results demonstrate the ability of interpretable techniques to reveal underlying patterns in the inverse design process, leading to the development of better-performing components.
Emerging ML-AI Techniques for Analog and RF EDA
Paper ↗
Abstract
This survey explores the integration of machine learning (ML) into EDA workflows for analog and RF circuits, addressing challenges unique to analog design, which include complex constraints, nonlinear design spaces, and high computational costs. State-of-the-art learning and optimization techniques are reviewed for circuit tasks such as constraint formulation, topology generation, device modeling, sizing, placement, and routing. The survey highlights the capability of ML to enhance automation, improve design quality, and reduce time-to-market while meeting the target specifications of an analog or RF circuit. Emerging trends and cross-cutting challenges, including robustness to variations and considerations of interconnect parasitics, are also discussed.
Spec2Assertion: Automatic Pre-RTL Assertion Generation using Large Language Models with Progressive Regularization
Paper ↗
Abstract
SystemVerilog Assertions (SVAs) play a critical role in detecting and debugging functional bugs in digital chip design. However, generating SVAs has traditionally been a manual, labor-intensive, and error-prone process. Recent advances in automatic assertion generation, particularly those using machine learning and large language models (LLMs), have shown promising potential, though most approaches remain in the early stages of development. In this work, we introduce Spec2Assertion, a new technique for automatically generating assertions from design specifications prior to RTL implementation. It leverages LLMs with progressive regularization and incorporates Chain-of-Thought (CoT) prompting to guide assertion synthesis. Additionally, we propose a new evaluation methodology that assesses assertion quality across a broad range of scenarios. Experiments on multiple benchmark designs show that Spec2Assertion generates 70% more syntax-correct assertions with 2X quality improvement on average compared to a recent state-of-the-art approach.
RTL++: Graph-enhanced LLM for RTL Code Generation
Paper ↗
Abstract
As hardware design complexity escalates, there is an urgent need for advanced automation in electronic design automation (EDA). Traditional register transfer level (RTL) design methods are manual, time-consuming, and prone to errors. While commercial (instruction-tuned) large language models (LLMs) shows promising performance for automation, they pose security and privacy concerns. Open-source models offer alternatives; however, they frequently fall short in quality/correctness, largely due to limited, high-quality RTL code data essential for effective training and generalization. This paper proposes RTL++, a first-of-its-kind LLM-assisted method for RTL code generation that utilizes graph representations of code structures to enhance the quality of generated code. By encoding RTL code into a textualized control flowgraphs (CFG) and data flow graphs (DFG), RTL++ captures the inherent hierarchy, dependencies, and relationships within the code. This structured graph-based approach enhances the context available to LLMs, enabling them to better understand and generate instructions. By focusing on data generation through graph representations, RTL++ addresses the limitations of previous approaches that rely solely on code and suffer from lack of diversity. Experimental results demonstrate that RTL++ outperforms state-of-the-art models fine-tuned for RTL generation, as evaluated using the VerilogEval benchmark's Pass@1/5/10 metric, as well as the RTLLM1.1 model, which highlight the effectiveness of graph-enhanced context in advancing the capabilities of LLM-assisted RTL code generation.
LATENT: LLM-Augmented Trojan Insertion and Evaluation Framework for Analog Netlist Topologies
Paper ↗
Abstract
Analog and mixed-signal (A/MS) integrated circuits (ICs) are integral to safety-critical applications. However, the globalization and outsourcing of A/MS ICs to untrusted third-party foundries expose them to security threats, particularly analog Trojans. Unlike digital Trojans which have been extensively studied, analog Trojans remain largely unexplored. There has been only limited research on their diversity and stealth in analog designs, where a Trojan is activated only during a narrow input voltage range. Effective defense techniques require a clear understanding of the attack vectors; however, the lack of diverse analog Trojan instances limits robust advances in detection strategies. To address this gap, we present LATENT, the first large language model (LLM)-driven framework for crafting stealthy, circuit-specific analog Trojans. LATENT incorporates LLM as an autonomous agent to intelligently insert and refine Trojan components within analog designs based on iterative feedback from a detection model. This feedback loop ensures that the inserted Trojans remain stealthy while successfully evading detection. Experimental results demonstrate that our generated Trojan designs exhibit an average Trojan-activation range of 15.74%, ensuring they remain inactive under most operating voltages, while causing a significant performance degradation of 11.3% upon activation.
Quantum State Preparation via Large-Language-Model-Driven Evolution
Paper ↗
Abstract
We propose an automated framework for quantum circuit design by integrating large-language models (LLMs) with evolutionary optimization to overcome the rigidity, scalability limitations, and expert dependence of traditional ones in variational quantum algorithms. Our approach (FunSearch) autonomously discovers hardware-efficient ans\"atze with new features of scalability and system-size-independent number of variational parameters entirely from scratch. Demonstrations on the Ising and XY spin chains with n = 9 qubits yield circuits containing 4 parameters, achieving near-exact energy extrapolation across system sizes. Implementations on quantum hardware (Zuchongzhi chip) validate practicality, where two-qubit quantum gate noises can be effectively mitigated via zero-noise extrapolations for a spin chain system as large as 20 sites. This framework bridges algorithmic design and experimental constraints, complementing contemporary quantum architecture search frameworks to advance scalable quantum simulations.
Quantum State Preparation via Large-Language-Model-Driven Evolution
Paper ↗
Abstract
We propose an automated framework for quantum circuit design by integrating large-language models (LLMs) with evolutionary optimization to overcome the rigidity, scalability limitations, and expert dependence of traditional ones in variational quantum algorithms. Our approach (FunSearch) autonomously discovers hardware-efficient ans\"atze with new features of scalability and system-size-independent number of variational parameters entirely from scratch. Demonstrations on the Ising and XY spin chains with n = 9 qubits yield circuits containing 4 parameters, achieving near-exact energy extrapolation across system sizes. Implementations on quantum hardware (Zuchongzhi chip) validate practicality, where two-qubit quantum gate noises can be effectively mitigated via zero-noise extrapolations for a spin chain system as large as 20 sites. This framework bridges algorithmic design and experimental constraints, complementing contemporary quantum architecture search frameworks to advance scalable quantum simulations.
Free and Fair Hardware: A Pathway to Copyright Infringement-Free Verilog Generation using LLMs
Paper ↗
Abstract
Limitations in Large Language Model (LLM) capabilities for hardware design tasks, such as generating functional Verilog codes, have motivated various fine-tuning optimizations utilizing curated hardware datasets from open-source repositories. However, these datasets remain limited in size and contain minimal checks on licensing for reuse, resulting in potential copyright violations by fine-tuned LLMs. Therefore, we propose an evaluation benchmark to estimate the risk of Verilog-trained LLMs to generate copyright-protected codes. To minimize this risk, we present an open-source Verilog dataset, FreeSet, containing over 220k files, along with the automated dataset curation framework utilized to provide additional guarantees of fair-use Verilog data. We then execute an LLM fine-tuning framework consisting of continual pre-training, resulting in a fine-tuned Llama model for Verilog, FreeV. Our results indicate that FreeV demonstrates the smallest risk of copyright-infringement among prior works, with only a 3% violation rate. Furthermore, experimental results demonstrate improvements in Verilog generation functionality over its baseline model, improving VerilogEval pass@10 rates by over 10%.
Veritas: Deterministic Verilog Code Synthesis from LLM-Generated Conjunctive Normal Form
Paper ↗
Abstract
Automated Verilog code synthesis poses significant challenges and typically demands expert oversight. Traditional high-level synthesis (HLS) methods often fail to scale for real-world designs. While large language models (LLMs) have enhanced scalability, they often introduce syntactical and logical errors requiring extensive post-generation verification. Here, we introduce a novel conjunctive normal form (CNF)-guided synthesis methodology. The idea is to have an LLM generate CNF clauses, a format widely used for formal verification and synthesis validation in hardware design, but here it is used to formally describe the desired circuit functionality. These CNF specifications are then deterministically converted into Verilog, ensuring correctness by construction. Our approach fine-tunes an open-source and lightweight LLM, namely the CPU-deployable LLama-3.2-3B-Instruct model (parameters < 4B), on a dataset of standard RTL components. Experimental results demonstrate that our approach reliably produces functionally correct Verilog code on the first attempt, compared to other lightweight open-source SoTA works such as Verigen (2B parameters) and RTLCoder (4-bit quantized with around 7B parameters). We will release our method and data in full post peer-review.
Can Large Language Models Predict Parallel Code Performance?
Paper ↗
Abstract
Accurate determination of the performance of parallel GPU code typically requires execution-time profiling on target hardware -- an increasingly prohibitive step due to limited access to high-end GPUs. This paper explores whether Large Language Models (LLMs) can offer an alternative approach for GPU performance prediction without relying on hardware. We frame the problem as a roofline classification task: given the source code of a GPU kernel and the hardware specifications of a target GPU, can an LLM predict whether the GPU kernel is compute-bound or bandwidth-bound? For this study, we build a balanced dataset of 340 GPU kernels, obtained from HeCBench benchmark and written in CUDA and OpenMP, along with their ground-truth labels obtained via empirical GPU profiling. We evaluate LLMs across four scenarios: (1) with access to profiling data of the kernel source, (2) zero-shot with source code only, (3) few-shot with code and label pairs, and (4) fine-tuned on a small custom dataset. Our results show that state-of-the-art LLMs have a strong understanding of the Roofline model, achieving 100% classification accuracy when provided with explicit profiling data. We also find that reasoning-capable LLMs significantly outperform standard LLMs in zero- and few-shot settings, achieving up to 64% accuracy on GPU source codes, without profiling information. Lastly, we find that LLM fine-tuning will require much more data than what we currently have available. This work is among the first to use LLMs for source-level roofline performance prediction via classification, and illustrates their potential to guide optimization efforts when runtime profiling is infeasible. Our findings suggest that with better datasets and prompt strategies, LLMs could become practical tools for HPC performance analysis and performance portability.
Leveraging LLMs to Automate Energy-Aware Refactoring of Parallel Scientific Codes
Paper ↗
Abstract
While large language models (LLMs) are increasingly used for generating parallel scientific code, most current efforts emphasize functional correctness, often overlooking performance and energy considerations. In this work, we propose LASSI-EE, an automated LLM-based refactoring framework that generates energy-efficient parallel code on a target parallel system for a given parallel code as input. Through a multi-stage, iterative pipeline process, LASSI-EE achieved an average energy reduction of 47% across 85% of the 20 HeCBench benchmarks tested on NVIDIA A100 GPUs. Our findings demonstrate the broader potential of LLMs, not only for generating correct code but also for enabling energy-aware programming. We also address key insights and limitations within the framework, offering valuable guidance for future improvements.
CircuitFusion: Multimodal Circuit Representation Learning for Agile Chip Design
Paper ↗
Abstract
The rapid advancements of AI rely on the support of ICs. However, the growing complexity of digital ICs makes the traditional IC design process costly and time-consuming. In recent years, AI-assisted IC design methods have demonstrated great potential, but most methods are task-specific or focus solely on the circuit structure in graph format, overlooking other circuit modalities with rich functional information. In this paper, we introduce CircuitFusion, the first multimodal and implementation-aware circuit encoder. It encodes circuits into general representations that support different downstream circuit design tasks. To learn from circuits, we propose to fuse three circuit modalities: hardware code, structural graph, and functionality summary. More importantly, we identify four unique properties of circuits: parallel execution, functional equivalent transformation, multiple design stages, and circuit reusability. Based on these properties, we propose new strategies for both the development and application of CircuitFusion: 1) During circuit preprocessing, utilizing the parallel nature of circuits, we split each circuit into multiple sub-circuits based on sequential-element boundaries, each sub-circuit in three modalities. 2) During CircuitFusion pre-training, we introduce three self-supervised tasks that utilize equivalent transformations both within and across modalities. 3) When applying CircuitFusion to downstream tasks, we propose a new retrieval-augmented inference method, which retrieves similar known circuits as a reference for predictions. It improves fine-tuning performance and even enables zero-shot inference. Evaluated on five different circuit design tasks, CircuitFusion consistently outperforms the SOTA supervised method specifically developed for every single task, demonstrating its generalizability and ability to learn circuits' inherent properties.
QiMeng-Xpiler: Transcompiling Tensor Programs for Deep Learning Systems with a Neural-Symbolic Approach
Paper ↗
Abstract
Heterogeneous deep learning systems (DLS) such as GPUs and ASICs have been widely deployed in industrial data centers, which requires to develop multiple low-level tensor programs for different platforms. An attractive solution to relieve the programming burden is to transcompile the legacy code of one platform to others. However, current transcompilation techniques struggle with either tremendous manual efforts or functional incorrectness, rendering "Write Once, Run Anywhere" of tensor programs an open question. We propose a novel transcompiler, i.e., QiMeng-Xpiler, for automatically translating tensor programs across DLS via both large language models (LLMs) and symbolic program synthesis, i.e., neural-symbolic synthesis. The key insight is leveraging the powerful code generation ability of LLM to make costly search-based symbolic synthesis computationally tractable. Concretely, we propose multiple LLM-assisted compilation passes via pre-defined meta-prompts for program transformation. During each program transformation, efficient symbolic program synthesis is employed to repair incorrect code snippets with a limited scale. To attain high performance, we propose a hierarchical auto-tuning approach to systematically explore both the parameters and sequences of transformation passes. Experiments on 4 DLS with distinct programming interfaces, i.e., Intel DL Boost with VNNI, NVIDIA GPU with CUDA, AMD MI with HIP, and Cambricon MLU with BANG, demonstrate that QiMeng-Xpiler correctly translates different tensor programs at the accuracy of 95% on average, and the performance of translated programs achieves up to 2.0x over vendor-provided manually-optimized libraries. As a result, the programming productivity of DLS is improved by up to 96.0x via transcompiling legacy tensor programs.
Deep Representation Learning for Electronic Design Automation
Paper ↗
Abstract
Representation learning has become an effective technique utilized by electronic design automation (EDA) algorithms, which leverage the natural representation of workflow elements as images, grids, and graphs. By addressing challenges related to the increasing complexity of circuits and stringent power, performance, and area (PPA) requirements, representation learning facilitates the automatic extraction of meaningful features from complex data formats, including images, grids, and graphs. This paper examines the application of representation learning in EDA, covering foundational concepts and analyzing prior work and case studies on tasks that include timing prediction, routability analysis, and automated placement. Key techniques, including image-based methods, graph-based approaches, and hybrid multimodal solutions, are presented to illustrate the improvements provided in routing, timing, and parasitic prediction. The provided advancements demonstrate the potential of representation learning to enhance efficiency, accuracy, and scalability in current integrated circuit design flows.
ForgeEDA: A Comprehensive Multimodal Dataset for Advancing EDA
Paper ↗
Abstract
We introduce ForgeEDA, an open-source comprehensive circuit dataset across various categories. ForgeEDA includes diverse circuit representations such as Register Transfer Level (RTL) code, Post-mapping (PM) netlists, And-Inverter Graphs (AIGs), and placed netlists, enabling comprehensive analysis and development. We demonstrate ForgeEDA's utility by benchmarking state-of-the-art EDA algorithms on critical tasks such as Power, Performance, and Area (PPA) optimization, highlighting its ability to expose performance gaps and drive advancements. Additionally, ForgeEDA's scale and diversity facilitate the training of AI models for EDA tasks, demonstrating its potential to improve model performance and generalization. By addressing limitations in existing datasets, ForgeEDA aims to catalyze breakthroughs in modern IC design and support the next generation of innovations in EDA.
Artificial Intelligence implementation of onboard flexible payload and adaptive beamforming using commercial off-the-shelf devices
Paper ↗
Abstract
Very High Throughput satellites typically provide multibeam coverage, however, a common problem is that there can be a mismatch between the capacity of each beam and the traffic demand: some beams may fall short, while others exceed the requirements. This challenge can be addressed by integrating machine learning with flexible payload and adaptive beamforming techniques. These methods allow for dynamic allocation of payload resources based on real-time capacity needs. As artificial intelligence advances, its ability to automate tasks, enhance efficiency, and increase precision is proving invaluable, especially in satellite communications, where traditional optimization methods are often computationally intensive. AI-driven solutions offer faster, more effective ways to handle complex satellite communication tasks. Artificial intelligence in space has more constraints than other fields, considering the radiation effects, the spaceship power capabilities, mass, and area. Current onboard processing uses legacy space-certified general-purpose processors, costly application-specific integrated circuits, or field-programmable gate arrays subjected to a highly stringent certification process. The increased performance demands of onboard processors to satisfy the accelerated data rates and autonomy requirements have rendered current space-graded processors obsolete. This work is focused on transforming the satellite payload using artificial intelligence and machine learning methodologies over available commercial off-the-shelf chips for onboard processing. The objectives include validating artificial intelligence-driven scenarios, focusing on flexible payload and adaptive beamforming as machine learning models onboard. Results show that machine learning models significantly improve signal quality, spectral efficiency, and throughput compared to conventional payload.
OneDSE: A Unified Microprocessor Metric Prediction and Design Space Exploration Framework
Paper ↗
Abstract
With the diminishing returns of Moore Law scaling and as power constraints become more impactful, processor designs rely on architectural innovation to achieve differentiating performance. Innovation complexity has increased the design space of modern high-performance processors. This work offers an efficient and novel design space exploration (DSE) solution to these challenges of modern CPU design. We identify three key challenges in past DSE approaches: (a) Metric prediction is slow and inaccurate for unseen workloads, microarchitectures, (b) Search is slow and inaccurate in CPU parameter space, and (c) A Single model is unable to learn the huge design space. We present OneDSE, a unified metric predictor and CPU parameter explorer to mitigate these challenges with three key techniques: (a) Transformer-based workload-Aware CPU DSE (TrACE) predictor that outperforms state-of-the-art ANN-based prediction methods by 2.75x and 6.12x with and without fine-tuning, respectively, on several benchmarks; (b) a novel metric space search approach that outperforms optimized metaheuristics by 1.19x while reducing search time by an order of magnitude; (c) MARL-based multi-agent framework that achieves a 10.6% reduction in prediction error compared to its non-MARL counterpart, enabling more accurate and efficient exploration of the CPU design space.
OneDSE: A Unified Microprocessor Metric Prediction and Design Space Exploration Framework
Paper ↗
Abstract
With the slowing of Moores Law and increasing impact of power constraints, processor designs rely on architectural innovation to achieve differentiating performance. However, the innovation complexity has simultaneously increased the design space of modern high performance processors. Specifically, we identify two key challenges in prior Design Space Exploration (DSE) approaches for modern CPU design - (a) cost model (prediction method) is either slow or microarchitecture-specific or workload-specific and single model is inefficient to learn the whole design space (b) optimization (exploration method) is slow and inaccurate in the large CPU parameter space. This work presents a novel solution called OneDSE to address these emerging challenges in modern CPU design. OneDSE is a unified cost model (metric predictor) and optimizer (CPU parameter explorer) with three key techniques - 1. Transformer-based workload-Aware CPU Estimation (TrACE) framework to predict metrics in the parameter space (TrACE-p) and parameters in the in the metric space (TrACE-m). TrACE-p outperforms State of The Art (SOTA) IPC prediction methods by 5.71x and 28x for single and multiple workloads respectively while being two orders of magnitude faster. 2. We also propose a novel Metric spAce Search opTimizer (MAST) that leverages TrACE-m and outperforms SoTA metaheuristics by 1.19x while being an order of magnitude faster. 3. We propose Subsystem-based Multi-Agent Reinforcement-learning based fine-Tuning (SMART)-TrACE that achieves a 10.6% reduction in prediction error compared to TrACE, enabling more accurate and efficient exploration of the CPU design space.
ComplexVCoder: An LLM-Driven Framework for Systematic Generation of Complex Verilog Code
Paper ↗
Abstract
Recent advances have demonstrated the promising capabilities of large language models (LLMs) in generating register-transfer level (RTL) code, such as Verilog. However, existing LLM-based frameworks still face significant challenges in accurately handling the complexity of real-world RTL designs, particularly those that are large-scale and involve multi-level module instantiations. To address this issue, we present ComplexVCoder, an open-source LLM-driven framework that enhances both the generation quality and efficiency of complex Verilog code. Specifically, we introduce a two-stage generation mechanism, which leverages an intermediate representation to enable a more accurate and structured transition from natural language descriptions to intricate Verilog designs. In addition, we introduce a rule-based alignment method and a domain-specific retrieval-augmented generation (RAG) to further improve the correctness of the synthesized code by incorporating relevant design knowledge during generation. To evaluate our approach, we construct a comprehensive dataset comprising 55 complex Verilog designs derived from real-world implementations. We also release an open-source benchmark suite for systematically assessing the quality of auto-generated RTL code together with the ComplexVCoder framework. Experimental results show that ComplexVCoder outperforms SOTA frameworks such as CodeV and RTLCoder by 14.6% and 22.2%, respectively, in terms of function correctness on complex Verilog benchmarks. Furthermore, ComplexVcoder achieves comparable generation performances in terms of functionality correctness using a lightweight 32B model (Qwen2.5), rivaling larger-scale models such as GPT-3.5 and DeepSeek-V3.
ComplexVCoder: An LLM-Driven Framework for Systematic Generation of Complex Verilog Code
Paper ↗
Abstract
Recent advances have demonstrated the promising capabilities of large language models (LLMs) in generating register-transfer level (RTL) code, such as Verilog. However, existing LLM-based frameworks still face significant challenges in accurately handling the complexity of real-world RTL designs, particularly those that are large-scale and involve multi-level module instantiations. To address this issue, we present ComplexVCoder, an open-source LLM-driven framework that enhances both the generation quality and efficiency of complex Verilog code. Specifically, we introduce a two-stage generation mechanism, which leverages an intermediate representation to enable a more accurate and structured transition from natural language descriptions to intricate Verilog designs. In addition, we introduce a rule-based alignment method and a domain-specific retrieval-augmented generation (RAG) to further improve the correctness of the synthesized code by incorporating relevant design knowledge during generation. To evaluate our approach, we construct a comprehensive dataset comprising 55 complex Verilog designs derived from real-world implementations. We also release an open-source benchmark suite for systematically assessing the quality of auto-generated RTL code together with the ComplexVCoder framework. Experimental results show that ComplexVCoder outperforms SOTA frameworks such as CodeV and RTLCoder by 14.6% and 22.2%, respectively, in terms of function correctness on complex Verilog benchmarks. Furthermore, ComplexVcoder achieves comparable generation performances in terms of functionality correctness using a lightweight 32B model (Qwen2.5), rivaling larger-scale models such as GPT-3.5 and DeepSeek-V3.
ComplexVCoder: An LLM-Driven Framework for Systematic Generation of Complex Verilog Code
Paper ↗
Abstract
Recent advances have demonstrated the promising capabilities of large language models (LLMs) in generating register-transfer level (RTL) code, such as Verilog. However, existing LLM-based frameworks still face significant challenges in accurately handling the complexity of real-world RTL designs, particularly those that are large-scale and involve multi-level module instantiations. To address this issue, we present ComplexVCoder, an open-source LLM-driven framework that enhances both the generation quality and efficiency of complex Verilog code. Specifically, we introduce a two-stage generation mechanism, which leverages an intermediate representation to enable a more accurate and structured transition from natural language descriptions to intricate Verilog designs. In addition, we introduce a rule-based alignment method and a domain-specific retrieval-augmented generation (RAG) to further improve the correctness of the synthesized code by incorporating relevant design knowledge during generation. To evaluate our approach, we construct a comprehensive dataset comprising 55 complex Verilog designs derived from real-world implementations. We also release an open-source benchmark suite for systematically assessing the quality of auto-generated RTL code together with the ComplexVCoder framework. Experimental results show that ComplexVCoder outperforms SOTA frameworks such as CodeV and RTLCoder by 14.6% and 22.2%, respectively, in terms of function correctness on complex Verilog benchmarks. Furthermore, ComplexVcoder achieves comparable generation performances in terms of functionality correctness using a lightweight 32B model (Qwen2.5), rivaling larger-scale models such as GPT-3.5 and DeepSeek-V3.
From Concept to Practice: an Automated LLM-aided UVM Machine for RTL Verification
Paper ↗
Abstract
Verification presents a major bottleneck in Integrated Circuit (IC) development, consuming nearly 70% of the total development effort. While the Universal Verification Methodology (UVM) is widely used in industry to improve verification efficiency through structured and reusable testbenches, constructing these testbenches and generating sufficient stimuli remain challenging. These challenges arise from the considerable manual coding effort required, repetitive manual execution of multiple EDA tools, and the need for in-depth domain expertise to navigate complex designs.Here, we present UVM^2, an automated verification framework that leverages Large Language Models (LLMs) to generate UVM testbenches and iteratively refine them using coverage feedback, significantly reducing manual effort while maintaining rigorous verification standards.To evaluate UVM^2, we introduce a benchmark suite comprising Register Transfer Level (RTL) designs of up to 1.6K lines of code.The results show that UVM^2 reduces testbench setup time by up to UVM^2 compared to experienced engineers, and achieve average code and function coverage of 87.44% and 89.58%, outperforming state-of-the-art solutions by 20.96% and 23.51%, respectively.
From Concept to Practice: an Automated LLM-aided UVM Machine for RTL Verification
Paper ↗
Abstract
Verification presents a major bottleneck in Integrated Circuit (IC) development, consuming nearly 70% of the total development effort. While the Universal Verification Methodology (UVM) is widely used in industry to improve verification efficiency through structured and reusable testbenches, constructing these testbenches and generating sufficient stimuli remain challenging. These challenges arise from the considerable manual coding effort required, repetitive manual execution of multiple EDA tools, and the need for in-depth domain expertise to navigate complex designs.Here, we present UVM^2, an automated verification framework that leverages Large Language Models (LLMs) to generate UVM testbenches and iteratively refine them using coverage feedback, significantly reducing manual effort while maintaining rigorous verification standards.To evaluate UVM^2, we introduce a benchmark suite comprising Register Transfer Level (RTL) designs of up to 1.6K lines of code.The results show that UVM^2 reduces testbench setup time by up to UVM^2 compared to experienced engineers, and achieve average code and function coverage of 87.44% and 89.58%, outperforming state-of-the-art solutions by 20.96% and 23.51%, respectively.
Intelligent4DSE: Optimizing High-Level Synthesis Design Space Exploration with Graph Neural Networks and Large Language Models
Paper ↗
Abstract
High-level synthesis (HLS) design space exploration (DSE) is an optimization process in electronic design automation (EDA) that systematically explores high-level design configurations to achieve Pareto-optimal hardware implementations balancing performance, area, and power (PPA). To optimize this process, HLS prediction tasks often employ message-passing neural networks (MPNNs), leveraging complex architectures to achieve high accuracy. These predictors serve as evaluators in the DSE process, effectively bypassing the time-consuming estimations traditionally required by HLS tools. However, existing models often prioritize structural complexity and minimization of training loss, overlooking task-specific characteristics. Additionally, while evolutionary algorithms are widely used in DSE, they typically require extensive domain-specific knowledge to design effective crossover and mutation operators. To address these limitations, we propose CoGNNs-LLMEA, a framework that integrates a graph neural network with task-adaptive message passing and a large language model-enhanced evolutionary algorithm. As a predictive model, CoGNNs directly leverages intermediate representations generated from source code after compiler front-end processing, enabling prediction of quality of results (QoR) without invoking HLS tools. Due to its strong adaptability to tasks, CoGNNs can be tuned to predict post-HLS and post-implementation outcomes, effectively bridging the gap between high-level abstractions and physical implementation characteristics. CoGNNs achieves state-of-the-art prediction accuracy in post-HLS QoR prediction, reducing mean prediction errors by 2.8$\times$ for latency and 3.4$\times$ for resource utilization compared to baseline models.
ChiseLLM: Unleashing the Power of Reasoning LLMs for Chisel Agile Hardware Development
Paper ↗
Abstract
The growing demand for Domain-Specific Architecture (DSA) has driven the development of Agile Hardware Development Methodology (AHDM). Hardware Construction Language (HCL) like Chisel offers high-level abstraction features, making it an ideal language for HCL-Based AHDM. While Large Language Models (LLMs) excel in code generation tasks, they still face challenges with Chisel generation, particularly regarding syntax correctness and design variability. Recent reasoning models have significantly enhanced code generation capabilities through test-time scaling techniques. However, we found that reasoning models without domain adaptation cannot bring substantial benefits to Chisel code generation tasks. This paper presents ChiseLLM, a solution comprising data processing and transformation, prompt-guided reasoning trace synthesis, and domain-adapted model training. We constructed high-quality datasets from public RTL code resources and guided the model to adopt structured thinking patterns through prompt enhancement methods. Experiments demonstrate that our ChiseLLM-7B and ChiseLLM-32B models improved syntax correctness by 18.85% and 26.32% respectively over base models, while increasing variability design ability by 47.58% compared to baseline reasoning models. Our datasets and models are publicly available, providing high-performance, cost-effective models for HCL-Based AHDM, and offering an effective baseline for future research. Github repository: https://github.com/observerw/ChiseLLM
VeriDebug: A Unified LLM for Verilog Debugging via Contrastive Embedding and Guided Correction
Paper ↗
Abstract
Large Language Models (LLMs) have demonstrated remarkable potential in debugging for various programming languages. However, the application of LLMs to Verilog debugging remains insufficiently explored. Here, we present VeriDebug, an approach that integrates contrastive representation and guided correction capabilities for automated Verilog debugging. Unlike existing methods, VeriDebug employs an embedding-based technique to accurately retrieve internal information, followed by bug-fixing. VeriDebug unifies Verilog bug detection and correction through a shared parameter space. By simultaneously learning bug patterns and fixes, it streamlines debugging via contrastive embedding and guided correction. Empirical results show the efficacy of VeriDebug in enhancing Verilog debugging. Our VeriDebugLoc, Type model achieves 64.7 accuracy in bug fixing (Acc1), a significant improvement from the existing open-source SOTAs 11.3. This performance not only outperforms open-source alternatives but also exceeds larger closed-source models like GPT-3.5-turbo (36.6), offering a more accurate alternative to conventional debugging methods.
FLAG: Formal and LLM-assisted SVA Generation for Formal Specifications of On-Chip Communication Protocols
Paper ↗
Abstract
Formal specifications of on-chip communication protocols are crucial for system-on-chip (SoC) design and verification. However, manually constructing these formal specifications from informal documents remains a tedious and error-prone task. Although recent efforts have used Large Language Models (LLMs) to generate SystemVerilog Assertion (SVA) properties from design documents for Register-Transfer Level (RTL) design verification, in our experience these approaches have not shown promise in generating SVA properties for communication protocols. Since protocol specification documents are unstructured and ambiguous in nature, LLMs often fail to extract the necessary information and end up generating irrelevant or even incorrect properties. We propose FLAG, a two-stage framework to help construct formal protocol specifications from informal documents. In the first stage, a predefined template set is used to generate candidate SVA properties. To avoid missing necessary properties, we develop a grammar-based approach to generate comprehensive template sets that capture critical signal behaviors for various communication protocols. In the second stage, we utilize unambiguous timing diagrams in conjunction with textual descriptions from the specification documents to filter out incorrect properties. A formal approach is first implemented to check the candidate properties and filter out those inconsistent with the timing diagrams. An LLM is then consulted to further remove incorrect properties with respect to the textual description, obtaining the final property set. Experiments on various open-source communication protocols demonstrate the effectiveness of FLAG in generating SVA properties from informal documents.
Reinforcement learning framework for the mechanical design of microelectronic components under multiphysics constraints
Paper ↗
Abstract
This study focuses on the development of reinforcement learning based techniques for the design of microelectronic components under multiphysics constraints. While traditional design approaches based on global optimization approaches are effective when dealing with a small number of design parameters, as the complexity of the solution space and of the constraints increases different techniques are needed. This is an important reason that makes the design and optimization of microelectronic components (characterized by large solution space and multiphysics constraints) very challenging for traditional methods. By taking as prototypical elements an application-specific integrated circuit (ASIC) and a heterogeneously integrated (HI) interposer, we develop and numerically test an optimization framework based on reinforcement learning (RL). More specifically, we consider the optimization of the bonded interconnect geometry for an ASIC chip as well as the placement of components on a HI interposer while satisfying thermoelastic and design constraints. This placement problem is particularly interesting because it features a high-dimensional solution space.
Insights from Verification: Training a Verilog Generation LLM with Reinforcement Learning with Testbench Feedback
Paper ↗
Abstract
Large language models (LLMs) have shown strong performance in Verilog generation from natural language description. However, ensuring the functional correctness of the generated code remains a significant challenge. This paper introduces a method that integrates verification insights from testbench into the training of Verilog generation LLMs, aligning the training with the fundamental goal of hardware design: functional correctness. The main obstacle in using LLMs for Verilog code generation is the lack of sufficient functional verification data, particularly testbenches paired with design specifications and code. To address this problem, we introduce an automatic testbench generation pipeline that decomposes the process and uses feedback from the Verilog compiler simulator (VCS) to reduce hallucination and ensure correctness. We then use the testbench to evaluate the generated codes and collect them for further training, where verification insights are introduced. Our method applies reinforcement learning (RL), specifically direct preference optimization (DPO), to align Verilog code generation with functional correctness by training preference pairs based on testbench outcomes. In evaluations on VerilogEval-Machine, VerilogEval-Human, RTLLM v1.1, RTLLM v2, and VerilogEval v2, our approach consistently outperforms state-of-the-art baselines in generating functionally correct Verilog code. We open source all training code, data, and models at https://anonymous.4open.science/r/VeriPrefer-E88B.
SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference
Paper ↗
Abstract
Large language models (LLMs) with different architectures and sizes have been developed. Serving each LLM with dedicated GPUs leads to resource waste and service inefficiency due to the varying demand of LLM requests. A common practice is to share multiple LLMs. However, existing sharing systems either do not consider the autoregressive pattern of LLM services, or only focus on improving the throughput, which impairs the sharing performance, especially the serving latency. We present SeaLLM, which enables service-aware and latency-optimized LLM sharing. SeaLLM improves the overall sharing performance by (1) a latency-optimized scheduling algorithm utilizing the characteristics of LLM services, (2) a placement algorithm to determine the placement plan and an adaptive replacement algorithm to decide the replacement interval, and (3) a unified key-value cache to share GPU memory among LLM services efficiently. Our evaluation under real-world traces and LLM services demonstrates that SeaLLM improves the normalized latency by up to $13.60\times$, the tail latency by up to $18.69\times$, and the SLO attainment by up to $3.64\times$ compared to existing solutions.
SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference
Paper ↗
Abstract
Large language models (LLMs) with different architectures and sizes have been developed. Serving each LLM with dedicated GPUs leads to resource waste and service inefficiency due to the varying demand of LLM requests. A common practice is to share multiple LLMs. However, existing sharing systems either do not consider the autoregressive pattern of LLM services, or only focus on improving the throughput, which impairs the sharing performance, especially the serving latency. We present SeaLLM, which enables service-aware and latency-optimized LLM sharing. SeaLLM improves the overall sharing performance by (1) a latency-optimized scheduling algorithm utilizing the characteristics of LLM services, (2) a placement algorithm to determine the placement plan and an adaptive replacement algorithm to decide the replacement interval, and (3) a unified key-value cache to share GPU memory among LLM services efficiently. Our evaluation under real-world traces and LLM services demonstrates that SeaLLM improves the normalized latency by up to $13.60\times$, the tail latency by up to $18.69\times$, and the SLO attainment by up to $3.64\times$ compared to existing solutions.
VeriCoder: Enhancing LLM-Based RTL Code Generation through Functional Correctness Validation
Paper ↗
Abstract
Recent advances in Large Language Models (LLMs) have sparked growing interest in applying them to Electronic Design Automation (EDA) tasks, particularly Register Transfer Level (RTL) code generation. While several RTL datasets have been introduced, most focus on syntactic validity rather than functional validation with tests, leading to training examples that compile but may not implement the intended behavior. We present VERICODER, a model for RTL code generation fine-tuned on a dataset validated for functional correctness. This fine-tuning dataset is constructed using a novel methodology that combines unit test generation with feedback-directed refinement. Given a natural language specification and an initial RTL design, we prompt a teacher model (GPT-4o-mini) to generate unit tests and iteratively revise the RTL design based on its simulation results using the generated tests. If necessary, the teacher model also updates the tests to ensure they comply with the natural language specification. As a result of this process, every example in our dataset is functionally validated, consisting of a natural language description, an RTL implementation, and passing tests. Fine-tuned on this dataset of over 125,000 examples, VERICODER achieves state-of-the-art metrics in functional correctness on VerilogEval and RTLLM, with relative gains of up to 71.7% and 27.4% respectively. An ablation study further shows that models trained on our functionally validated dataset outperform those trained on functionally non-validated datasets, underscoring the importance of high-quality datasets in RTL code generation.
VeriCoder: Enhancing LLM-Based RTL Code Generation through Functional Correctness Validation
Paper ↗
Abstract
Recent advances in Large Language Models (LLMs) have sparked growing interest in applying them to Electronic Design Automation (EDA) tasks, particularly Register Transfer Level (RTL) code generation. While several RTL datasets have been introduced, most focus on syntactic validity rather than functional validation with tests, leading to training examples that compile but may not implement the intended behavior. We present VERICODER, a model for RTL code generation fine-tuned on a dataset validated for functional correctness. This fine-tuning dataset is constructed using a novel methodology that combines unit test generation with feedback-directed refinement. Given a natural language specification and an initial RTL design, we prompt a teacher model (GPT-4o-mini) to generate unit tests and iteratively revise the RTL design based on its simulation results using the generated tests. If necessary, the teacher model also updates the tests to ensure they comply with the natural language specification. As a result of this process, every example in our dataset is functionally validated, consisting of a natural language description, an RTL implementation, and passing tests. Fine-tuned on this dataset of 125,777 examples, VERICODER achieves state-of-the-art metrics in functional correctness on VerilogEval and RTLLM, with relative gains of up to 71.7% and 27.4%, respectively. An ablation study further shows that models trained on our functionally validated dataset outperform those trained on functionally non-validated datasets, underscoring the importance of high-quality datasets in RTL code generation. Our code, data, and models are publicly available at https://github.com/Anjiang-Wei/VeriCoder
Advancing AI-assisted Hardware Design with Hierarchical Decentralized Training and Personalized Inference-Time Optimization
Paper ↗
Abstract
Recent years have witnessed a significant increase in the adoption of AI techniques to enhance electronic design automation. In particular, the emergence of Large Language Models (LLMs) has sparked significant interest in LLM-assisted hardware design generation, spanning applications from classical digital circuits to quantum computing. Despite substantial progress in this direction, the quality of LLM-generated hardware design still cannot meet the requirements for practical deployment. In this work, we identify three critical challenges hindering the development of LLM-assisted hardware design generation: 1) limited data availability, 2) varied data quality, 3) inadequate inference-time efficiency. To address these fundamental challenges, this paper introduces a two-stage framework for AI-assisted hardware design by exploring decentralized training and personalized inference. In the first stage, we propose to harness private domain design sources through a hierarchical decentralized training mechanism that addresses data-sharing constraints. To mitigate the impact of low-quality data, we identify optimization opportunities in hardware generation tasks, using user-defined metrics for model aggregation. The second stage focuses on client personalization to enhance both speed and quality. We introduce a new metric, Trueput, to analyze LLM-assisted hardware generation efficiency. To optimize Trueput, we implement personalized inference-time acceleration and customized sampling strategies. Evaluating both classical and quantum benchmarks, our experimental results demonstrate that the proposed two-stage framework can significantly improve the model capability for hardware design generation. As orthogonal enhancements to existing methods, our framework can achieve $33\% \sim 50\%$ semantic accuracy improvement and $2.3$ times speedup, depending on the difficulty of the generation tasks.
HLSTester: Efficient Testing of Behavioral Discrepancies with LLMs for High-Level Synthesis
Paper ↗
Abstract
In high-level synthesis (HLS), C/C++ programs with synthesis directives are used to generate circuits for FPGA implementations. However, hardware-specific and platform-dependent characteristics in these implementations can introduce behavioral discrepancies between the original C/C++ programs and the circuits after high-level synthesis. Existing methods for testing behavioral discrepancies in HLS are still immature, and the testing workflow requires significant human efforts. To address this challenge, we propose HLSTester, a large language model (LLM) aided testing framework that efficiently detects behavioral discrepancies in HLS. To mitigate hallucinations in LLMs and enhance prompt quality, the testbenches for original C/C++ programs are leveraged to guide LLMs in generating HLS-compatible testbenches, effectively eliminating certain traditional C/C++ constructs that are incompatible with HLS tools. Key variables are pinpointed through a backward slicing technique in both C/C++ and HLS programs to monitor their runtime spectra, enabling an in-depth analysis of the discrepancy symptoms. To reduce test time, a testing input generation mechanism is introduced to integrate dynamic mutation with insights from an LLM-based progressive reasoning chain. In addition, repetitive hardware testing is skipped by a redundancy-aware filtering technique for the generated test inputs. Experimental results demonstrate that the proposed LLM-aided testing framework significantly accelerates the testing workflow while achieving higher testbench simulation pass rates compared with the traditional method and the direct use of LLMs on the same HLS programs.
HLSTester: Efficient Testing of Behavioral Discrepancies with LLMs for High-Level Synthesis
Paper ↗
Abstract
In high-level synthesis (HLS), C/C++ programs with synthesis directives are used to generate circuits for FPGA implementations. However, hardware-specific and platform-dependent characteristics in these implementations can introduce behavioral discrepancies between the original C/C++ programs and the circuits after high-level synthesis. Existing methods for testing behavioral discrepancies in HLS are still immature, and the testing workflow requires significant human efforts. To address this challenge, we propose HLSTester, a large language model (LLM) aided testing framework that efficiently detects behavioral discrepancies in HLS. To mitigate hallucinations in LLMs and enhance prompt quality, the testbenches for original C/C++ programs are leveraged to guide LLMs in generating HLS-compatible testbenches, effectively eliminating certain traditional C/C++ constructs that are incompatible with HLS tools. Key variables are pinpointed through a backward slicing technique in both C/C++ and HLS programs to monitor their runtime spectra, enabling an in-depth analysis of the discrepancy symptoms. To reduce test time, a testing input generation mechanism is introduced to integrate dynamic mutation with insights from an LLM-based progressive reasoning chain. In addition, repetitive hardware testing is skipped by a redundancy-aware filtering technique for the generated test inputs. Experimental results demonstrate that the proposed LLM-aided testing framework significantly accelerates the testing workflow while achieving higher testbench simulation pass rates compared with the traditional method and the direct use of LLMs on the same HLS programs.
Towards Optimal Circuit Generation: Multi-Agent Collaboration Meets Collective Intelligence
Paper ↗
Abstract
Large language models (LLMs) have transformed code generation, yet their application in hardware design produces gate counts 38\%--1075\% higher than human designs. We present CircuitMind, a multi-agent framework that achieves human-competitive efficiency through three key innovations: syntax locking (constraining generation to basic logic gates), retrieval-augmented generation (enabling knowledge-driven design), and dual-reward optimization (balancing correctness with efficiency). To evaluate our approach, we introduce TC-Bench, the first gate-level benchmark harnessing collective intelligence from the TuringComplete ecosystem -- a competitive circuit design platform with hundreds of thousands of players. Experiments show CircuitMind enables 55.6\% of model implementations to match or exceed top-tier human experts in composite efficiency metrics. Most remarkably, our framework elevates the 14B Phi-4 model to outperform both GPT-4o mini and Gemini 2.0 Flash, achieving efficiency comparable to the top 25\% of human experts without requiring specialized training. These innovations establish a new paradigm for hardware optimization where collaborative AI systems leverage collective human expertise to achieve optimal circuit designs. Our model, data, and code are open-source at https://github.com/BUAA-CLab/CircuitMind.
ReasoningV: Efficient Verilog Code Generation with Adaptive Hybrid Reasoning Model
Paper ↗
Abstract
Large Language Models (LLMs) have advanced Verilog code generation significantly, yet face challenges in data quality, reasoning capabilities, and computational efficiency. This paper presents ReasoningV, a novel model employing a hybrid reasoning strategy that integrates trained intrinsic capabilities with dynamic inference adaptation for Verilog code generation. Our framework introduces three complementary innovations: (1) ReasoningV-5K, a high-quality dataset of 5,000 functionally verified instances with reasoning paths created through multi-dimensional filtering of PyraNet samples; (2) a two-stage training approach combining parameter-efficient fine-tuning for foundational knowledge with full-parameter optimization for enhanced reasoning; and (3) an adaptive reasoning mechanism that dynamically adjusts reasoning depth based on problem complexity, reducing token consumption by up to 75\% while preserving performance. Experimental results demonstrate ReasoningV's effectiveness with a pass@1 accuracy of 57.8\% on VerilogEval-human, achieving performance competitive with leading commercial models like Gemini-2.0-flash (59.5\%) and exceeding the previous best open-source model by 10.4 percentage points. ReasoningV offers a more reliable and accessible pathway for advancing AI-driven hardware design automation, with our model, data, and code available at https://github.com/BUAA-CLab/ReasoningV.
A Novel Frequency-Spatial Domain Aware Network for Fast Thermal Prediction in 2.5D ICs
Paper ↗
Abstract
In the post-Moore era, 2.5D chiplet-based ICs present significant challenges in thermal management due to increased power density and thermal hotspots. Neural network-based thermal prediction models can perform real-time predictions for many unseen new designs. However, existing CNN-based and GCN-based methods cannot effectively capture the global thermal features, especially for high-frequency components, hindering prediction accuracy enhancement. In this paper, we propose a novel frequency-spatial dual domain aware prediction network (FSA-Heat) for fast and high-accuracy thermal prediction in 2.5D ICs. It integrates high-to-low frequency and spatial domain encoder (FSTE) module with frequency domain cross-scale interaction module (FCIFormer) to achieve high-to-low frequency and global-to-local thermal dissipation feature extraction. Additionally, a frequency-spatial hybrid loss (FSL) is designed to effectively attenuate high-frequency thermal gradient noise and spatial misalignments. The experimental results show that the performance enhancements offered by our proposed method are substantial, outperforming the newly-proposed 2.5D method, GCN+PNA, by considerable margins (over 99% RMSE reduction, 4.23X inference time speedup). Moreover, extensive experiments demonstrate that FSA-Heat also exhibits robust generalization capabilities.
Evolution of Optimization Algorithms for Global Placement via Large Language Models
Paper ↗
Abstract
Optimization algorithms are widely employed to tackle complex problems, but designing them manually is often labor-intensive and requires significant expertise. Global placement is a fundamental step in electronic design automation (EDA). While analytical approaches represent the state-of-the-art (SOTA) in global placement, their core optimization algorithms remain heavily dependent on heuristics and customized components, such as initialization strategies, preconditioning methods, and line search techniques. This paper presents an automated framework that leverages large language models (LLM) to evolve optimization algorithms for global placement. We first generate diverse candidate algorithms using LLM through carefully crafted prompts. Then we introduce an LLM-based genetic flow to evolve selected candidate algorithms. The discovered optimization algorithms exhibit substantial performance improvements across many benchmarks. Specifically, Our design-case-specific discovered algorithms achieve average HPWL improvements of \textbf{5.05\%}, \text{5.29\%} and \textbf{8.30\%} on MMS, ISPD2005 and ISPD2019 benchmarks, and up to \textbf{17\%} improvements on individual cases. Additionally, the discovered algorithms demonstrate good generalization ability and are complementary to existing parameter-tuning methods.
MetaDSE: A Few-shot Meta-learning Framework for Cross-workload CPU Design Space Exploration
Paper ↗
Abstract
Cross-workload design space exploration (DSE) is crucial in CPU architecture design. Existing DSE methods typically employ the transfer learning technique to leverage knowledge from source workloads, aiming to minimize the requirement of target workload simulation. However, these methods struggle with overfitting, data ambiguity, and workload dissimilarity. To address these challenges, we reframe the cross-workload CPU DSE task as a few-shot meta-learning problem and further introduce MetaDSE. By leveraging model agnostic meta-learning, MetaDSE swiftly adapts to new target workloads, greatly enhancing the efficiency of cross-workload CPU DSE. Additionally, MetaDSE introduces a novel knowledge transfer method called the workload-adaptive architectural mask algorithm, which uncovers the inherent properties of the architecture. Experiments on SPEC CPU 2017 demonstrate that MetaDSE significantly reduces prediction error by 44.3\% compared to the state-of-the-art. MetaDSE is open-sourced and available at this \href{https://anonymous.4open.science/r/Meta_DSE-02F8}{anonymous GitHub.}
HLS-Eval: A Benchmark and Framework for Evaluating LLMs on High-Level Synthesis Design Tasks
Paper ↗
Abstract
The rapid scaling of large language model (LLM) training and inference has driven their adoption in semiconductor design across academia and industry. While most prior work evaluates LLMs on hardware description language (HDL) tasks, particularly Verilog, designers are increasingly using high-level synthesis (HLS) to build domain-specific accelerators and complex hardware systems. However, benchmarks and tooling to comprehensively evaluate LLMs for HLS design tasks remain scarce. To address this, we introduce HLS-Eval, the first complete benchmark and evaluation framework for LLM-driven HLS design. HLS-Eval targets two core tasks: (1) generating HLS code from natural language descriptions, and (2) performing HLS-specific code edits to optimize performance and hardware efficiency. The benchmark includes 94 unique designs drawn from standard HLS benchmarks and novel sources. Each case is prepared via a semi-automated flow that produces a natural language description and a paired testbench for C-simulation and synthesis validation, ensuring each task is "LLM-ready." Beyond the benchmark, HLS-Eval offers a modular Python framework for automated, parallel evaluation of both local and hosted LLMs. It includes a parallel evaluation engine, direct HLS tool integration, and abstractions for to support different LLM interaction paradigms, enabling rapid prototyping of new benchmarks, tasks, and LLM methods. We demonstrate HLS-Eval through baseline evaluations of open-source LLMs on Vitis HLS, measuring outputs across four key metrics - parseability, compilability, runnability, and synthesizability - reflecting the iterative HLS design cycle. We also report pass@k metrics, establishing clear baselines and reusable infrastructure for the broader LLM-for-hardware community. All benchmarks, framework code, and results are open-sourced at https://github.com/stefanpie/hls-eval.
AutoRAN: Automated and Zero-Touch Open RAN Systems
Paper ↗
Abstract
[...] This paper presents AutoRAN, an automated, intent-driven framework for zero-touch provisioning of open, programmable cellular networks. Leveraging cloud-native principles, AutoRAN employs virtualization, declarative infrastructure-as-code templates, and disaggregated micro-services to abstract physical resources and protocol stacks. Its orchestration engine integrates Language Models (LLMs) to translate high-level intents into machine-readable configurations, enabling closed-loop control via telemetry-driven observability. Implemented on a multi-architecture OpenShift cluster with heterogeneous compute (x86/ARM CPUs, NVIDIA GPUs) and multi-vendor Radio Access Network (RAN) hardware (Foxconn, NI), AutoRAN automates deployment of O-RAN-compliant stacks-including OpenAirInterface, NVIDIA ARC RAN, Open5GS core, and O-RAN Software Community (OSC) RIC components-using CI/CD pipelines. Experimental results demonstrate that AutoRAN is capable of deploying an end-to-end Private 5G network in less than 60 seconds with 1.6 Gbps throughput, validating its ability to streamline configuration, accelerate testing, and reduce manual intervention with similar performance than non cloud-based implementations. With its novel LLM-assisted intent translation mechanism, and performance-optimized automation workflow for multi-vendor environments, AutoRAN has the potential of advancing the robustness of next-generation cellular supply chains through reproducible, intent-based provisioning across public and private deployments.
Timing Analysis Agent: Autonomous Multi-Corner Multi-Mode (MCMM) Timing Debugging with Timing Debug Relation Graph
Paper ↗
Abstract
Timing analysis is an essential and demanding verification method for Very Large Scale Integrated (VLSI) circuit design and optimization. In addition, it also serves as the cornerstone of the final sign-off, determining whether the chip is ready to be sent to the semiconductor foundry for fabrication. Recently, as the technology advance relentlessly, smaller metal pitches and the increasing number of devices have led to greater challenges and longer turn-around-time for experienced human designers to debug timing issues from the Multi-Corner Multi-Mode (MCMM) timing reports. As a result, an efficient and intelligent methodology is highly necessary and essential for debugging timing issues and reduce the turnaround times. Recently, Large Language Models (LLMs) have shown great promise across various tasks in language understanding and interactive decision-making, incorporating reasoning and actions. In this work, we propose a timing analysis agent, that is empowered by multi-LLMs task solving, and incorporates a novel hierarchical planning and solving flow to automate the analysis of timing reports from commercial tool. In addition, we build a Timing Debug Relation Graph (TDRG) that connects the reports with the relationships of debug traces from experienced timing engineers. The timing analysis agent employs the novel Agentic Retrieval Augmented Generation (RAG) approach, that includes agent and coding to retrieve data accurately, on the developed TDRG. In our studies, the proposed timing analysis agent achieves an average 98% pass-rate on a single-report benchmark and a 90% pass-rate for multi-report benchmark from industrial designs, demonstrating its effectiveness and adaptability.
LLM-based AI Agent for Sizing of Analog and Mixed Signal Circuit
Paper ↗
Abstract
The design of Analog and Mixed-Signal (AMS) integrated circuits (ICs) often involves significant manual effort, especially during the transistor sizing process. While Machine Learning techniques in Electronic Design Automation (EDA) have shown promise in reducing complexity and minimizing human intervention, they still face challenges such as numerous iterations and a lack of knowledge about AMS circuit design. Recently, Large Language Models (LLMs) have demonstrated significant potential across various fields, showing a certain level of knowledge in circuit design and indicating their potential to automate the transistor sizing process. In this work, we propose an LLM-based AI agent for AMS circuit design to assist in the sizing process. By integrating LLMs with external circuit simulation tools and data analysis functions and employing prompt engineering strategies, the agent successfully optimized multiple circuits to achieve target performance metrics. We evaluated the performance of different LLMs to assess their applicability and optimization effectiveness across seven basic circuits, and selected the best-performing model Claude 3.5 Sonnet for further exploration on an operational amplifier, with complementary input stage and class AB output stage. This circuit was evaluated against nine performance metrics, and we conducted experiments under three distinct performance requirement groups. A success rate of up to 60% was achieved for reaching the target requirements. Overall, this work demonstrates the potential of LLMs to improve AMS circuit design.
GNN-ACLP: Graph Neural Networks Based Analog Circuit Link Prediction
Paper ↗
Abstract
Circuit link prediction identifying missing component connections from incomplete netlists is crucial in automating analog circuit design. However, existing methods face three main challenges: 1) Insufficient use of topological patterns in circuit graphs reduces prediction accuracy; 2) Data scarcity due to the complexity of annotations hinders model generalization; 3) Limited adaptability to various netlist formats. We propose GNN-ACLP, a Graph Neural Networks (GNNs) based framework featuring three innovations to tackle these challenges. First, we introduce the SEAL (Subgraphs, Embeddings, and Attributes for Link Prediction) framework and achieve port-level accuracy in circuit link prediction. Second, we propose Netlist Babel Fish, a netlist format conversion tool leveraging retrieval-augmented generation (RAG) with a large language model (LLM) to enhance the compatibility of netlist formats. Finally, we construct SpiceNetlist, a comprehensive dataset that contains 775 annotated circuits across 10 different component classes. Experiments demonstrate accuracy improvements of 16.08% on SpiceNetlist, 11.38% on Image2Net, and 16.01% on Masala-CHAI compared to the baseline in intra-dataset evaluation, while maintaining accuracy from 92.05% to 99.07% in cross-dataset evaluation, exhibiting robust feature transfer capabilities.
GNN-ACLP: Graph Neural Networks Based Analog Circuit Link Prediction
Paper ↗
Abstract
Circuit link prediction identifying missing component connections from incomplete netlists is crucial in analog circuit design automation. However, existing methods face three main challenges: 1) Insufficient use of topological patterns in circuit graphs reduces prediction accuracy; 2) Data scarcity due to the complexity of annotations hinders model generalization; 3) Limited adaptability to various netlist formats. We propose GNN-ACLP, a graph neural networks (GNNs) based method featuring three innovations to tackle these challenges. First, we introduce the SEAL (learning from Subgraphs, Embeddings, and Attributes for Link prediction) framework and achieve port-level accuracy in circuit link prediction. Second, we propose Netlist Babel Fish, a netlist format conversion tool leveraging retrieval-augmented generation (RAG) with a large language model (LLM) to improve the compatibility of netlist formats. Finally, we construct SpiceNetlist, a comprehensive dataset that contains 775 annotated circuits across 10 different component classes. Experiments demonstrate accuracy improvements of 16.08% on SpiceNetlist, 11.38% on Image2Net, and 16.01% on Masala-CHAI compared to the baseline in intra-dataset evaluation, while maintaining accuracy from 92.05% to 99.07% in cross-dataset evaluation, exhibiting robust feature transfer capabilities.
NetTAG: A Multimodal RTL-and-Layout-Aligned Netlist Foundation Model via Text-Attributed Graph
Paper ↗
Abstract
Circuit representation learning has shown promise in advancing Electronic Design Automation (EDA) by capturing structural and functional circuit properties for various tasks. Existing pre-trained solutions rely on graph learning with complex functional supervision, such as truth table simulation. However, they only handle simple and-inverter graphs (AIGs), struggling to fully encode other complex gate functionalities. While large language models (LLMs) excel at functional understanding, they lack the structural awareness for flattened netlists. To advance netlist representation learning, we present NetTAG, a netlist foundation model that fuses gate semantics with graph structure, handling diverse gate types and supporting a variety of functional and physical tasks. Moving beyond existing graph-only methods, NetTAG formulates netlists as text-attributed graphs, with gates annotated by symbolic logic expressions and physical characteristics as text attributes. Its multimodal architecture combines an LLM-based text encoder for gate semantics and a graph transformer for global structure. Pre-trained with gate and graph self-supervised objectives and aligned with RTL and layout stages, NetTAG captures comprehensive circuit intrinsics. Experimental results show that NetTAG consistently outperforms each task-specific method on four largely different functional and physical tasks and surpasses state-of-the-art AIG encoders, demonstrating its versatility.
AGENT: An Aerial Vehicle Generation and Design Tool Using Large Language Models
Paper ↗
Abstract
Computer-aided design (CAD) is a promising application area for emerging artificial intelligence methods. Traditional workflows for cyberphysical systems create detailed digital models which can be evaluated by physics simulators in order to narrow the search space before creating physical prototypes. A major bottleneck of this approach is that the simulators are often computationally expensive and slow. Recent advancements in AI methods offer the possibility to accelerate these pipelines. We use the recently released AircraftVerse dataset, which is especially suited for developing and evaluating large language models for designs. AircraftVerse contains a diverse set of UAV designs represented via textual design trees together with detailed physics simulation results. Following the recent success of large language models (LLMs), we propose AGENT (Aircraft GENeraTor). AGENT is a comprehensive design tool built on the CodeT5+ LLM which learns powerful representations of aircraft textual designs directly from JSON files. We develop a curriculum of training tasks which imbues a single model with a suite of useful features. AGENT is able to generate designs conditioned on properties of flight dynamics (hover time, maximum speed, etc.). Additionally, AGENT can issue evaluations of designs allowing it to act as a surrogate model of the physics simulation that underlies the AircraftVerse dataset. We present a series of experiments which demonstrate our system's abilities. We are able to achieve strong performance using the smallest member of the CodeT5+ family (220M parameters). This allows for a flexible and powerful system which can be executed on a single GPU enabling a clear path toward future deployment.
AGENT: An Aerial Vehicle Generation and Design Tool Using Large Language Models
Paper ↗
Abstract
Computer-aided design (CAD) is a promising application area for emerging artificial intelligence methods. Traditional workflows for cyberphysical systems create detailed digital models which can be evaluated by physics simulators in order to narrow the search space before creating physical prototypes. A major bottleneck of this approach is that the simulators are often computationally expensive and slow. Recent advancements in AI methods offer the possibility to accelerate these pipelines. We use the recently released AircraftVerse dataset, which is especially suited for developing and evaluating large language models for designs. AircraftVerse contains a diverse set of UAV designs represented via textual design trees together with detailed physics simulation results. Following the recent success of large language models (LLMs), we propose AGENT (Aircraft GENeraTor). AGENT is a comprehensive design tool built on the CodeT5+ LLM which learns powerful representations of aircraft textual designs directly from JSON files. We develop a curriculum of training tasks which imbues a single model with a suite of useful features. AGENT is able to generate designs conditioned on properties of flight dynamics (hover time, maximum speed, etc.). Additionally, AGENT can issue evaluations of designs allowing it to act as a surrogate model of the physics simulation that underlies the AircraftVerse dataset. We present a series of experiments which demonstrate our system's abilities. We are able to achieve strong performance using the smallest member of the CodeT5+ family (220M parameters). This allows for a flexible and powerful system which can be executed on a single GPU enabling a clear path toward future deployment.
RAG-Based Fuzzing of Cross-Architecture Compilers
Paper ↗
Abstract
OneAPI is an open standard that supports cross-architecture software development with minimal effort from developers. It brings DPC++ and C++ compilers which need to be thoroughly tested to verify their correctness, reliability, and security. Compilers have numerous code flows and optimization features. This process requires developers with deep understanding of the different compiler flows to craft testcases specific to target paths in the compiler. This testcase creation is a time-consuming and costly process. In this paper, we propose a large-language model (LLM)-based compiler fuzzing tool that integrates the concept of retrieval-augmented generation (RAG). This tool automates the testcase generation task and relieves experienced compiler developers from investing time to craft testcase generation patterns. We test our proposed approach on the Intel DPC++/C++ compiler. This compiler compiles SYCL code and allows developers to offload it to different architectures, e.g. GPUs and CPUs from different vendors. Using this tool, we managed to identify 87 SYCL code test cases that lead to output value mismatch or compiler runtime errors when compiled using Intel DPC++ and clang++ compilers and run on different architectures. The testcases and the identified unexpected behaviors of the compilers under test were obtained within only few hours with no prior background on the compiler passes under tests. This tool facilitates efficient compiler fuzzing with reduced developer time requirements via the dynamic testcase creation capability provided by an LLM with RAG.
An Adaptive Vector Index Partitioning Scheme for Low-Latency RAG Pipeline
Paper ↗
Abstract
Retrieval Augmented Generation (RAG) systems enhance response quality by integrating Large Language Models (LLMs) with vector databases, enabling external knowledge retrieval to support language model reasoning. While RAG enables efficient question answering with smaller LLMs, existing optimizations for vector search and LLM serving have largely been developed in isolation. As a result, their integration often leads to suboptimal end-to-end performance. ... This paper introduces VectorLiteRAG, an optimized vector index partitioning mechanism designed for RAG systems that enhances the responsiveness of the system by jointly optimizing vector search and LLM serving across CPU and GPU system. A key challenge is to determine which indices and how much of the vector index should reside on the GPU and adjusting LLM batch sizes to balance the pipeline for lower Time-To-First-Token (TTFT) and meeting user-defined Service-Level Objectives (SLOs). To address this, we leverage the insight that cluster access in vector databases exhibits access skew, where a subset of clusters are queried significantly more frequently than others. VectorLiteRAG exploits this property through an optimized memory distribution strategy, dynamically allocating the minimum number of vector indices corresponding to frequently accessed clusters onto the GPU HBM to ensure a balanced pipeline with the LLM for high responsiveness. This adaptive partitioning scheme is guided by a statistical model that informs memory allocation and workload distribution. Our evaluation demonstrates that VectorLiteRAG improves vector search responsiveness by 2x, significantly reduces end-to-end TTFT in RAG systems by intelligently balancing memory resources between vector search and LLM execution.
VectorLiteRAG: Latency-Aware and Fine-Grained Resource Partitioning for Efficient RAG
Paper ↗
Abstract
Retrieval-Augmented Generation (RAG) systems combine vector similarity search with large language models (LLMs) to deliver accurate, context-aware responses. However, co-locating the vector retriever and the LLM on shared GPU infrastructure introduces significant challenges: vector search is memory and I/O intensive, while LLM inference demands high throughput and low latency. Naive resource sharing often leads to severe performance degradation, particularly under high request load or large index sizes. We present VectorLiteRAG, a deployment-friendly RAG system that achieves latency-compliant inference without requiring additional hardware resources. VectorLiteRAG introduces a fine-grained GPU resource allocation mechanism based on detailed performance modeling and access pattern analysis. By estimating search latency and query hit rate distributions, it identifies an optimal index partitioning point across CPU and GPU tiers to minimize contention and maximize throughput. Our evaluations show that VectorLiteRAG consistently expands the SLO compliant request rate range across all tested configurations, including both small and large LLMs, and small and large vector databases compared to naive baselines and state of the art alternatives. In the best case, VectorLiteRAG improves the attainable SLO throughput by up to 1.5 times without compromising generation quality or requiring additional compute resources.
RTLRepoCoder: Repository-Level RTL Code Completion through the Combination of Fine-Tuning and Retrieval Augmentation
Paper ↗
Abstract
As an essential part of modern hardware design, manually writing Register Transfer Level (RTL) code such as Verilog is often labor-intensive. Following the tremendous success of large language models (LLMs), researchers have begun to explore utilizing LLMs for generating RTL code. However, current studies primarily focus on generating simple single modules, which can not meet the demands in real world. In fact, due to challenges in managing long-context RTL code and complex cross-file dependencies, existing solutions cannot handle large-scale Verilog repositories in practical hardware development. As the first endeavor to exclusively adapt LLMs for large-scale RTL development, we propose RTLRepoCoder, a groundbreaking solution that incorporates specific fine-tuning and Retrieval-Augmented Generation (RAG) for repository-level Verilog code completion. Open-source Verilog repositories from the real world, along with an extended context size, are used for domain-specific fine-tuning. The optimized RAG system improves the information density of the input context by retrieving relevant code snippets. Tailored optimizations for RAG are carried out, including the embedding model, the cross-file context splitting strategy, and the chunk size. Our solution achieves state-of-the-art performance on public benchmark, significantly surpassing GPT-4 and advanced domain-specific LLMs on Edit Similarity and Exact Match rate. Comprehensive experiments demonstrate the remarkable effectiveness of our approach and offer insights for future work.
Hardware Design and Security Needs Attention: From Survey to Path Forward
Paper ↗
Abstract
Recent advances in attention-based artificial intelligence (AI) models have unlocked vast potential to automate digital hardware design while enhancing and strengthening security measures against various threats. This rapidly emerging field leverages Large Language Models (LLMs) to generate HDL code, identify vulnerabilities, and sometimes mitigate them. The state of the art in this design automation space utilizes optimized LLMs with HDL datasets, creating automated systems for register-transfer level (RTL) generation, verification, and debugging, and establishing LLM-driven design environments for streamlined logic designs. Additionally, attention-based models like graph attention have shown promise in chip design applications, including floorplanning. This survey investigates the integration of these models into hardware-related domains, emphasizing logic design and hardware security, with or without the use of IP libraries. This study explores the commercial and academic landscape, highlighting technical hurdles and future prospects for automating hardware design and security. Moreover, it provides new insights into the study of LLM-driven design systems, advances in hardware security mechanisms, and the impact of influential works on industry practices. Through the examination of 30 representative approaches and illustrative case studies, this paper underscores the transformative potential of attention-based models in revolutionizing hardware design while addressing the challenges that lie ahead in this interdisciplinary domain.
BRIDGES: Bridging Graph Modality and Large Language Models within EDA Tasks
Paper ↗
Abstract
While many EDA tasks already involve graph-based data, existing LLMs in EDA primarily either represent graphs as sequential text, or simply ignore graph-structured data that might be beneficial like dataflow graphs of RTL code. Recent studies have found that LLM performance suffers when graphs are represented as sequential text, and using additional graph information significantly boosts performance. To address these challenges, we introduce BRIDGES, a framework designed to incorporate graph modality into LLMs for EDA tasks. BRIDGES integrates an automated data generation workflow, a solution that combines graph modality with LLM, and a comprehensive evaluation suite. First, we establish an LLM-driven workflow to generate RTL and netlist-level data, converting them into dataflow and netlist graphs with function descriptions. This workflow yields a large-scale dataset comprising over 500,000 graph instances and more than 1.5 billion tokens. Second, we propose a lightweight cross-modal projector that encodes graph representations into text-compatible prompts, enabling LLMs to effectively utilize graph data without architectural modifications. Experimental results demonstrate 2x to 10x improvements across multiple tasks compared to text-only baselines, including accuracy in design retrieval, type prediction and perplexity in function description, with negligible computational overhead (<1% model weights increase and <30% additional runtime overhead). Even without additional LLM finetuning, our results outperform text-only by a large margin. We plan to release BRIDGES, including the dataset, models, and training flow.
TuRTLe: A Unified Evaluation of LLMs for RTL Generation
Paper ↗
Abstract
The rapid advancements in LLMs have driven the adoption of generative AI in various domains, including Electronic Design Automation (EDA). Unlike traditional software development, EDA presents unique challenges, as generated RTL code must not only be syntactically correct and functionally accurate but also synthesizable by hardware generators while meeting performance, power, and area constraints. These additional requirements introduce complexities that existing code-generation benchmarks often fail to capture, limiting their effectiveness in evaluating LLMs for RTL generation. To address this gap, we propose TuRTLe, a unified evaluation framework designed to systematically assess LLMs across key RTL generation tasks. TuRTLe integrates multiple existing benchmarks and automates the evaluation process, enabling a comprehensive assessment of LLM performance in syntax correctness, functional correctness, synthesis, PPA optimization, and exact line completion. Using this framework, we benchmark a diverse set of open LLMs and analyze their strengths and weaknesses in EDA-specific tasks. Our results show that reasoning-based models, such as DeepSeek R1, consistently outperform others across multiple evaluation criteria, but at the cost of increased computational overhead and inference latency. Additionally, base models are better suited in module completion tasks, while instruct-tuned models perform better in specification-to-RTL tasks.
ANNs-SaDE: A Machine-Learning-Based Design Automation Framework for Microwave Branch-Line Couplers
Paper ↗
Abstract
The traditional method for designing branch-line couplers involves a trial-and-error optimization process that requires multiple design iterations through electromagnetic (EM) simulations. Thus, it is extremely time consuming and labor intensive. In this paper, a novel machine-learning-based framework is proposed to tackle this issue. It integrates artificial neural networks with a self-adaptive differential evolution algorithm (ANNs-SaDE). This framework enables the self-adaptive design of various types of microwave branch-line couplers by precisely optimizing essential electrical properties, such as coupling factor, isolation, and phase difference between output ports. The effectiveness of the ANNs-SaDE framework is demonstrated by the designs of folded single-stage branch-line couplers and multi-stage wideband branch-line couplers.
VFlow: Discovering Optimal Agentic Workflows for Verilog Generation
Paper ↗
Abstract
Hardware design automation faces challenges in generating high-quality Verilog code efficiently. This paper introduces VFlow, an automated framework that optimizes agentic workflows for Verilog code generation. Unlike traditional approaches relying on fixed prompts or manually designed flows, VFlow treats workflow discovery as a search over graph-structured LLM invocation sequences. It introduces a multi-population cooperative evolution (CEPE-MCTS) algorithm that balances multiple hardware objectives -- functional correctness, area, power, timing and token cost -- while sharing successful patterns and avoiding repeated failures. Integrated multi-level verification ensures syntactic correctness, functional behavior, and synthesizability. Experiments on VerilogEval and RTLLM2.0 show VFlow improves pass@1 by 20--30\% over prompting baselines and closely matches designer-level area/power. Remarkably, VFlow enables small LLMs to outperform larger models with up to 10.9$\times$ ROI, offering a cost-effective solution for RTL design. This work paves the way for intelligent, automated hardware development, advancing LLM applications in EDA.
Concorde: Fast and Accurate CPU Performance Modeling with Compositional Analytical-ML Fusion
Paper ↗
Abstract
Cycle-level simulators such as gem5 are widely used in microarchitecture design, but they are prohibitively slow for large-scale design space explorations. We present Concorde, a new methodology for learning fast and accurate performance models of microarchitectures. Unlike existing simulators and learning approaches that emulate each instruction, Concorde predicts the behavior of a program based on compact performance distributions that capture the impact of different microarchitectural components. It derives these performance distributions using simple analytical models that estimate bounds on performance induced by each microarchitectural component, providing a simple yet rich representation of a program's performance characteristics across a large space of microarchitectural parameters. Experiments show that Concorde is more than five orders of magnitude faster than a reference cycle-level simulator, with about 2% average Cycles-Per-Instruction (CPI) prediction error across a range of SPEC, open-source, and proprietary benchmarks. This enables rapid design-space exploration and performance sensitivity analyses that are currently infeasible, e.g., in about an hour, we conducted a first-of-its-kind fine-grained performance attribution to different microarchitectural components across a diverse set of programs, requiring nearly 150 million CPI evaluations.
Late Breaking Results: Breaking Symmetry- Unconventional Placement of Analog Circuits using Multi-Level Multi-Agent Reinforcement Learning
Paper ↗
Abstract
Layout-dependent effects (LDEs) significantly impact analog circuit performance. Traditionally, designers have relied on symmetric placement of circuit components to mitigate variations caused by LDEs. However, due to non-linear nature of these effects, conventional methods often fall short. We propose an objective-driven, multi-level, multi-agent Q-learning framework to explore unconventional design space of analog layout, opening new avenues for optimizing analog circuit performance. Our approach achieves better variation performance than the state-of-the-art layout techniques. Notably, this is the first application of multi-agent RL in analog layout automation. The proposed approach is compared with non-ML approach based on simulated annealing.
NLS: Natural-Level Synthesis for Hardware Implementation Through GenAI
Paper ↗
Abstract
This paper introduces Natural-Level Synthesis, an innovative approach for generating hardware using generative artificial intelligence on both the system level and component-level. NLS bridges a gap in current hardware development processes, where algorithm and application engineers' involvement typically ends at the requirements stage. With NLS, engineers can participate more deeply in the development, synthesis, and test stages by using Gen-AI models to convert natural language descriptions directly into Hardware Description Language code. This approach not only streamlines hardware development but also improves accessibility, fostering a collaborative workflow between hardware and algorithm engineers. We developed the NLS tool to facilitate natural language-driven HDL synthesis, enabling rapid generation of system-level HDL designs while significantly reducing development complexity. Evaluated through case studies and benchmarks using Performance, Power, and Area metrics, NLS shows its potential to enhance resource efficiency in hardware development. This work provides a extensible, efficient solution for hardware synthesis and establishes a Visual Studio Code Extension to assess Gen-AI-driven HDL generation and system integration, laying a foundation for future AI-enhanced and AI-in-the-loop Electronic Design Automation tools.
A Survey of Circuit Foundation Model: Foundation AI Models for VLSI Circuit Design and EDA
Paper ↗
Abstract
Artificial intelligence (AI)-driven electronic design automation (EDA) techniques have been extensively explored for VLSI circuit design applications. Most recently, foundation AI models for circuits have emerged as a new technology trend. Unlike traditional task-specific AI solutions, these new AI models are developed through two stages: 1) self-supervised pre-training on a large amount of unlabeled data to learn intrinsic circuit properties; and 2) efficient fine-tuning for specific downstream applications, such as early-stage design quality evaluation, circuit-related context generation, and functional verification. This new paradigm brings many advantages: model generalization, less reliance on labeled circuit data, efficient adaptation to new tasks, and unprecedented generative capability. In this paper, we propose referring to AI models developed with this new paradigm as circuit foundation models (CFMs). This paper provides a comprehensive survey of the latest progress in circuit foundation models, unprecedentedly covering over 130 relevant works. Over 90% of our introduced works were published in or after 2022, indicating that this emerging research trend has attracted wide attention in a short period. In this survey, we propose to categorize all existing circuit foundation models into two primary types: 1) encoder-based methods performing general circuit representation learning for predictive tasks; and 2) decoder-based methods leveraging large language models (LLMs) for generative tasks. For our introduced works, we cover their input modalities, model architecture, pre-training strategies, domain adaptation techniques, and downstream design applications. In addition, this paper discussed the unique properties of circuits from the data perspective. These circuit properties have motivated many works in this domain and differentiated them from general AI techniques.
A Self-Supervised Learning of a Foundation Model for Analog Layout Design Automation
Paper ↗
Abstract
We propose a UNet-based foundation model and its self-supervised learning method to address two key challenges: 1) lack of qualified annotated analog layout data, and 2) excessive variety in analog layout design tasks. For self-supervised learning, we propose random patch sampling and random masking techniques automatically to obtain enough training data from a small unannotated layout dataset. The obtained data are greatly augmented, less biased, equally sized, and contain enough information for excessive varieties of qualified layout patterns. By pre-training with the obtained data, the proposed foundation model can learn implicit general knowledge on layout patterns so that it can be fine-tuned for various downstream layout tasks with small task-specific datasets. Fine-tuning provides an efficient and consolidated methodology for diverse downstream tasks, reducing the enormous human effort to develop a model per task separately. In experiments, the foundation model was pre-trained using 324,000 samples obtained from 6 silicon-proved manually designed analog circuits, then it was fine-tuned for the five example downstream tasks: generating contacts, vias, dummy fingers, N-wells, and metal routings. The fine-tuned models successfully performed these tasks for more than one thousand unseen layout inputs, generating DRC/LVS-clean layouts for 96.6% of samples. Compared with training the model from scratch for the metal routing task, fine-tuning required only 1/8 of the data to achieve the same dice score of 0.95. With the same data, fine-tuning achieved a 90% lower validation loss and a 40% higher benchmark score than training from scratch.
RocketPPA: Code-Level Power, Performance, and Area Prediction via LLM and Mixture of Experts
Paper ↗
Abstract
This paper presents RocketPPA, a novel ultra-fast power, performance (delay), and area (PPA) estimator operating directly at the code-level abstraction using HDL code as input. The key technical innovation is its LLM-based regression model, which uniquely integrates a large language model (LLM) with a mixture-of-experts (MoE) architecture composed of multilayer perceptrons (MLPs). The LLM interprets the input HDL code and then utilizes its final hidden-layer representations to predict PPA metrics. Low-rank adaptation (LoRA) is used for parameter-efficient fine-tuning to enable efficient LLM training. Furthermore, the work includes the development of an LLM-based HDL code repair framework to generate a large and synthesizable training dataset. Experimental results on the VerilogEval benchmark demonstrate that RocketPPA achieves significant improvements in the accuracy of PPA estimation compared to previous state-of-the-art methods like Llama3-MetRex-8B. Specifically, at a 10% relative error threshold, RocketPPA enhances the pass rate for area prediction by 13.6%, delay by 9.4%, and power by 14.7%. At a 20% threshold, the improvements are 9.6% for area, 10.8% for delay, and 18.5% for power. Moreover, RocketPPA achieves a speedup of over 20x compared to MetRex and 30x over MasterRTL in processing the test set. The impact of RocketPPA is the potential to substantially accelerate the hardware design process by providing accurate PPA estimations early in the design cycle, thus avoiding the overhead of manual feature engineering and time-consuming synthesis flows.
Enhancing Finite State Machine Design Automation with Large Language Models and Prompt Engineering Techniques
Paper ↗
Abstract
Large Language Models (LLMs) have attracted considerable attention in recent years due to their remarkable compatibility with Hardware Description Language (HDL) design. In this paper, we examine the performance of three major LLMs, Claude 3 Opus, ChatGPT-4, and ChatGPT-4o, in designing finite state machines (FSMs). By utilizing the instructional content provided by HDLBits, we evaluate the stability, limitations, and potential approaches for improving the success rates of these models. Furthermore, we explore the impact of using the prompt-refining method, To-do-Oriented Prompting (TOP) Patch, on the success rate of these LLM models in various FSM design scenarios. The results show that the systematic format prompt method and the novel prompt refinement method have the potential to be applied to other domains beyond HDL design automation, considering its possible integration with other prompt engineering techniques in the future.
"Test, Build, Deploy" -- A CI/CD Framework for Open-Source Hardware Designs
Paper ↗
Abstract
Addressing TedX, Amber Huffman made an impassioned case that "none of us is as smart as all of us" and that open-source hardware is the future. A major contribution to software quality, open source and otherwise, on the software side, is the systems design methodology of Continuous Integration and Delivery (CI/CD), which we propose to systematically bring to hardware designs and their specifications. To do so, we automatically generate specifications using specification mining, "a machine learning approach to discovering formal specifications" which dramatically impacted the ability of software engineers to achieve quality, verification, and security. Yet applying the same techniques to hardware is non-trivial. We present a technique for generalized, continuous integration (CI) of hardware specification designs that continually deploys (CD) a hardware specification. As a proof-of-concept, we demonstrate Myrtha, a cloud-based, specification generator based on established hardware and software quality tools.
AssertionForge: Enhancing Formal Verification Assertion Generation with Structured Representation of Specifications and RTL
Paper ↗
Abstract
Generating SystemVerilog Assertions (SVAs) from natural language specifications remains a major challenge in formal verification (FV) due to the inherent ambiguity and incompleteness of specifications. Existing LLM-based approaches, such as AssertLLM, focus on extracting information solely from specification documents, often failing to capture essential internal signal interactions and design details present in the RTL code, leading to incomplete or incorrect assertions. We propose a novel approach that constructs a Knowledge Graph (KG) from both specifications and RTL, using a hardware-specific schema with domain-specific entity and relation types. We create an initial KG from the specification and then systematically fuse it with information extracted from the RTL code, resulting in a unified, comprehensive KG. This combined representation enables a more thorough understanding of the design and allows for a multi-resolution context synthesis process which is designed to extract diverse verification contexts from the KG. Experiments on four designs demonstrate that our method significantly enhances SVA quality over prior methods. This structured representation not only improves FV but also paves the way for future research in tasks like code generation and design understanding.
LIMCA: LLM for Automating Analog In-Memory Computing Architecture Design Exploration
Paper ↗
Abstract
Resistive crossbars enabling analog In-Memory Computing (IMC) have emerged as a promising architecture for Deep Neural Network (DNN) acceleration, offering high memory bandwidth and in-situ computation. However, the manual, knowledge-intensive design process and the lack of high-quality circuit netlists have significantly constrained design space exploration and optimization to behavioral system-level tools. In this work, we introduce LIMCA, a novel fine-tune-free Large Language Model (LLM)-driven framework for automating the design and evaluation of IMC crossbar architectures. Unlike traditional approaches, LIMCA employs a No-Human-In-Loop (NHIL) automated pipeline to generate and validate circuit netlists for SPICE simulations, eliminating manual intervention. LIMCA systematically explores the IMC design space by leveraging a structured dataset and LLM-based performance evaluation. Our experimental results on MNIST classification demonstrate that LIMCA successfully generates crossbar designs achieving $\geq$96% accuracy while maintaining a power consumption $\leq$3W, making this the first work in LLM-assisted IMC design space exploration. Compared to existing frameworks, LIMCA provides an automated, scalable, and hardware-aware solution, reducing design exploration time while ensuring user-constrained performance trade-offs.
Can Reasoning Models Reason about Hardware? An Agentic HLS Perspective
Paper ↗
Abstract
Recent Large Language Models (LLMs) such as OpenAI o3-mini and DeepSeek-R1 use enhanced reasoning through Chain-of-Thought (CoT). Their potential in hardware design, which relies on expert-driven iterative optimization, remains unexplored. This paper investigates whether reasoning LLMs can address challenges in High-Level Synthesis (HLS) design space exploration and optimization. During HLS, engineers manually define pragmas/directives to balance performance and resource constraints. We propose an LLM-based optimization agentic framework that automatically restructures code, inserts pragmas, and identifies optimal design points via feedback from HLs tools and access to integer-linear programming (ILP) solvers. Experiments compare reasoning models against conventional LLMs on benchmarks using success rate, efficiency, and design quality (area/latency) metrics, and provide the first-ever glimpse into the CoTs produced by a powerful open-source reasoning model like DeepSeek-R1.
VeriMind: Agentic LLM for Automated Verilog Generation with a Novel Evaluation Metric
Paper ↗
Abstract
Designing Verilog modules requires meticulous attention to correctness, efficiency, and adherence to design specifications. However, manually writing Verilog code remains a complex and time-consuming task that demands both expert knowledge and iterative refinement. Leveraging recent advancements in large language models (LLMs) and their structured text generation capabilities, we propose VeriMind, an agentic LLM framework for Verilog code generation that significantly automates and optimizes the synthesis process. Unlike traditional LLM-based code generators, VeriMind employs a structured reasoning approach: given a user-provided prompt describing design requirements, the system first formulates a detailed train of thought before the final Verilog code is generated. This multi-step methodology enhances interpretability, accuracy, and adaptability in hardware design. In addition, we introduce a novel evaluation metric-pass@ARC-which combines the conventional pass@k measure with Average Refinement Cycles (ARC) to capture both success rate and the efficiency of iterative refinement. Experimental results on diverse hardware design tasks demonstrated that our approach achieved up to $8.3\%$ improvement on pass@k metric and $8.1\%$ on pass@ARC metric. These findings underscore the transformative potential of agentic LLMs in automated hardware design, RTL development, and digital system synthesis.
LLMPerf: GPU Performance Modeling meets Large Language Models
Paper ↗
Abstract
Performance modeling, a pivotal domain in program cost analysis, currently relies on manually crafted models constrained by various program and hardware limitations, especially in the intricate landscape of GPGPU. Meanwhile, Large Language Models (LLMs) have demonstrated their effectiveness in addressing diverse programming challenges. Our work establishes a connection between LLMs and performance modeling, employing the LLM as a performance estimator. Through experimental exploration with carefully designed large-scale OpenCL datasets, we highlight the potential capability as well as the main difficulties of using LLMs in handling performance modeling tasks for OpenCL device source programs. As the first study for this line of work, our LLM-based performance model achieves a mean absolute percentage error of $24.25\%$ for a large-scale generated validation set. On a set of publicly available OpenCL programs, our model achieves a mean absolute percentage error of $46.1\%$.
Towards Efficient PCSEL Design: A Fully AI-driven Approach
Paper ↗
Abstract
We present an fully AI-driven design framework for photonic crystals (PhCs), engineered to achieve high efficiency in photonic crystal surface-emitting lasers (PCSELs). By discretizing the PhC structure into a grid, where the edges of the holes are represented by the cross-sections of two-dimensional Gaussian surfaces, we achieve high-degree-of-freedom and fabrication-friendly hole design. Coupled-wave theory (CWT) generates a dataset by evaluating surface-emitting efficiency ($SEE$) and quality factor ($Q$) of PhC designs, while a multi-layered neural network (NN) learns and extracts essential features from these designs. Finally, black-box optimization (BBO) is employed to fine-tune the photonic crystal structure, enabling a fully AI-driven design process. The model achieves high prediction accuracy, with Pearson correlation coefficients of 0.780 for $SEE$ and 0.887 for the log-transformed $Q$. Additionally, we perform Shapley value analysis to identify the most important Fourier coefficients, providing insights into the factors that impact the performance of PCSEL designs. Our work accelerates the design process by over 1,000,000 times compared to traditional FDTD simulations, reducing parameter optimization from two weeks to just one second. Our work speeds up the design process and enables efficient optimization of high-performance PCSELs, driving the development of fully photonic design automation (PDA).
Enhancing Large Language Models for Hardware Verification: A Novel SystemVerilog Assertion Dataset
Paper ↗
Abstract
Hardware verification is crucial in modern SoC design, consuming around 70% of development time. SystemVerilog assertions ensure correct functionality. However, existing industrial practices rely on manual efforts for assertion generation, which becomes increasingly untenable as hardware systems become complex. Recent research shows that Large Language Models (LLMs) can automate this process. However, proprietary SOTA models like GPT-4o often generate inaccurate assertions and require expensive licenses, while smaller open-source LLMs need fine-tuning to manage HDL code complexities. To address these issues, we introduce **VERT**, an open-source dataset designed to enhance SystemVerilog assertion generation using LLMs. VERT enables researchers in academia and industry to fine-tune open-source models, outperforming larger proprietary ones in both accuracy and efficiency while ensuring data privacy through local fine-tuning and eliminating costly licenses. The dataset is curated by systematically augmenting variables from open-source HDL repositories to generate synthetic code snippets paired with corresponding assertions. Experimental results demonstrate that fine-tuned models like Deepseek Coder 6.7B and Llama 3.1 8B outperform GPT-4o, achieving up to 96.88% improvement over base models and 24.14% over GPT-4o on platforms including OpenTitan, CVA6, OpenPiton and Pulpissimo. VERT is available at https://github.com/AnandMenon12/VERT.
ResBench: Benchmarking LLM-Generated FPGA Designs with Resource Awareness
Paper ↗
Abstract
Field-Programmable Gate Arrays (FPGAs) are widely used in modern hardware design, yet writing Hardware Description Language (HDL) code for FPGA implementation remains a complex and time-consuming task. Large Language Models (LLMs) have emerged as a promising tool for HDL generation, but existing benchmarks for LLM-based code generation primarily focus on functional correctness while overlooking hardware resource usage. Furthermore, current benchmarks offer limited diversity and do not fully represent the wide range of real-world FPGA applications. To address these shortcomings, we introduce ResBench, the first resource-focused benchmark explicitly designed to distinguish between resource-optimized and inefficient LLM-generated HDL code. ResBench consists of 56 problems across 12 categories, covering applications from finite state machines to financial computing. Our open-source evaluation framework automatically tests LLMs by generating Verilog code, verifying correctness, and measuring resource usage. The experiments, which primarily analyze Lookup Table (LUT) usage, reveal significant differences among LLMs, demonstrating ResBench's capability to identify models that generate more resource-optimized FPGA designs.
Insights from Rights and Wrongs: A Large Language Model for Solving Assertion Failures in RTL Design
Paper ↗
Abstract
SystemVerilog Assertions (SVAs) are essential for verifying Register Transfer Level (RTL) designs, as they can be embedded into key functional paths to detect unintended behaviours. During simulation, assertion failures occur when the design's behaviour deviates from expectations. Solving these failures, i.e., identifying and fixing the issues causing the deviation, requires analysing complex logical and timing relationships between multiple signals. This process heavily relies on human expertise, and there is currently no automatic tool available to assist with it. Here, we present AssertSolver, an open-source Large Language Model (LLM) specifically designed for solving assertion failures. By leveraging synthetic training data and learning from error responses to challenging cases, AssertSolver achieves a bug-fixing pass@1 metric of 88.54% on our testbench, significantly outperforming OpenAI's o1-preview by up to 11.97%. We release our model and testbench for public access to encourage further research: https://github.com/SEU-ACAL/reproduce-AssertSolver-DAC-25.
Review of Machine Learning for Micro-Electronic Design Verification
Paper ↗
Abstract
Microelectronic design verification remains a critical bottleneck in device development, traditionally mitigated by expanding verification teams and computational resources. Since the late 1990s, machine learning (ML) has been proposed to enhance verification efficiency, yet many techniques have not achieved mainstream adoption. This review, from the perspective of verification and ML practitioners, examines the application of ML in dynamic-based techniques for functional verification of microelectronic designs, and provides a starting point for those new to this interdisciplinary field. Historical trends, techniques, ML types, and evaluation baselines are analysed to understand why previous research has not been widely adopted in industry. The review highlights the application of ML, the techniques used and critically discusses their limitations and successes. Although there is a wealth of promising research, real-world adoption is hindered by challenges in comparing techniques, identifying suitable applications, and the expertise required for implementation. This review proposes that the field can progress through the creation and use of open datasets, common benchmarks, and verification targets. By establishing open evaluation criteria, industry can guide future research. Parallels with ML in software verification suggest potential for collaboration. Additionally, greater use of open-source designs and verification environments can allow more researchers from outside the hardware verification discipline to contribute to the challenge of verifying microelectronic designs.
Are LLMs Ready for Practical Adoption for Assertion Generation?
Paper ↗
Abstract
Assertions have been the de facto collateral for simulation-based and formal verification of hardware designs for over a decade. The quality of hardware verification, i.e., detection and diagnosis of corner-case design bugs, is critically dependent on the quality of the assertions. With the onset of generative AI such as Transformers and Large-Language Models (LLMs), there has been a renewed interest in developing novel, effective, and scalable techniques of generating functional and security assertions from design source code. While there have been recent works that use commercial-of-the-shelf (COTS) LLMs for assertion generation, there is no comprehensive study in quantifying the effectiveness of LLMs in generating syntactically and semantically correct assertions. In this paper, we first discuss AssertionBench from our prior work, a comprehensive set of designs and assertions to quantify the goodness of a broad spectrum of COTS LLMs for the task of assertion generations from hardware design source code. Our key insight was that COTS LLMs are not yet ready for prime-time adoption for assertion generation as they generate a considerable fraction of syntactically and semantically incorrect assertions. Motivated by the insight, we propose AssertionLLM, a first of its kind LLM model, specifically fine-tuned for assertion generation. Our initial experimental results show that AssertionLLM considerably improves the semantic and syntactic correctness of the generated assertions over COTS LLMs.
Transfer Learning Assisted Fast Design Migration Over Technology Nodes: A Study on Transformer Matching Network
Paper ↗
Abstract
In this study, we introduce an innovative methodology for the design of mm-Wave passive networks that leverages knowledge transfer from a pre-trained synthesis neural network (NN) model in one technology node and achieves swift and reliable design adaptation across different integrated circuit (IC) technologies, operating frequencies, and metal options. We prove this concept through simulation-based demonstrations focusing on the training and comparison of the coefficient of determination (R2) of synthesis NNs for 1:1 on-chip transformers in GlobalFoundries(GF) 22nm FDX+ (target domain), with and without transfer learning from a model trained in GF 45nm SOI (source domain). In the experiments, we explore varying target data densities of 0.5%, 1%, 5%, and 100% with a complete dataset of 0.33 million in GF 22FDX+, and for comparative analysis, apply source data densities of 25%, 50%, 75%, and 100% with a complete dataset of 2.5 million in GF 45SOI. With the source data only at 30GHz, the experiments span target data from two metal options in GF 22FDX+ at frequencies of 30 and 39 GHz. The results prove that the transfer learning with the source domain knowledge (GF 45SOI) can both accelerate the training process in the target domain (GF 22FDX+) and improve the R2 values compared to models without knowledge transfer. Furthermore, it is observed that a model trained with just 5% of target data and augmented by transfer learning achieves R2 values superior to a model trained with 20% of the data without transfer, validating the advantage seen from 1% to 5% data density. This demonstrates a notable reduction of 4X in the necessary dataset size highlighting the efficacy of utilizing transfer learning to mm-Wave passive network design. The PyTorch learning and testing code is publicly available at https://github.com/ChenhaoChu/RFIC-TL.
DeepCircuitX: A Comprehensive Repository-Level Dataset for RTL Code Understanding, Generation, and PPA Analysis
Paper ↗
Abstract
This paper introduces DeepCircuitX, a comprehensive repository-level dataset designed to advance RTL (Register Transfer Level) code understanding, generation, and power-performance-area (PPA) analysis. Unlike existing datasets that are limited to either file-level RTL code or physical layout data, DeepCircuitX provides a holistic, multilevel resource that spans repository, file, module, and block-level RTL code. This structure enables more nuanced training and evaluation of large language models (LLMs) for RTL-specific tasks. DeepCircuitX is enriched with Chain of Thought (CoT) annotations, offering detailed descriptions of functionality and structure at multiple levels. These annotations enhance its utility for a wide range of tasks, including RTL code understanding, generation, and completion. Additionally, the dataset includes synthesized netlists and PPA metrics, facilitating early-stage design exploration and enabling accurate PPA prediction directly from RTL code. We demonstrate the dataset's effectiveness on various LLMs finetuned with our dataset and confirm the quality with human evaluations. Our results highlight DeepCircuitX as a critical resource for advancing RTL-focused machine learning applications in hardware design automation.Our data is available at https://zeju.gitbook.io/lcm-team.
The Art of Beating the Odds with Predictor-Guided Random Design Space Exploration
Paper ↗
Abstract
This work introduces an innovative method for improving combinational digital circuits through random exploration in MIG-based synthesis. High-quality circuits are crucial for performance, power, and cost, making this a critical area of active research. Our approach incorporates next-state prediction and iterative selection, significantly accelerating the synthesis process. This novel method achieves up to 14x synthesis speedup and up to 20.94% better MIG minimization on the EPFL Combinational Benchmark Suite compared to state-of-the-art techniques. We further explore various predictor models and show that increased prediction accuracy does not guarantee an equivalent increase in synthesis quality of results or speedup, observing that randomness remains a desirable factor.
Marco: Configurable Graph-Based Task Solving and Multi-AI Agents Framework for Hardware Design
Paper ↗
Abstract
Hardware design presents numerous challenges stemming from its complexity and advancing technologies. These challenges result in longer turn-around-time (TAT) for optimizing performance, power, area, and cost (PPAC) during synthesis, verification, physical design, and reliability loops. Large Language Models (LLMs) have shown remarkable capacity to comprehend and generate natural language at a massive scale, leading to many potential applications and benefits across various domains. Successful LLM-based agents for hardware design can drastically reduce TAT, leading to faster product cycles, lower costs, improved design reliability and reduced risk of costly errors. In this work, we propose a unified framework, Marco, that integrates configurable graph-based task solving with multi-modality and multi-AI agents for chip design by leveraging the natural language and reasoning abilities with collaborative toolkits. Lastly, we demonstrate promising performance, productivity, and efficiency of LLM agents by leveraging the Marco framework on layout optimization, Verilog/design rule checker (DRC) coding, and timing analysis tasks.
The Power of Graph Signal Processing for Chip Placement Acceleration
Paper ↗
Abstract
Placement is a critical task with high computation complexity in VLSI physical design. Modern analytical placers formulate the placement objective as a nonlinear optimization task, which suffers a long iteration time. To accelerate and enhance the placement process, recent studies have turned to deep learning-based approaches, particularly leveraging graph convolution networks (GCNs). However, learning-based placers require time- and data-consuming model training due to the complexity of circuit placement that involves large-scale cells and design-specific graph statistics. This paper proposes GiFt, a parameter-free technique for accelerating placement, rooted in graph signal processing. GiFt excels at capturing multi-resolution smooth signals of circuit graphs to generate optimized placement solutions without the need for time-consuming model training, and meanwhile significantly reduces the number of iterations required by analytical placers. Experimental results show that GiFt significantly improving placement efficiency, while achieving competitive or superior performance compared to state-of-the-art placers. In particular, compared to DREAMPlace, the recently proposed GPU-accelerated analytical placer, GF-Placer improves total runtime over 45%.
Optimizing Coverage-Driven Verification Using Machine Learning and PyUVM: A Novel Approach
Paper ↗
Abstract
The escalating complexity of System-on-Chip (SoC) designs has created a bottleneck in verification, with traditional techniques struggling to achieve complete coverage. Existing techniques, such as Constrained Random Verification (CRV) and coverage-driven methodologies, rely on time-consuming and redundant simulation regression, leading to higher verification costs and longer time-to-market due to the manual effort required to adjust constraints and drive the stimuli to achieve coverage objectives. To address this challenge, we propose a novel methodology that leverages supervised Machine Learning (ML) to optimize simulation regressions, resulting in reduced simulation run-time and the number of test simulations required to achieve target coverage goals. We also investigate and compare the effectiveness of various supervised learning algorithms from scikit-learn. Our results demonstrate that these algorithms can achieve at least 99% coverage regain with significantly reduced simulation cycles. We utilize Python Universal Verification Methodology (PyUVM) over SystemVerilog-Universal Verification Methodology (SV-UVM) for testbench creation, enabling simpler constructs using Python and facilitating the reuse of existing ML libraries. Our methodology is applied to three diverse designs, and our results show that it can significantly reduce verification costs, manual efforts, and time-to-market, while enhancing verification productivity and completeness, by automating the testbench update process and achieving target coverage goals.
Machine Learning Framework for Early Power, Performance, and Area Estimation of RTL
Paper ↗
Abstract
A critical stage in the evolving landscape of VLSI design is the design phase that is transformed into register-transfer level (RTL), which specifies system functionality through hardware description languages like Verilog. Generally, evaluating the quality of an RTL design demands full synthesis via electronic design automation (EDA) tool is time-consuming process that is not well-suited to rapid design iteration and optimization. Although recent breakthroughs in machine Learning (ML) have brought early prediction models, these methods usually do not provide robust and generalizable solutions with respect to a wide range of RTL designs. This paper proposes a pre-synthesis framework that makes early estimation of power, performance and area (PPA) metrics directly from the hardware description language (HDL) code making direct use of library files instead of toggle files. The proposed framework introduces a bit-level representation referred to as the simple operator graph (SOG), which uses single-bit operators to generate a generalized and flexible structure that closely mirrors the characteristics of post synthesis design. The proposed model bridges the RTL and post-synthesis design, which will help in precisely predicting key metrics. The proposed tree-based ML framework shows superior predictive performance PPA estimation. Validation is carried out on 147 distinct RTL designs. The proposed model with 147 different designs shows accuracy of 98%, 98%, and 90% for WNS, TNS and power, respectively, indicates significant accuracy improvements relative to state-of-the-art methods.
DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model
Paper ↗
Abstract
Recent advancements in large language models (LLMs) have shown significant potential for automating hardware description language (HDL) code generation from high-level natural language instructions. While fine-tuning has improved LLMs' performance in hardware design tasks, prior efforts have largely focused on Verilog generation, overlooking the equally critical task of Verilog understanding. Furthermore, existing models suffer from weak alignment between natural language descriptions and Verilog code, hindering the generation of high-quality, synthesizable designs. To address these issues, we present DeepRTL, a unified representation model that excels in both Verilog understanding and generation. Based on CodeT5+, DeepRTL is fine-tuned on a comprehensive dataset that aligns Verilog code with rich, multi-level natural language descriptions. We also introduce the first benchmark for Verilog understanding and take the initiative to apply embedding similarity and GPT Score to evaluate the models' understanding capabilities. These metrics capture semantic similarity more accurately than traditional methods like BLEU and ROUGE, which are limited to surface-level n-gram overlaps. By adapting curriculum learning to train DeepRTL, we enable it to significantly outperform GPT-4 in Verilog understanding tasks, while achieving performance on par with OpenAI's o1-preview model in Verilog generation tasks.
Exploring Code Language Models for Automated HLS-based Hardware Generation: Benchmark, Infrastructure and Analysis
Paper ↗
Abstract
Recent advances in code generation have illuminated the potential of employing large language models (LLMs) for general-purpose programming languages such as Python and C++, opening new opportunities for automating software development and enhancing programmer productivity. The potential of LLMs in software programming has sparked significant interest in exploring automated hardware generation and automation. Although preliminary endeavors have been made to adopt LLMs in generating hardware description languages (HDLs), several challenges persist in this direction. First, the volume of available HDL training data is substantially smaller compared to that for software programming languages. Second, the pre-trained LLMs, mainly tailored for software code, tend to produce HDL designs that are more error-prone. Third, the generation of HDL requires a significantly higher number of tokens compared to software programming, leading to inefficiencies in cost and energy consumption. To tackle these challenges, this paper explores leveraging LLMs to generate High-Level Synthesis (HLS)-based hardware design. Although code generation for domain-specific programming languages is not new in the literature, we aim to provide experimental results, insights, benchmarks, and evaluation infrastructure to investigate the suitability of HLS over low-level HDLs for LLM-assisted hardware design generation. To achieve this, we first finetune pre-trained models for HLS-based hardware generation, using a collected dataset with text prompts and corresponding reference HLS designs. An LLM-assisted framework is then proposed to automate end-to-end hardware code generation, which also investigates the impact of chain-of-thought and feedback loops promoting techniques on HLS-design generation. Limited by the timeframe of this research, we plan to evaluate more advanced reasoning models in the future.
Architect of the Bits World: Masked Autoregressive Modeling for Circuit Generation Guided by Truth Table
Paper ↗
Abstract
Logic synthesis, a critical stage in electronic design automation (EDA), optimizes gate-level circuits to minimize power consumption and area occupancy in integrated circuits (ICs). Traditional logic synthesis tools rely on human-designed heuristics, often yielding suboptimal results. Although differentiable architecture search (DAS) has shown promise in generating circuits from truth tables, it faces challenges such as high computational complexity, convergence to local optima, and extensive hyperparameter tuning. Consequently, we propose a novel approach integrating conditional generative models with DAS for circuit generation. Our approach first introduces CircuitVQ, a circuit tokenizer trained based on our Circuit AutoEncoder We then develop CircuitAR, a masked autoregressive model leveraging CircuitVQ as the tokenizer. CircuitAR can generate preliminary circuit structures from truth tables, which guide DAS in producing functionally equivalent circuits. Notably, we observe the scalability and emergent capability in generating complex circuit structures of our CircuitAR models. Extensive experiments also show the superior performance of our method. This research bridges the gap between probabilistic generative models and precise circuit generation, offering a robust solution for logic synthesis.
Circuit Representation Learning with Masked Gate Modeling and Verilog-AIG Alignment
Paper ↗
Abstract
Understanding the structure and function of circuits is crucial for electronic design automation (EDA). Circuits can be formulated as And-Inverter graphs (AIGs), enabling efficient implementation of representation learning through graph neural networks (GNNs). Masked modeling paradigms have been proven effective in graph representation learning. However, masking augmentation to original circuits will destroy their logical equivalence, which is unsuitable for circuit representation learning. Moreover, existing masked modeling paradigms often prioritize structural information at the expense of abstract information such as circuit function. To address these limitations, we introduce MGVGA, a novel constrained masked modeling paradigm incorporating masked gate modeling (MGM) and Verilog-AIG alignment (VGA). Specifically, MGM preserves logical equivalence by masking gates in the latent space rather than in the original circuits, subsequently reconstructing the attributes of these masked gates. Meanwhile, large language models (LLMs) have demonstrated an excellent understanding of the Verilog code functionality. Building upon this capability, VGA performs masking operations on original circuits and reconstructs masked gates under the constraints of equivalent Verilog codes, enabling GNNs to learn circuit functions from LLMs. We evaluate MGVGA on various logic synthesis tasks for EDA and show the superior performance of MGVGA compared to previous state-of-the-art methods. Our code is available at https://github.com/wuhy68/MGVGA.
Ramp Up NTT in Record Time using GPU-Accelerated Algorithms and LLM-based Code Generation
Paper ↗
Abstract
Homomorphic encryption (HE) is a core building block in privacy-preserving machine learning (PPML), but HE is also widely known as its efficiency bottleneck. Therefore, many GPU-accelerated cryptographic schemes have been proposed to improve the performance of HE. However, these methods often require complex modifications tailored to specific algorithms and are tightly coupled with specific GPU and operating systems. It is interesting to ask how to generally offer more practical GPU-accelerated cryptographic algorithm implementations. Given the powerful code generation capabilities of large language models (LLMs), we aim to explore their potential to automatically generate practical GPU-friendly algorithm code using CPU-friendly code. In this paper, we focus on number theoretic transform (NTT) -- the core mechanism of HE. We first develop and optimize a GPU-friendly NTT (GNTT) family that exploits PyTorch's fast matrix computation and precomputation, achieving an approximately 62x speedup -- a significant boost over existing ones. Then we explore GPU-friendly code generation using various LLMs, including DeepSeek-R1, OpenAI o1 and o3-mini. We discover many interesting findings throughout the process. For instance, somewhat surprisingly, our experiments demonstrate that DeepSeek-R1 significantly outperforms OpenAI o3-mini and o1, but still cannot beat our optimized protocol. The findings provide valuable insights for turbocharging PPML and enhancing code generation capabilities of LLMs. Codes are available at: https://github.com/LMPC-Lab/GenGPUCrypto.
Ramp Up NTT in Record Time using GPU-Accelerated Algorithms and LLM-based Code Generation
Paper ↗
Abstract
Homomorphic encryption (HE) is a core building block in privacy-preserving machine learning (PPML), but HE is also widely known as its efficiency bottleneck. Therefore, many GPU-accelerated cryptographic schemes have been proposed to improve the performance of HE. However, these methods often require complex modifications tailored to specific algorithms and are tightly coupled with specific GPU and operating systems. It is interesting to ask how to generally offer more practical GPU-accelerated cryptographic algorithm implementations. Given the powerful code generation capabilities of large language models (LLMs), we aim to explore their potential to automatically generate practical GPU-friendly algorithm code using CPU-friendly code. In this paper, we focus on number theoretic transform (NTT) -- the core mechanism of HE. We first develop and optimize a GPU-friendly NTT (GNTT) family that exploits PyTorch's fast matrix computation and precomputation, achieving an approximately 62x speedup -- a significant boost over existing ones. Then we explore GPU-friendly code generation using various LLMs, including DeepSeek-R1, OpenAI o1 and o3-mini. We discover many interesting findings throughout the process. For instance, somewhat surprisingly, our experiments demonstrate that DeepSeek-R1 significantly outperforms OpenAI o3-mini and o1, but still cannot beat our optimized protocol. The findings provide valuable insights for turbocharging PPML and enhancing code generation capabilities of LLMs. Codes are available at: https://github.com/LMPC-Lab/GenGPUCrypto.
Divergent Thoughts toward One Goal: LLM-based Multi-Agent Collaboration System for Electronic Design Automation
Paper ↗
Abstract
Recently, with the development of tool-calling capabilities in large language models (LLMs), these models have demonstrated significant potential for automating electronic design automation (EDA) flows by interacting with EDA tool APIs via EDA scripts. However, considering the limited understanding of EDA tools, LLMs face challenges in practical scenarios where diverse interfaces of EDA tools exist across different platforms. Additionally, EDA flow automation often involves intricate, long-chain tool-calling processes, increasing the likelihood of errors in intermediate steps. Any errors will lead to the instability and failure of EDA flow automation. To address these challenges, we introduce EDAid, a multi-agent collaboration system where multiple agents harboring divergent thoughts converge towards a common goal, ensuring reliable and successful EDA flow automation. Specifically, each agent is controlled by ChipLlama models, which are expert LLMs fine-tuned for EDA flow automation. Our experiments demonstrate the state-of-the-art (SOTA) performance of our ChipLlama models and validate the effectiveness of our EDAid in the automation of complex EDA flows, showcasing superior performance compared to single-agent systems.
LintLLM: An Open-Source Verilog Linting Framework Based on Large Language Models
Paper ↗
Abstract
Code Linting tools are vital for detecting potential defects in Verilog code. However, the limitations of traditional Linting tools are evident in frequent false positives and redundant defect reports. Recent advancements in large language models (LLM) have introduced new possibilities in this area. In this paper, we propose LintLLM, an open-source Linting framework that utilizes LLMs to detect defects in Verilog code via Prompt of Logic-Tree and Defect Tracker. Furthermore, we create an open-source benchmark using the mutation-based defect injection technique to evaluate LLM's ability in detecting Verilog defects. Experimental results show that o1-mini improves the correct rate by 18.89\% and reduces the false-positive rate by 15.56\% compared with the best-performing EDA tool. Simultaneously, LintLLM operates at less than one-tenth of the cost of commercial EDA tools. This study demonstrates the potential of LLM as an efficient and cost-effective Linting tool for hardware design. The benchmark and experimental results are open-source at URL: https://github.com/fangzhigang32/Static-Verilog-Analysis
Lorecast: Layout-Aware Performance and Power Forecasting from Natural Language
Paper ↗
Abstract
In chip design planning, obtaining reliable performance and power forecasts for various design options is of critical importance. Traditionally, this involves using system-level models, which often lack accuracy, or trial synthesis, which is both labor-intensive and time-consuming. We introduce a new methodology, called Lorecast, which accepts English prompts as input to rapidly generate layout-aware performance and power estimates. This approach bypasses the need for HDL code development and synthesis, making it both fast and user-friendly. Experimental results demonstrate that Lorecast achieves accuracy within a few percent of error compared to post-layout analysis, while significantly reducing turnaround time.
KernelBench: Can LLMs Write Efficient GPU Kernels?
Paper ↗
Abstract
Efficient GPU kernels are crucial for building performant machine learning architectures, but writing them is a time-consuming challenge that requires significant expertise; therefore, we explore using language models (LMs) to automate kernel generation. We introduce KernelBench, an open-source framework for evaluating LMs' ability to write fast and correct kernels on a suite of 250 carefully selected PyTorch ML workloads. KernelBench represents a real-world engineering environment and making progress on the introduced benchmark directly translates to faster practical kernels. We introduce a new evaluation metric fast_p, which measures the percentage of generated kernels that are functionally correct and offer a speedup greater than an adjustable threshold p over baseline. Our experiments across various state-of-the-art models and test-time methods show that frontier reasoning models perform the best out of the box but still fall short overall, matching the PyTorch baseline in less than 20% of the cases. While we show that results can improve by leveraging execution and profiling feedback during iterative refinement, KernelBench remains a challenging benchmark, with its difficulty increasing as we raise speedup threshold p.
Open-Source AI-Powered Optimization in Scalene: Advancing Python Performance Profiling with DeepSeek-R1 and LLaMA 3.2
Paper ↗
Abstract
Python's flexibility and ease of use come at the cost of performance inefficiencies, requiring developers to rely on profilers to optimize execution. SCALENE, a high-performance CPU, GPU, and memory profiler, provides fine-grained insights into Python applications while running significantly faster than traditional profilers. Originally, SCALENE integrated OpenAI's API to generate AI-powered optimization suggestions, but its reliance on a proprietary API limited accessibility. This study explores the feasibility of using opensource large language models (LLMs), such as DeepSeek-R1 and Llama 3.2, to generate optimization recommendations within SCALENE. Our evaluation reveals that DeepSeek-R1 provides effective code optimizations comparable to proprietary models. We integrate DeepSeek-R1 into SCALENE to automatically analyze performance bottlenecks and suggest improvements, enhancing SCALENE's utility while maintaining its open-source nature. This study demonstrates that open-source LLMs can be viable alternatives for AI-driven code optimization, paving the way for more accessible and cost-effective performance analysis tools.
DICE: Device-level Integrated Circuits Encoder with Graph Contrastive Pretraining
Paper ↗
Abstract
Pretraining models with unsupervised graph representation learning has led to significant advancements in domains such as social network analysis, molecular design, and electronic design automation (EDA). However, prior work in EDA has mainly focused on pretraining models for digital circuits, overlooking analog and mixed-signal circuits. To bridge this gap, we introduce DICE, a Device-level Integrated Circuits Encoder, which is the first graph neural network (GNN) pretrained via self-supervised learning specifically tailored for graph-level prediction tasks in both analog and digital circuits. DICE adopts a simulation-free pretraining approach based on graph contrastive learning, leveraging two novel graph augmentation techniques. Experimental results demonstrate substantial performance improvements across three downstream tasks, highlighting the effectiveness of DICE for both analog and digital circuits. The code is available at github.com/brianlsy98/DICE.
CIRCUIT: A Benchmark for Circuit Interpretation and Reasoning Capabilities of LLMs
Paper ↗
Abstract
The role of Large Language Models (LLMs) has not been extensively explored in analog circuit design, which could benefit from a reasoning-based approach that transcends traditional optimization techniques. In particular, despite their growing relevance, there are no benchmarks to assess LLMs' reasoning capability about circuits. Therefore, we created the CIRCUIT dataset consisting of 510 question-answer pairs spanning various levels of analog-circuit-related subjects. The best-performing model on our dataset, GPT-4o, achieves 48.04% accuracy when evaluated on the final numerical answer. To evaluate the robustness of LLMs on our dataset, we introduced a unique feature that enables unit-test-like evaluation by grouping questions into unit tests. In this case, GPT-4o can only pass 27.45% of the unit tests, highlighting that the most advanced LLMs still struggle with understanding circuits, which requires multi-level reasoning, particularly when involving circuit topologies. This circuit-specific benchmark highlights LLMs' limitations, offering valuable insights for advancing their application in analog integrated circuit design.
CIRCUIT: A Benchmark for Circuit Interpretation and Reasoning Capabilities of LLMs
Paper ↗
Abstract
The role of Large Language Models (LLMs) has not been extensively explored in analog circuit design, which could benefit from a reasoning-based approach that transcends traditional optimization techniques. In particular, despite their growing relevance, there are no benchmarks to assess LLMs' reasoning capability about circuits. Therefore, we created the CIRCUIT dataset consisting of 510 question-answer pairs spanning various levels of analog-circuit-related subjects. The best-performing model on our dataset, GPT-4o, achieves 48.04% accuracy when evaluated on the final numerical answer. To evaluate the robustness of LLMs on our dataset, we introduced a unique feature that enables unit-test-like evaluation by grouping questions into unit tests. In this case, GPT-4o can only pass 27.45% of the unit tests, highlighting that the most advanced LLMs still struggle with understanding circuits, which requires multi-level reasoning, particularly when involving circuit topologies. This circuit-specific benchmark highlights LLMs' limitations, offering valuable insights for advancing their application in analog integrated circuit design.
Estimating Voltage Drop: Models, Features and Data Representation Towards a Neural Surrogate
Paper ↗
Abstract
Accurate estimation of voltage drop (IR drop) in modern Application-Specific Integrated Circuits (ASICs) is highly time and resource demanding, due to the growing complexity and the transistor density in recent technology nodes. To mitigate this challenge, we investigate how Machine Learning (ML) techniques, including Extreme Gradient Boosting (XGBoost), Convolutional Neural Network (CNN), and Graph Neural Network (GNN) can aid in reducing the computational effort and implicitly the time required to estimate the IR drop in Integrated Circuits (ICs). Traditional methods, including commercial tools, require considerable time to produce accurate approximations, especially for complicated designs with numerous transistors. ML algorithms, on the other hand, are explored as an alternative solution to offer quick and precise IR drop estimation, but in considerably less time. Our approach leverages ASICs' electrical, timing, and physical to train ML models, ensuring adaptability across diverse designs with minimal adjustments. Experimental results underscore the superiority of ML models over commercial tools, greatly enhancing prediction speed. Particularly, GNNs exhibit promising performance with minimal prediction errors in voltage drop estimation. The incorporation of GNNs marks a groundbreaking advancement in accurate IR drop prediction. This study illustrates the effectiveness of ML algorithms in precisely estimating IR drop and optimizing ASIC sign-off. Utilizing ML models leads to expedited predictions, reducing calculation time and improving energy efficiency, thereby reducing environmental impact through optimized power circuits.
Deep Learning-Optimized, Fabrication Error-Tolerant Photonic Crystal Nanobeam Cavities for Scalable On-Chip Diamond Quantum Systems
Paper ↗
Abstract
Cavity-enhanced diamond color center qubits can be initialized, manipulated, entangled, and read individually with high fidelity, which makes them ideal for large-scale, modular quantum computers, quantum networks, and distributed quantum sensing systems. However, diamond's unique material properties pose significant challenges in manufacturing nanophotonic devices, leading to fabrication-induced structural imperfections and inaccuracies in defect implantation, which hinder reproducibility, degrade optical properties and compromise the spatial coupling of color centers to small mode-volume cavities. A cavity design tolerant to fabrication imperfections, such as surface roughness, sidewall slant, and non-optimal emitter positioning, can improve coupling efficiency while simplifying fabrication. To address this challenge, a deep learning-based optimization methodology is developed to enhance the fabrication error tolerance of nanophotonic devices. Convolutional neural networks (CNNs) are applied to promising designs, such as L2 and fishbone nanobeam cavities, predicting Q-factors up to one million times faster than traditional finite-difference time-domain (FDTD) simulations, enabling efficient optimization of complex, high-dimensional parameter spaces. The CNNs achieve prediction errors below 3.99% and correlation coefficients up to 0.988. Optimized structures demonstrate a 52% reduction in Q-factor degradation, achieving quality factors of 5e4 under real-world conditions and a two-fold expansion in field distribution, enabling efficient coupling of non-optimally positioned emitters. This methodology enables scalable, high-yield manufacturing of robust nanophotonic devices, including the cavity-enhanced diamond quantum systems developed in this study.
Accelerating OTA Circuit Design: Transistor Sizing Based on a Transformer Model and Precomputed Lookup Tables
Paper ↗
Abstract
Device sizing is crucial for meeting performance specifications in operational transconductance amplifiers (OTAs), and this work proposes an automated sizing framework based on a transformer model. The approach first leverages the driving-point signal flow graph (DP-SFG) to map an OTA circuit and its specifications into transformer-friendly sequential data. A specialized tokenization approach is applied to the sequential data to expedite the training of the transformer on a diverse range of OTA topologies, under multiple specifications. Under specific performance constraints, the trained transformer model is used to accurately predict DP-SFG parameters in the inference phase. The predicted DP-SFG parameters are then translated to transistor sizes using a precomputed look-up table-based approach inspired by the gm/Id methodology. In contrast to previous conventional or machine-learning-based methods, the proposed framework achieves significant improvements in both speed and computational efficiency by reducing the need for expensive SPICE simulations within the optimization loop; instead, almost all SPICE simulations are confined to the one-time training phase. The method is validated on a variety of unseen specifications, and the sizing solution demonstrates over 90% success in meeting specifications with just one SPICE simulation for validation, and 100% success with 3-5 additional SPICE simulations.
PICBench: Benchmarking LLMs for Photonic Integrated Circuits Design
Paper ↗
Abstract
While large language models (LLMs) have shown remarkable potential in automating various tasks in digital chip design, the field of Photonic Integrated Circuits (PICs)-a promising solution to advanced chip designs-remains relatively unexplored in this context. The design of PICs is time-consuming and prone to errors due to the extensive and repetitive nature of code involved in photonic chip design. In this paper, we introduce PICBench, the first benchmarking and evaluation framework specifically designed to automate PIC design generation using LLMs, where the generated output takes the form of a netlist. Our benchmark consists of dozens of meticulously crafted PIC design problems, spanning from fundamental device designs to more complex circuit-level designs. It automatically evaluates both the syntax and functionality of generated PIC designs by comparing simulation outputs with expert-written solutions, leveraging an open-source simulator. We evaluate a range of existing LLMs, while also conducting comparative tests on various prompt engineering techniques to enhance LLM performance in automated PIC design. The results reveal the challenges and potential of LLMs in the PIC design domain, offering insights into the key areas that require further research and development to optimize automation in this field. Our benchmark and evaluation code is available at https://github.com/PICDA/PICBench.
DeepCell: Self-Supervised Multiview Fusion for Circuit Representation Learning
Paper ↗
Abstract
We introduce DeepCell, a novel circuit representation learning framework that effectively integrates multiview information from both And-Inverter Graphs (AIGs) and Post-Mapping (PM) netlists. At its core, DeepCell employs a self-supervised Mask Circuit Modeling (MCM) strategy, inspired by masked language modeling, to fuse complementary circuit representations from different design stages into unified and rich embeddings. To our knowledge, DeepCell is the first framework explicitly designed for PM netlist representation learning, setting new benchmarks in both predictive accuracy and reconstruction quality. We demonstrate the practical efficacy of DeepCell by applying it to critical EDA tasks such as functional Engineering Change Orders (ECO) and technology mapping. Extensive experimental results show that DeepCell significantly surpasses state-of-the-art open-source EDA tools in efficiency and performance.
LLM-USO: Large Language Model-based Universal Sizing Optimizer
Paper ↗
Abstract
The design of analog circuits is a cornerstone of integrated circuit (IC) development, requiring the optimization of complex, interconnected sub-structures such as amplifiers, comparators, and buffers. Traditionally, this process relies heavily on expert human knowledge to refine design objectives by carefully tuning sub-components while accounting for their interdependencies. Existing methods, such as Bayesian Optimization (BO), offer a mathematically driven approach for efficiently navigating large design spaces. However, these methods fall short in two critical areas compared to human expertise: (i) they lack the semantic understanding of the sizing solution space and its direct correlation with design objectives before optimization, and (ii) they fail to reuse knowledge gained from optimizing similar sub-structures across different circuits. To overcome these limitations, we propose the Large Language Model-based Universal Sizing Optimizer (LLM-USO), which introduces a novel method for knowledge representation to encode circuit design knowledge in a structured text format. This representation enables the systematic reuse of optimization insights for circuits with similar sub-structures. LLM-USO employs a hybrid framework that integrates BO with large language models (LLMs) and a learning summary module. This approach serves to: (i) infuse domain-specific knowledge into the BO process and (ii) facilitate knowledge transfer across circuits, mirroring the cognitive strategies of expert designers. Specifically, LLM-USO constructs a knowledge summary mechanism to distill and apply design insights from one circuit to related ones. It also incorporates a knowledge summary critiquing mechanism to ensure the accuracy and quality of the summaries and employs BO-guided suggestion filtering to identify optimal design points efficiently.
DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scale
Paper ↗
Abstract
Circuit representation learning has become pivotal in electronic design automation, enabling critical tasks such as testability analysis, logic reasoning, power estimation, and SAT solving. However, existing models face significant challenges in scaling to large circuits due to limitations like over-squashing in graph neural networks and the quadratic complexity of transformer-based models. To address these issues, we introduce DeepGate4, a scalable and efficient graph transformer specifically designed for large-scale circuits. DeepGate4 incorporates several key innovations: (1) an update strategy tailored for circuit graphs, which reduce memory complexity to sub-linear and is adaptable to any graph transformer; (2) a GAT-based sparse transformer with global and local structural encodings for AIGs; and (3) an inference acceleration CUDA kernel that fully exploit the unique sparsity patterns of AIGs. Our extensive experiments on the ITC99 and EPFL benchmarks show that DeepGate4 significantly surpasses state-of-the-art methods, achieving 15.5% and 31.1% performance improvements over the next-best models. Furthermore, the Fused-DeepGate4 variant reduces runtime by 35.1% and memory usage by 46.8%, making it highly efficient for large-scale circuit analysis. These results demonstrate the potential of DeepGate4 to handle complex EDA tasks while offering superior scalability and efficiency. Code is available at https://github.com/zyzheng17/DeepGate4-ICLR-25.
Optimizing Code Runtime Performance through Context-Aware Retrieval-Augmented Generation
Paper ↗
Abstract
Optimizing software performance through automated code refinement offers a promising avenue for enhancing execution speed and efficiency. Despite recent advancements in LLMs, a significant gap remains in their ability to perform in-depth program analysis. This study introduces AUTOPATCH, an in-context learning approach designed to bridge this gap by enabling LLMs to automatically generate optimized code. Inspired by how programmers learn and apply knowledge to optimize software, AUTOPATCH incorporates three key components: (1) an analogy-driven framework to align LLM optimization with human cognitive processes, (2) a unified approach that integrates historical code examples and CFG analysis for context-aware learning, and (3) an automated pipeline for generating optimized code through in-context prompting. Experimental results demonstrate that AUTOPATCH achieves a 7.3% improvement in execution efficiency over GPT-4o across common generated executable code, highlighting its potential to advance automated program runtime optimization.
Improving Figures of Merit for Quantum Circuit Compilation
Paper ↗
Abstract
Quantum computing is an emerging technology that has seen significant software and hardware improvements in recent years. Executing a quantum program requires the compilation of its quantum circuit for a target Quantum Processing Unit (QPU). Various methods for qubit mapping, gate synthesis, and optimization of quantum circuits have been proposed and implemented in compilers. These compilers try to generate a quantum circuit that leads to the best execution quality - a criterion that is usually approximated by figures of merit such as the number of (two-qubit) gates, the circuit depth, expected fidelity, or estimated success probability. However, it is often unclear how well these figures of merit represent the actual execution quality on a QPU. In this work, we investigate the correlation between established figures of merit and actual execution quality on real machines - revealing that the correlation is weaker than anticipated and that more complex figures of merit are not necessarily more accurate. Motivated by this finding, we propose an improved figure of merit (based on a machine learning approach) that can be used to predict the expected execution quality of a quantum circuit for a chosen QPU without actually executing it. The employed machine learning model reveals the influence of various circuit features on generating high correlation scores. The proposed figure of merit demonstrates a strong correlation and outperforms all previous ones in a case study - achieving an average correlation improvement of 49%.
VRank: Enhancing Verilog Code Generation from Large Language Models via Self-Consistency
Paper ↗
Abstract
Large Language Models (LLMs) have demonstrated promising capabilities in generating Verilog code from module specifications. To improve the quality of such generated Verilog codes, previous methods require either time-consuming manual inspection or generation of multiple Verilog codes, from which the one with the highest quality is selected with manually designed testbenches. To enhance the generation efficiency while maintaining the quality of the generated codes, we propose VRank, an automatic framework that generates Verilog codes with LLMs. In our framework, multiple code candidates are generated with LLMs by leveraging their probabilistic nature. Afterwards, we group Verilog code candidates into clusters based on identical outputs when tested against the same testbench, which is also generated by LLMs. Clusters are ranked based on the consistency they show on testbench. To determine the best candidate, Chain-of-Thought is further applied to select the best candidate from the top-ranked clusters. By systematically analyzing diverse outputs of generated codes, VRank reduces errors and enhances the overall quality of the generated Verilog code. Experimental results on the VerilogEval-Human benchmark demonstrate a significant 10.5% average increase in functional correctness (passl1) across multiple LLMs, demonstrating VRank's effectiveness in improving the accuracy of automated hardware description language generation for complex design tasks.
Paradigm-Based Automatic HDL Code Generation Using LLMs
Paper ↗
Abstract
While large language models (LLMs) have demonstrated the ability to generate hardware description language (HDL) code for digital circuits, they still face the hallucination problem, which can result in the generation of incorrect HDL code or misinterpretation of specifications. In this work, we introduce a human-expert-inspired method to mitigate the hallucination of LLMs and enhance their performance in HDL code generation. We begin by constructing specialized paradigm blocks that consist of several steps designed to divide and conquer generation tasks, mirroring the design methodology of human experts. These steps include information extraction, human-like design flows, and the integration of external tools. LLMs are then instructed to classify the type of circuit in order to match it with the appropriate paradigm block and execute the block to generate the HDL codes. Additionally, we propose a two-phase workflow for multi-round generation, aimed at effectively improving the testbench pass rate of the generated HDL codes within a limited number of generation and verification rounds. Experimental results demonstrate that our method significantly enhances the functional correctness of the generated Verilog code
Application of Machine Learning Techniques for Secure Traffic in NoC-based Manycores
Paper ↗
Abstract
Like most computer systems, a manycore can also be the target of security attacks. It is essential to ensure the security of the NoC since all information travels through its channels, and any interference in the traffic of messages can reflect on the entire chip, causing communication problems. Among the possible attacks on NoC, Denial of Service (DoS) attacks are the most cited in the literature. The state of the art shows a lack of work that can detect such attacks through learning techniques. On the other hand, these techniques are widely explored in computer network security via an Intrusion Detection System (IDS). In this context, the main goal of this document is to present the progress of a work that explores an IDS technique using machine learning and temporal series for detecting DoS attacks in NoC-based manycore systems. To fulfill this goal, it is necessary to extract traffic data from a manycore NoC and execute the learning techniques in the extracted data. However, while low-level platforms offer precision and slow execution, high-level platforms offer higher speed and data incompatible with reality. Therefore, a platform is being developed using the OVP tool, which has a higher level of abstraction. To solve the low precision problem, the developed platform will have its data validated with a low-level platform.
Supervised Learning for Analog and RF Circuit Design: Benchmarks and Comparative Insights
Paper ↗
Abstract
Automating analog and radio-frequency (RF) circuit design using machine learning (ML) significantly reduces the time and effort required for parameter optimization. This study explores supervised ML-based approaches for designing circuit parameters from performance specifications across various circuit types, including homogeneous and heterogeneous designs. By evaluating diverse ML models, from neural networks like transformers to traditional methods like random forests, we identify the best-performing models for each circuit. Our results show that simpler circuits, such as low-noise amplifiers, achieve exceptional accuracy with mean relative errors as low as 0.3% due to their linear parameter-performance relationships. In contrast, complex circuits, like power amplifiers and voltage-controlled oscillators, present challenges due to their non-linear interactions and larger design spaces. For heterogeneous circuits, our approach achieves an 88% reduction in errors with increased training data, with the receiver achieving a mean relative error as low as 0.23%, showcasing the scalability and accuracy of the proposed methodology. Additionally, we provide insights into model strengths, with transformers excelling in capturing non-linear mappings and k-nearest neighbors performing robustly in moderately linear parameter spaces, especially in heterogeneous circuits with larger datasets. This work establishes a foundation for extending ML-driven design automation, enabling more efficient and scalable circuit design workflows.
A Survey of Research in Large Language Models for Electronic Design Automation
Paper ↗
Abstract
Within the rapidly evolving domain of Electronic Design Automation (EDA), Large Language Models (LLMs) have emerged as transformative technologies, offering unprecedented capabilities for optimizing and automating various aspects of electronic design. This survey provides a comprehensive exploration of LLM applications in EDA, focusing on advancements in model architectures, the implications of varying model sizes, and innovative customization techniques that enable tailored analytical insights. By examining the intersection of LLM capabilities and EDA requirements, the paper highlights the significant impact these models have on extracting nuanced understandings from complex datasets. Furthermore, it addresses the challenges and opportunities in integrating LLMs into EDA workflows, paving the way for future research and application in this dynamic field. Through this detailed analysis, the survey aims to offer valuable insights to professionals in the EDA industry, AI researchers, and anyone interested in the convergence of advanced AI technologies and electronic design.
CuAsmRL: Optimizing GPU SASS Schedules via Deep Reinforcement Learning
Paper ↗
Abstract
Large language models (LLMs) are remarked by their substantial computational requirements. To mitigate the cost, researchers develop specialized CUDA kernels, which often fuse several tensor operations to maximize the utilization of GPUs as much as possible. However, those specialized kernels may still leave performance on the table as CUDA assembly experts show that manual optimization of GPU SASS schedules can lead to better performance, and trial-and-error is largely employed to manually find the best GPU SASS schedules. In this work, we employ an automatic approach to optimize GPU SASS schedules, which thus can be integrated into existing compiler frameworks. The key to automatic optimization is training an RL agent to mimic how human experts perform manual scheduling. To this end, we formulate an assembly game, where RL agents can play to find the best GPU SASS schedules. The assembly game starts from a \textit{-O3} optimized SASS schedule, and the RL agents can iteratively apply actions to mutate the current schedules. Positive rewards are generated if the mutated schedules get higher throughput by executing on GPUs. Experiments show that CuAsmRL can further improve the performance of existing specialized CUDA kernels transparently by up to $26\%$, and on average $9\%$. Moreover, it is used as a tool to reveal potential optimization moves learned automatically.
E2ESlack: An End-to-End Graph-Based Framework for Pre-Routing Slack Prediction
Paper ↗
Abstract
Pre-routing slack prediction remains a critical area of research in Electronic Design Automation (EDA). Despite numerous machine learning-based approaches targeting this task, there is still a lack of a truly end-to-end framework that engineers can use to obtain TNS/WNS metrics from raw circuit data at the placement stage. Existing works have demonstrated effectiveness in Arrival Time (AT) prediction but lack a mechanism for Required Arrival Time (RAT) prediction, which is essential for slack prediction and obtaining TNS/WNS metrics. In this work, we propose E2ESlack, an end-to-end graph-based framework for pre-routing slack prediction. The framework includes a TimingParser that supports DEF, SDF and LIB files for feature extraction and graph construction, an arrival time prediction model and a fast RAT estimation module. To the best of our knowledge, this is the first work capable of predicting path-level slacks at the pre-routing stage. We perform extensive experiments and demonstrate that our proposed RAT estimation method outperforms the SOTA ML-based prediction method and also pre-routing STA tool. Additionally, the proposed E2ESlack framework achieves TNS/WNS values comparable to post-routing STA results while saving up to 23x runtime.
Defect Detection Network In PCB Circuit Devices Based on GAN Enhanced YOLOv11
Paper ↗
Abstract
This study proposes an advanced method for surface defect detection in printed circuit boards (PCBs) using an improved YOLOv11 model enhanced with a generative adversarial network (GAN). The approach focuses on identifying six common defect types: missing hole, rat bite, open circuit, short circuit, burr, and virtual welding. By employing GAN to generate synthetic defect images, the dataset is augmented with diverse and realistic patterns, improving the model's ability to generalize, particularly for complex and infrequent defects like burrs. The enhanced YOLOv11 model is evaluated on a PCB defect dataset, demonstrating significant improvements in accuracy, recall, and robustness, especially when dealing with defects in complex environments or small targets. This research contributes to the broader field of electronic design automation (EDA), where efficient defect detection is a crucial step in ensuring high-quality PCB manufacturing. By integrating advanced deep learning techniques, this approach enhances the automation and precision of defect detection, reducing reliance on manual inspection and accelerating design-to-production workflows. The findings underscore the importance of incorporating GAN-based data augmentation and optimized detection architectures in EDA processes, providing valuable insights for improving reliability and efficiency in PCB defect detection within industrial applications.
TransPlace: Transferable Circuit Global Placement via Graph Neural Network
Paper ↗
Abstract
Global placement, a critical step in designing the physical layout of computer chips, is essential to optimize chip performance. Prior global placement methods optimize each circuit design individually from scratch. Their neglect of transferable knowledge limits solution efficiency and chip performance as circuit complexity drastically increases. This study presents TransPlace, a global placement framework that learns to place millions of mixed-size cells in continuous space. TransPlace introduces i) Netlist Graph to efficiently model netlist topology, ii) Cell-flow and relative position encoding to learn SE(2)-invariant representation, iii) a tailored graph neural network architecture for informed parameterization of placement knowledge, and iv) a two-stage strategy for coarse-to-fine placement. Compared to state-of-the-art placement methods, TransPlace-trained on a few high-quality placements-can place unseen circuits with 1.2x speedup while reducing congestion by 30%, timing by 9%, and wirelength by 5%.
HaVen: Hallucination-Mitigated LLM for Verilog Code Generation Aligned with HDL Engineers
Paper ↗
Abstract
Recently, the use of large language models (LLMs) for Verilog code generation has attracted great research interest to enable hardware design automation. However, previous works have shown a gap between the ability of LLMs and the practical demands of hardware description language (HDL) engineering. This gap includes differences in how engineers phrase questions and hallucinations in the code generated. To address these challenges, we introduce HaVen, a novel LLM framework designed to mitigate hallucinations and align Verilog code generation with the practices of HDL engineers. HaVen tackles hallucination issues by proposing a comprehensive taxonomy and employing a chain-of-thought (CoT) mechanism to translate symbolic modalities (e.g. truth tables, state diagrams, etc.) into accurate natural language descriptions. Furthermore, HaVen bridges this gap by using a data augmentation strategy. It synthesizes high-quality instruction-code pairs that match real HDL engineering practices. Our experiments demonstrate that HaVen significantly improves the correctness of Verilog code generation, outperforming state-of-the-art LLM-based Verilog generation methods on VerilogEval and RTLLM benchmark. HaVen is publicly available at https://github.com/Intelligent-Computing-Research-Group/HaVen.
Enabling New HDLs with Agents
Paper ↗
Abstract
Large Language Models (LLMs) based agents are transforming the programming language landscape by facilitating learning for beginners, enabling code generation, and optimizing documentation workflows. Hardware Description Languages (HDLs), with their smaller user community, stand to benefit significantly from the application of LLMs as tools for learning new HDLs. This paper investigates the challenges and solutions of enabling LLMs for HDLs, particularly for HDLs that LLMs have not been previously trained on. This work introduces HDLAgent, an AI agent optimized for LLMs with limited knowledge of various HDLs. It significantly enhances off-the-shelf LLMs.
AGON: Automated Design Framework for Customizing Processors from ISA Documents
Paper ↗
Abstract
Customized processors are attractive solutions for vast domain-specific applications due to their high energy efficiency. However, designing a processor in traditional flows is time-consuming and expensive. To address this, researchers have explored methods including the use of agile development tools like Chisel or SpinalHDL, high-level synthesis (HLS) from programming languages like C or SystemC, and more recently, leveraging large language models (LLMs) to generate hardware description language (HDL) code from natural language descriptions. However, each method has limitations in terms of expressiveness, correctness, and performance, leading to a persistent contradiction between the level of automation and the effectiveness of the design. Overall, how to automatically design highly efficient and practical processors with minimal human effort remains a challenge. In this paper, we propose AGON, a novel framework designed to leverage LLMs for the efficient design of out-of-order (OoO) customized processors with minimal human effort. Central to AGON is the nano-operator function (nOP function) based Intermediate Representation (IR), which bridges high-level descriptions and hardware implementations while decoupling functionality from performance optimization, thereby providing an automatic design framework that is expressive and efficient, has correctness guarantees, and enables PPA (Power, Performance, and Area) optimization. Experimental results show that superior to previous LLM-assisted automatic design flows, AGON facilitates designing a series of customized OoO processors that achieve on average 2.35 $\times$ speedup compared with BOOM, a general-purpose CPU designed by experts, with minimal design effort.
An Efficient Stochastic Optimization Method for Global Placement in VLSI Problem
Paper ↗
Abstract
The placement problem in very large-scale integration (VLSI) is a critical step in chip design, the goal of which is to optimize the wirelength of circuit components within a confined area while adhering to non-overlapping constraints. Most analytical placement models often rely on smooth approximations, thereby sacrificing the accuracy of wirelength estimation. To mitigate these inaccuracies, this paper introduces a novel approach that directly optimizes the original nonsmooth wirelength and proposes an innovative penalty model tailored for the global placement problem. Specifically, we transform the non-overlapping constraints into rectified linear penalty functions, allowing for a more precise formulation of the problem. Notably, we reformulate the resultant optimization problem into an equivalent framework resembling deep neural network training. Leveraging automatic differentiation techniques from deep learning, we efficiently compute the subgradient of the objective function, thus facilitating the application of stochastic subgradient methods to solve the model. To enhance the algorithm's performance, several advanced techniques are further introduced, leading to significant improvements in both efficiency and solution quality. Numerical experiments conducted on GSRC benchmark circuits demonstrate that our proposed model and algorithm achieve significant reductions in wirelength while effectively eliminating overlaps, highlighting its potential as a transformative advancement for large-scale VLSI placement.
DFModel: Design Space Optimization of Large-Scale Systems Exploiting Dataflow Mappings
Paper ↗
Abstract
We propose DFModel, a modeling framework for mapping dataflow computation graphs onto large-scale systems. Mapping a workload to a system requires optimizing dataflow mappings at various levels, including the inter-chip (between chips) level and the intra-chip (within a chip) level. DFModel is, to the best of our knowledge, the first framework to perform the optimization at multiple levels of the memory hierarchy and the interconnection network hierarchy. We use DFModel to explore a wide range of workloads on a variety of systems. Evaluated workloads include two state-of-the-art machine learning applications (Large Language Models and Deep Learning Recommendation Models) and two high-performance computing applications (High Performance LINPACK and Fast Fourier Transform). System parameters investigated span the combination of dataflow and traditional accelerator architectures, memory technologies (DDR, HBM), interconnect technologies (PCIe, NVLink), and interconnection network topologies (torus, DGX, dragonfly). For a variety of workloads on a wide range of systems, the DFModel provided a mapping that predicts an average of 1.25X better performance compared to the ones measured on real systems. DFModel shows that for large language model training, dataflow architectures achieve 1.52X higher performance, 1.59X better cost efficiency, and 1.6X better power efficiency compared to non-dataflow architectures. On an industrial system with dataflow architectures, the DFModel-optimized dataflow mapping achieves a speedup of 6.13X compared to non-dataflow mappings from previous performance models such as Calculon, and 1.52X compared to a vendor provided dataflow mapping.
Accelerating Hardware Verification with Graph Models
Paper ↗
Abstract
The increasing complexity of modern processor and IP designs presents significant challenges in identifying and mitigating hardware flaws early in the IC design cycle. Traditional hardware fuzzing techniques, inspired by software testing, have shown promise but face scalability issues, especially at the gate-level netlist where bugs introduced during synthesis are often missed by RTL-level verification due to longer simulation times. To address this, we introduce GraphFuzz, a graph-based hardware fuzzer designed for gate-level netlist verification. In this approach, hardware designs are modeled as graph nodes, with gate behaviors encoded as features. By leveraging graph learning algorithms, GraphFuzz efficiently detects hardware vulnerabilities by analyzing node patterns. Our evaluation across benchmark circuits and open-source processors demonstrates an average prediction accuracy of 80% and bug detection accuracy of 70%, highlighting the potential of graph-based methods for enhancing hardware verification.
AnalogXpert: Automating Analog Topology Synthesis by Incorporating Circuit Design Expertise into Large Language Models
Paper ↗
Abstract
Analog circuits are crucial in modern electronic systems, and automating their design has attracted significant research interest. One of major challenges is topology synthesis, which determines circuit components and their connections. Recent studies explore large language models (LLM) for topology synthesis. However, the scenarios addressed by these studies do not align well with practical applications. Specifically, existing work uses vague design requirements as input and outputs an ideal model, but detailed structural requirements and device-level models are more practical. Moreover, current approaches either formulate topology synthesis as graph generation or Python code generation, whereas practical topology design is a complex process that demands extensive design knowledge. In this work, we propose AnalogXpert, a LLM-based agent aiming at solving practical topology synthesis problem by incorporating circuit design expertise into LLMs. First, we represent analog topology as SPICE code and introduce a subcircuit library to reduce the design space, in the same manner as experienced designers. Second, we decompose the problem into two sub-task (i.e., block selection and block connection) through the use of CoT and incontext learning techniques, to mimic the practical design process. Third, we introduce a proofreading strategy that allows LLMs to incrementally correct the errors in the initial design, akin to human designers who iteratively check and adjust the initial topology design to ensure accuracy. Finally, we construct a high-quality benchmark containing both real data (30) and synthetic data (2k). AnalogXpert achieves 40% and 23% success rates on the synthetic dataset and real dataset respectively, which is markedly better than those of GPT-4o (3% on both the synthetic dataset and the real dataset).
CoopetitiveV: Leveraging LLM-powered Coopetitive Multi-Agent Prompting for High-quality Verilog Generation
Paper ↗
Abstract
Recent advances in agentic LLMs have demonstrated great capabilities in Verilog code generation. However, existing approaches either use LLM-assisted single-agent prompting or cooperation-only multi-agent learning, which will lead to: (i) Degeneration issue for single-agent learning: characterized by diminished error detection and correction capabilities; (ii) Error propagation in cooperation-only multi-agent learning: erroneous information from the former agent will be propagated to the latter through prompts, which can make the latter agents generate buggy code. In this paper, we propose an LLM-based coopetitive multi-agent prompting framework, in which the agents cannot collaborate with each other to form the generation pipeline, but also create a healthy competitive mechanism to improve the generating quality. Our experimental results show that the coopetitive multi-agent framework can effectively mitigate the degeneration risk and reduce the error propagation while improving code error correction capabilities, resulting in higher quality Verilog code generation. The effectiveness of our approach is validated through extensive experiments. On VerilogEval Machine and Human dataset, CoopetitiveV+GPT-4 achieves 99.2% and 99.1% pass@10 scores, respectively. While on RTLLM, CoopetitiveV+GPT-4 obtains 100% syntax and 99.9% functionality pass@5 scores.
Explainable Fuzzy Neural Network with Multi-Fidelity Reinforcement Learning for Micro-Architecture Design Space Exploration
Paper ↗
Abstract
With the continuous advancement of processors, modern micro-architecture designs have become increasingly complex. The vast design space presents significant challenges for human designers, making design space exploration (DSE) algorithms a significant tool for $\mu$-arch design. In recent years, efforts have been made in the development of DSE algorithms, and promising results have been achieved. However, the existing DSE algorithms, e.g., Bayesian Optimization and ensemble learning, suffer from poor interpretability, hindering designers' understanding of the decision-making process. To address this limitation, we propose utilizing Fuzzy Neural Networks to induce and summarize knowledge and insights from the DSE process, enhancing interpretability and controllability. Furthermore, to improve efficiency, we introduce a multi-fidelity reinforcement learning approach, which primarily conducts exploration using cheap but less precise data, thereby substantially diminishing the reliance on costly data. Experimental results show that our method achieves excellent results with a very limited sample budget and successfully surpasses the current state-of-the-art. Our DSE framework is open-sourced and available at https://github.com/fanhanwei/FNN\_MFRL\_ArchDSE/\ .
AiEDA: Agentic AI Design Framework for Digital ASIC System Design
Paper ↗
Abstract
The paper addresses advancements in Generative Artificial Intelligence (GenAI) and digital chip design, highlighting the integration of Large Language Models (LLMs) in automating hardware description and design. LLMs, known for generating human-like content, are now being explored for creating hardware description languages (HDLs) like Verilog from natural language inputs. This approach aims to enhance productivity and reduce costs in VLSI system design. The study introduces "AiEDA", a proposed agentic design flow framework for digital ASIC systems, leveraging autonomous AI agents to manage complex design tasks. AiEDA is designed to streamline the transition from conceptual design to GDSII layout using an open-source toolchain. The framework is demonstrated through the design of an ultra-low-power digital ASIC for KeyWord Spotting (KWS). The use of agentic AI workflows promises to improve design efficiency by automating the integration of multiple design tools, thereby accelerating the development process and addressing the complexities of hardware design.
MAGE: A Multi-Agent Engine for Automated RTL Code Generation
Paper ↗
Abstract
The automatic generation of RTL code (e.g., Verilog) through natural language instructions has emerged as a promising direction with the advancement of large language models (LLMs). However, producing RTL code that is both syntactically and functionally correct remains a significant challenge. Existing single-LLM-agent approaches face substantial limitations because they must navigate between various programming languages and handle intricate generation, verification, and modification tasks. To address these challenges, this paper introduces MAGE, the first open-source multi-agent AI system designed for robust and accurate Verilog RTL code generation. We propose a novel high-temperature RTL candidate sampling and debugging system that effectively explores the space of code candidates and significantly improves the quality of the candidates. Furthermore, we design a novel Verilog-state checkpoint checking mechanism that enables early detection of functional errors and delivers precise feedback for targeted fixes, significantly enhancing the functional correctness of the generated RTL code. MAGE achieves a 95.7% rate of syntactic and functional correctness code generation on VerilogEval-Human 2 benchmark, surpassing the state-of-the-art Claude-3.5-sonnet by 23.3 %, demonstrating a robust and reliable approach for AI-driven RTL design workflows.
TrojanWhisper: Evaluating Pre-trained LLMs to Detect and Localize Hardware Trojans
Paper ↗
Abstract
Existing Hardware Trojans (HT) detection methods face several critical limitations: logic testing struggles with scalability and coverage for large designs, side-channel analysis requires golden reference chips, and formal verification methods suffer from state-space explosion. The emergence of Large Language Models (LLMs) offers a promising new direction for HT detection by leveraging their natural language understanding and reasoning capabilities. For the first time, this paper explores the potential of general-purpose LLMs in detecting various HTs inserted in Register Transfer Level (RTL) designs, including SRAM, AES, and UART modules. We propose a novel tool for this goal that systematically assesses state-of-the-art LLMs (GPT-4o, Gemini 1.5 pro, and Llama 3.1) in detecting HTs without prior fine-tuning. To address potential training data bias, the tool implements perturbation techniques, i.e., variable name obfuscation, and design restructuring, that make the cases more sophisticated for the used LLMs. Our experimental evaluation demonstrates perfect detection rates by GPT-4o and Gemini 1.5 pro in baseline scenarios (100%/100% precision/recall), with both models achieving better trigger line coverage (TLC: 0.82-0.98) than payload line coverage (PLC: 0.32-0.46). Under code perturbation, while Gemini 1.5 pro maintains perfect detection performance (100%/100%), GPT-4o (100%/85.7%) and Llama 3.1 (66.7%/85.7%) show some degradation in detection rates, and all models experience decreased accuracy in localizing both triggers and payloads. This paper validates the potential of LLM approaches for hardware security applications, highlighting areas for future improvement.
Reinforcement Learning Policy as Macro Regulator Rather than Macro Placer
Paper ↗
Abstract
In modern chip design, placement aims at placing millions of circuit modules, which is an essential step that significantly influences power, performance, and area (PPA) metrics. Recently, reinforcement learning (RL) has emerged as a promising technique for improving placement quality, especially macro placement. However, current RL-based placement methods suffer from long training times, low generalization ability, and inability to guarantee PPA results. A key issue lies in the problem formulation, i.e., using RL to place from scratch, which results in limits useful information and inaccurate rewards during the training process. In this work, we propose an approach that utilizes RL for the refinement stage, which allows the RL policy to learn how to adjust existing placement layouts, thereby receiving sufficient information for the policy to act and obtain relatively dense and precise rewards. Additionally, we introduce the concept of regularity during training, which is considered an important metric in the chip design industry but is often overlooked in current RL placement methods. We evaluate our approach on the ISPD 2005 and ICCAD 2015 benchmark, comparing the global half-perimeter wirelength and regularity of our proposed method against several competitive approaches. Besides, we test the PPA performance using commercial software, showing that RL as a regulator can achieve significant PPA improvements. Our RL regulator can fine-tune placements from any method and enhance their quality. Our work opens up new possibilities for the application of RL in placement, providing a more effective and efficient approach to optimizing chip design. Our code is available at \url{https://github.com/lamda-bbo/macro-regulator}.
PyraNet: A Multi-Layered Hierarchical Dataset for Verilog
Paper ↗
Abstract
Recently, there has been a growing interest in leveraging Large Language Models for Verilog code generation. However, the current quality of the generated Verilog code remains suboptimal. This is largely due to the absence of well-defined, well-organized datasets with high-quality samples, as well as a lack of innovative fine-tuning methods and models specifically trained on Verilog. In this paper, we introduce a novel open-source dataset and a corresponding fine-tuning technique, which utilizes a multi-layered structure that we refer to as PyraNet. Our experiments demonstrate that employing the proposed dataset and fine-tuning approach leads to a more accurate fine-tuned model, producing syntactically and functionally correct Verilog code. The evaluation results show improvements by up-to $32.6\%$ in comparison to the CodeLlama-7B baseline model and up-to $16.7\%$ in comparison to the state-of-the-art models using VerilogEval evaluation platform.
HiVeGen -- Hierarchical LLM-based Verilog Generation for Scalable Chip Design
Paper ↗
Abstract
With Large Language Models (LLMs) recently demonstrating impressive proficiency in code generation, it is promising to extend their abilities to Hardware Description Language (HDL). However, LLMs tend to generate single HDL code blocks rather than hierarchical structures for hardware designs, leading to hallucinations, particularly in complex designs like Domain-Specific Accelerators (DSAs). To address this, we propose HiVeGen, a hierarchical LLM-based Verilog generation framework that decomposes generation tasks into LLM-manageable hierarchical submodules. HiVeGen further harnesses the advantages of such hierarchical structures by integrating automatic Design Space Exploration (DSE) into hierarchy-aware prompt generation, introducing weight-based retrieval to enhance code reuse, and enabling real-time human-computer interaction to lower error-correction cost, significantly improving the quality of generated designs.
Deep Learning Modeling Method for RF Devices Based on Uniform Noise Training Set
Paper ↗
Abstract
As the scale and complexity of integrated circuits continue to increase, traditional modeling methods are struggling to address the nonlinear challenges in radio frequency (RF) chips. Deep learning has been increasingly applied to RF device modeling. This paper proposes a deep learning-based modeling method for RF devices using a uniform noise training set, aimed at modeling and fitting the nonlinear characteristics of RF devices. We hypothesize that a uniform noise signal can encompass the full range of characteristics across both frequency and amplitude, and that a deep learning model can effectively capture and learn these features. Based on this hypothesis, the paper designs a complete integrated circuit modeling process based on measured data, including data collection, processing, and neural network training. The proposed method is experimentally validated using the RF amplifier PW210 as a case study. Experimental results show that the uniform noise training set allows the model to capture the nonlinear characteristics of RF devices, and the trained model can predict waveform patterns it has never encountered before. The proposed deep learning-based RF device modeling method, using a uniform noise training set, demonstrates strong generalization capability and excellent training performance, offering high practical application value.
Unleashing GHOST: An LLM-Powered Framework for Automated Hardware Trojan Design
Paper ↗
Abstract
Traditionally, inserting realistic Hardware Trojans (HTs) into complex hardware systems has been a time-consuming and manual process, requiring comprehensive knowledge of the design and navigating intricate Hardware Description Language (HDL) codebases. Machine Learning (ML)-based approaches have attempted to automate this process but often face challenges such as the need for extensive training data, long learning times, and limited generalizability across diverse hardware design landscapes. This paper addresses these challenges by proposing GHOST (Generator for Hardware-Oriented Stealthy Trojans), an automated attack framework that leverages Large Language Models (LLMs) for rapid HT generation and insertion. Our study evaluates three state-of-the-art LLMs - GPT-4, Gemini-1.5-pro, and Llama-3-70B - across three hardware designs: SRAM, AES, and UART. According to our evaluations, GPT-4 demonstrates superior performance, with 88.88% of HT insertion attempts successfully generating functional and synthesizable HTs. This study also highlights the security risks posed by LLM-generated HTs, showing that 100% of GHOST-generated synthesizable HTs evaded detection by an ML-based HT detection tool. These results underscore the urgent need for advanced detection and prevention mechanisms in hardware security to address the emerging threat of LLM-generated HTs. The GHOST HT benchmarks are available at: https://github.com/HSTRG1/GHOSTbenchmarks.git
Unleashing GHOST: An LLM-Powered Framework for Automated Hardware Trojan Design
Paper ↗
Abstract
Traditionally, inserting realistic Hardware Trojans (HTs) into complex hardware systems has been a time-consuming and manual process, requiring comprehensive knowledge of the design and navigating intricate Hardware Description Language (HDL) codebases. Machine Learning (ML)-based approaches have attempted to automate this process but often face challenges such as the need for extensive training data, long learning times, and limited generalizability across diverse hardware design landscapes. This paper addresses these challenges by proposing GHOST (Generator for Hardware-Oriented Stealthy Trojans), an automated attack framework that leverages Large Language Models (LLMs) for rapid HT generation and insertion. Our study evaluates three state-of-the-art LLMs - GPT-4, Gemini-1.5-pro, and Llama-3-70B - across three hardware designs: SRAM, AES, and UART. According to our evaluations, GPT-4 demonstrates superior performance, with 88.88% of HT insertion attempts successfully generating functional and synthesizable HTs. This study also highlights the security risks posed by LLM-generated HTs, showing that 100% of GHOST-generated synthesizable HTs evaded detection by an ML-based HT detection tool. These results underscore the urgent need for advanced detection and prevention mechanisms in hardware security to address the emerging threat of LLM-generated HTs. The GHOST HT benchmarks are available at: https://github.com/HSTRG1/GHOSTbenchmarks.git
PrefixLLM: LLM-aided Prefix Circuit Design
Paper ↗
Abstract
Prefix circuits are fundamental components in digital adders, widely used in digital systems due to their efficiency in calculating carry signals. Synthesizing prefix circuits with minimized area and delay is crucial for enhancing the performance of modern computing systems. Recently, large language models (LLMs) have demonstrated a surprising ability to perform text generation tasks. We propose PrefixLLM, that leverages LLMs for prefix circuit synthesis. PrefixLLM transforms the prefix circuit synthesis task into a structured text generation problem, termed the Structured Prefix Circuit Representation (SPCR), and introduces an iterative framework to automatically and accurately generate valid SPCRs. We further present a design space exploration (DSE) framework that uses LLMs to iteratively search for area and delay optimized prefix circuits. Compared to state-of-the-art, PrefixLLM can reduce the area by 3.70% under the same delay constraint. This work highlights the use of LLMs in the synthesis of arithmetic circuits, which can be transformed into the structured text generation.
ML-based AIG Timing Prediction to Enhance Logic Optimization
Paper ↗
Abstract
As circuit designs become more intricate, obtaining accurate performance estimation in early stages, for effective design space exploration, becomes more time-consuming. Traditional logic optimization approaches often rely on proxy metrics to approximate post-mapping performance and area. However, these proxies do not always correlate well with actual post-mapping delay and area, resulting in suboptimal designs. To address this issue, we explore a ground-truth-based optimization flow that directly incorporates the exact post-mapping delay and area during optimization. While this approach improves design quality, it also significantly increases computational costs, particularly for large-scale designs. To overcome the runtime challenge, we apply machine learning models to predict post-mapping delay and area using the features extracted from AIGs. Our experimental results show that the model has high prediction accuracy with good generalization to unseen designs. Furthermore, the ML-enhanced logic optimization flow significantly reduces runtime while maintaining comparable performance and area outcomes.
Agentic-HLS: An agentic reasoning based high-level synthesis system using large language models (AI for EDA workshop 2024)
Paper ↗
Abstract
Our aim for the ML Contest for Chip Design with HLS 2024 was to predict the validity, running latency in the form of cycle counts, utilization rate of BRAM (util-BRAM), utilization rate of lookup tables (uti-LUT), utilization rate of flip flops (util-FF), and the utilization rate of digital signal processors (util-DSP). We used Chain-of-thought techniques with large language models to perform classification and regression tasks. Our prediction is that with larger models reasoning was much improved. We release our prompts and propose a HLS benchmarking task for LLMs.
C2HLSC: Leveraging Large Language Models to Bridge the Software-to-Hardware Design Gap
Paper ↗
Abstract
High-Level Synthesis (HLS) tools offer rapid hardware design from C code, but their compatibility is limited by code constructs. This paper investigates Large Language Models (LLMs) for automatically refactoring C code into HLS-compatible formats. We present a case study using an LLM to rewrite C code for NIST 800-22 randomness tests, a QuickSort algorithm, and AES-128 into HLS-synthesizable C. The LLM iteratively transforms the C code guided by the system prompt and tool's feedback, implementing functions like streaming data and hardware-specific signals. With the hindsight obtained from the case study, we implement a fully automated framework to refactor C code into HLS-compatible formats using LLMs. To tackle complex designs, we implement a preprocessing step that breaks down the hierarchy in order to approach the problem in a divide-and-conquer bottom-up way. We validated our framework on three ciphers, one hash function, five NIST 800-22 randomness tests, and a QuickSort algorithm. Our results show a high success rate on benchmarks that are orders of magnitude more complex than what has been achieved generating Verilog with LLMs.
Core Placement Optimization of Many-core Brain-Inspired Near-Storage Systems for Spiking Neural Network Training
Paper ↗
Abstract
With the increasing application scope of spiking neural networks (SNN), the complexity of SNN models has surged, leading to an exponential growth in demand for AI computility. As the new generation computing architecture of the neural networks, the efficiency and power consumption of distributed storage and parallel computing in the many-core near-memory computing system have attracted much attention. Among them, the mapping problem from logical cores to physical cores is one of the research hotspots. In order to improve the computing parallelism and system throughput of the many-core near-memory computing system, and to reduce power consumption, we propose a SNN training many-core deployment optimization method based on Off-policy Deterministic Actor-Critic. We utilize deep reinforcement learning as a nonlinear optimizer, treating the many-core topology as network graph features and using graph convolution to input the many-core structure into the policy network. We update the parameters of the policy network through near-end policy optimization to achieve deployment optimization of SNN models in the many-core near-memory computing architecture to reduce chip power consumption. To handle large-dimensional action spaces, we use continuous values matching the number of cores as the output of the policy network and then discretize them again to obtain new deployment schemes. Furthermore, to further balance inter-core computation latency and improve system throughput, we propose a model partitioning method with a balanced storage and computation strategy. Our method overcomes the problems such as uneven computation and storage loads between cores, and the formation of local communication hotspots, significantly reducing model training time, communication costs, and average flow load between cores in the many-core near-memory computing architecture.
DRC-Coder: Automated DRC Checker Code Generation Using LLM Autonomous Agent
Paper ↗
Abstract
In the advanced technology nodes, the integrated design rule checker (DRC) is often utilized in place and route tools for fast optimization loops for power-performance-area. Implementing integrated DRC checkers to meet the standard of commercial DRC tools demands extensive human expertise to interpret foundry specifications, analyze layouts, and debug code iteratively. However, this labor-intensive process, requiring to be repeated by every update of technology nodes, prolongs the turnaround time of designing circuits. In this paper, we present DRC-Coder, a multi-agent framework with vision capabilities for automated DRC code generation. By incorporating vision language models and large language models (LLM), DRC-Coder can effectively process textual, visual, and layout information to perform rule interpretation and coding by two specialized LLMs. We also design an auto-evaluation function for LLMs to enable DRC code debugging. Experimental results show that targeting on a sub-3nm technology node for a state-of-the-art standard cell layout tool, DRC-Coder achieves perfect F1 score 1.000 in generating DRC codes for meeting the standard of a commercial DRC tool, highly outperforming standard prompting techniques (F1=0.631). DRC-Coder can generate code for each design rule within four minutes on average, which significantly accelerates technology advancement and reduces engineering costs.
DocEDA: Automated Extraction and Design of Analog Circuits from Documents with Large Language Model
Paper ↗
Abstract
Efficient and accurate extraction of electrical parameters from circuit datasheets and design documents is critical for accelerating circuit design in Electronic Design Automation (EDA). Traditional workflows often rely on engineers manually searching and extracting these parameters, which is time-consuming, and prone to human error. To address these challenges, we introduce DocEDA, an automated system that leverages advanced computer vision techniques and Large Language Models (LLMs) to extract electrical parameters seamlessly from documents. The layout analysis model specifically designed for datasheet is proposed to classify documents into circuit-related parts. Utilizing the inherent Chain-of-Thought reasoning capabilities of LLMs, DocEDA automates the extraction of electronic component parameters from documents. For circuit diagrams parsing, an improved GAM-YOLO model is hybrid with topology identification to transform diagrams into circuit netlists. Then, a space mapping enhanced optimization framework is evoked for optimization the layout in the document. Experimental evaluations demonstrate that DocEDA significantly enhances the efficiency of processing circuit design documents and the accuracy of electrical parameter extraction. It exhibits adaptability to various circuit design scenarios and document formats, offering a novel solution for EDA with the potential to transform traditional methodologies.
SynDCIM: A Performance-Aware Digital Computing-in-Memory Compiler with Multi-Spec-Oriented Subcircuit Synthesis
Paper ↗
Abstract
Digital Computing-in-Memory (DCIM) is an innovative technology that integrates multiply-accumulation (MAC) logic directly into memory arrays to enhance the performance of modern AI computing. However, the need for customized memory cells and logic components currently necessitates significant manual effort in DCIM design. Existing tools for facilitating DCIM macro designs struggle to optimize subcircuit synthesis to meet user-defined performance criteria, thereby limiting the potential system-level acceleration that DCIM can offer. To address these challenges and enable agile design of DCIM macros with optimal architectures, we present SynDCIM, a performance-aware DCIM compiler that employs multi-spec-oriented subcircuit synthesis. SynDCIM features an automated performance-to-layout generation process that aligns with user-defined performance expectations. This is supported by a scalable subcircuit library and a multi-spec-oriented searching algorithm for effective subcircuit synthesis. The effectiveness of SynDCIM is demonstrated through extensive experiments and validated with a test chip fabricated in a 40nm CMOS process. Testing results reveal that designs generated by SynDCIM exhibit competitive performance when compared to state-of-the-art manually designed DCIM macros.
Scalable Parameter Design for Superconducting Quantum Circuits with Graph Neural Networks
Paper ↗
Abstract
To demonstrate supremacy of quantum computing, increasingly large-scale superconducting quantum computing chips are being designed and fabricated. However, the complexity of simulating quantum systems poses a significant challenge to computer-aided design of quantum chips, especially for large-scale chips. Harnessing the scalability of graph neural networks (GNNs), we here propose a parameter designing algorithm for large-scale superconducting quantum circuits. The algorithm depends on the so-called 'three-stair scaling' mechanism, which comprises two neural-network models: an evaluator supervisedly trained on small-scale circuits for applying to medium-scale circuits, and a designer unsupervisedly trained on medium-scale circuits for applying to large-scale ones. We demonstrate our algorithm in mitigating quantum crosstalk errors. Frequencies for both single- and two-qubit gates (corresponding to the parameters of nodes and edges) are considered simultaneously. Numerical results indicate that the well-trained designer achieves notable advantages in efficiency, effectiveness, and scalability. For example, for large-scale superconducting quantum circuits consisting of around 870 qubits, our GNNs-based algorithm achieves 51% of the errors produced by the state-of-the-art algorithm, with a time reduction from 90 min to 27 sec. Overall, a better-performing and more scalable algorithm for designing parameters of superconducting quantum chips is proposed, which initially demonstrates the advantages of applying GNNs in superconducting quantum chips.
Scalable Parameter Design for Superconducting Quantum Circuits with Graph Neural Networks
Paper ↗
Abstract
To demonstrate supremacy of quantum computing, increasingly large-scale superconducting quantum computing chips are being designed and fabricated. However, the complexity of simulating quantum systems poses a significant challenge to computer-aided design of quantum chips, especially for large-scale chips. Harnessing the scalability of graph neural networks (GNNs), we here propose a parameter designing algorithm for large-scale superconducting quantum circuits. The algorithm depends on the so-called 'three-stair scaling' mechanism, which comprises two neural-network models: an evaluator supervisedly trained on small-scale circuits for applying to medium-scale circuits, and a designer unsupervisedly trained on medium-scale circuits for applying to large-scale ones. We demonstrate our algorithm in mitigating quantum crosstalk errors. Frequencies for both single- and two-qubit gates (corresponding to the parameters of nodes and edges) are considered simultaneously. Numerical results indicate that the well-trained designer achieves notable advantages in efficiency, effectiveness, and scalability. For example, for large-scale superconducting quantum circuits consisting of around 870 qubits, our GNNs-based algorithm achieves 51% of the errors produced by the state-of-the-art algorithm, with a time reduction from 90 min to 27 sec. Overall, a better-performing and more scalable algorithm for designing parameters of superconducting quantum chips is proposed, which initially demonstrates the advantages of applying GNNs in superconducting quantum chips.
UVLLM: An Automated Universal RTL Verification Framework using LLMs
Paper ↗
Abstract
Verifying hardware designs in embedded systems is crucial but often labor-intensive and time-consuming. While existing solutions have improved automation, they frequently rely on unrealistic assumptions. To address these challenges, we introduce a novel framework, UVLLM, which combines Large Language Models (LLMs) with the Universal Verification Methodology (UVM) to relax these assumptions. UVLLM significantly enhances the automation of testing and repairing error-prone Register Transfer Level (RTL) codes, a critical aspect of verification development. Unlike existing methods, UVLLM ensures that all errors are triggered during verification, achieving a syntax error fix rate of 86.99% and a functional error fix rate of 71.92% on our proposed benchmark. These results demonstrate a substantial improvement in verification efficiency. Additionally, our study highlights the current limitations of LLM applications, particularly their reliance on extensive training data. We emphasize the transformative potential of LLMs in hardware design verification and suggest promising directions for future research in AI-driven hardware design methodologies. The Repo. of dataset and code: https://anonymous.4open.science/r/UVLLM/.
Automatic High-quality Verilog Assertion Generation through Subtask-Focused Fine-Tuned LLMs and Iterative Prompting
Paper ↗
Abstract
Formal Property Verification (FPV), using SystemVerilog Assertions (SVA), is crucial for ensuring the completeness of design with respect to the specification. However, writing SVA is a laborious task and has a steep learning curve. In this work, we present a large language model (LLM) -based flow to automatically generate high-quality SVA from the design specification documents, named \ToolName. We introduce a novel sub-task-focused fine-tuning approach that effectively addresses functionally incorrect assertions produced by baseline LLMs, leading to a remarkable 7.3-fold increase in the number of functionally correct assertions. Recognizing the prevalence of syntax and semantic errors, we also developed an iterative refinement method that enhances the LLM's initial outputs by systematically re-prompting it to correct identified issues. This process is further strengthened by a custom compiler that generates meaningful error messages, guiding the LLM towards improved accuracy. The experiments demonstrate a 26\% increase in the number of assertions free from syntax errors using this approach, showcasing its potential to streamline the FPV process.
Masala-CHAI: A Large-Scale SPICE Netlist Dataset for Analog Circuits by Harnessing AI
Paper ↗
Abstract
Masala-CHAI is a fully automated framework leveraging large language models (LLMs) to generate Simulation Programs with Integrated Circuit Emphasis (SPICE) netlists. It addresses a long-standing challenge in circuit design automation: automating netlist generation for analog circuits. Automating this workflow could accelerate the creation of fine-tuned LLMs for analog circuit design and verification. In this work, we identify key challenges in automated netlist generation and evaluate multimodal capabilities of state-of-the-art LLMs, particularly GPT-4, in addressing them. We propose a three-step workflow to overcome existing limitations: labeling analog circuits, prompt tuning, and netlist verification. This approach enables end-to-end SPICE netlist generation from circuit schematic images, tackling the persistent challenge of accurate netlist generation. We utilize Masala-CHAI to collect a corpus of 7,500 schematics that span varying complexities in 10 textbooks and benchmark various open source and proprietary LLMs. Models fine-tuned on Masala-CHAI when used in LLM-agentic frameworks such as AnalogCoder achieve a notable 46% improvement in Pass@1 scores. We open-source our dataset and code for community-driven development.
Improving Routability Prediction via NAS Using a Smooth One-shot Augmented Predictor
Paper ↗
Abstract
Routability optimization in modern EDA tools has benefited greatly from using machine learning (ML) models. Constructing and optimizing the performance of ML models continues to be a challenge. Neural Architecture Search (NAS) serves as a tool to aid in the construction and improvement of these models. Traditional NAS techniques struggle to perform well on routability prediction as a result of two primary factors. First, the separation between the training objective and the search objective adds noise to the NAS process. Secondly, the increased variance of the search objective further complicates performing NAS. We craft a novel NAS technique, coined SOAP-NAS, to address these challenges through novel data augmentation techniques and a novel combination of one-shot and predictor-based NAS. Results show that our technique outperforms existing solutions by 40% closer to the ideal performance measured by ROC-AUC (area under the receiver operating characteristic curve) in DRC hotspot detection. SOAPNet is able to achieve an ROC-AUC of 0.9802 and a query time of only 0.461 ms.
Physics-Informed LLM-Agent for Automated Modulation Design in Power Electronics Systems
Paper ↗
Abstract
LLM-based autonomous agents have demonstrated outstanding performance in solving complex industrial tasks. However, in the pursuit of carbon neutrality and high-performance renewable energy systems, existing AI-assisted design automation faces significant limitations in explainability, scalability, and usability. To address these challenges, we propose LP-COMDA, an LLM-based, physics-informed autonomous agent that automates the modulation design of power converters in Power Electronics Systems with minimal human supervision. Unlike traditional AI-assisted approaches, LP-COMDA contains an LLM-based planner that gathers and validates design specifications through a user-friendly chat interface. The planner then coordinates with physics-informed design and optimization tools to iteratively generate and refine modulation designs autonomously. Through the chat interface, LP-COMDA provides an explainable design process, presenting explanations and charts. Experiments show that LP-COMDA outperforms all baseline methods, achieving a 63.2% reduction in error compared to the second-best benchmark method in terms of standard mean absolute error. Furthermore, empirical studies with 20 experts conclude that design time with LP-COMDA is over 33 times faster than conventional methods, showing its significant improvement on design efficiency over the current processes.
Schemato -- An LLM for Netlist-to-Schematic Conversion
Paper ↗
Abstract
Machine learning models are advancing circuit design, particularly in analog circuits. They typically generate netlists that lack human interpretability. This is a problem as human designers heavily rely on the interpretability of circuit diagrams or schematics to intuitively understand, troubleshoot, and develop designs. Hence, to integrate domain knowledge effectively, it is crucial to translate ML-generated netlists into interpretable schematics quickly and accurately. We propose Schemato, a large language model (LLM) for netlist-to-schematic conversion. In particular, we consider our approach in converting netlists to .asc files, text-based schematic description used in LTSpice. Experiments on our circuit dataset show that Schemato achieves up to 76% compilation success rate, surpassing 63% scored by the state-of-the-art LLMs. Furthermore, our experiments show that Schemato generates schematics with an average graph edit distance score and mean structural similarity index measure, scaled by the compilation success rate that are 1.8x and 4.3x higher than the best performing LLMs respectively, demonstrating its ability to generate schematics that are more accurately connected and are closer to the reference human design.
EDA-Aware RTL Generation with Large Language Models
Paper ↗
Abstract
Large Language Models (LLMs) have become increasingly popular for generating RTL code. However, producing error-free RTL code in a zero-shot setting remains highly challenging for even state-of-the-art LLMs, often leading to issues that require manual, iterative refinement. This additional debugging process can dramatically increase the verification workload, underscoring the need for robust, automated correction mechanisms to ensure code correctness from the start. In this work, we introduce AIvril2, a self-verifying, LLM-agnostic agentic framework aimed at enhancing RTL code generation through iterative corrections of both syntax and functional errors. Our approach leverages a collaborative multi-agent system that incorporates feedback from error logs generated by EDA tools to automatically identify and resolve design flaws. Experimental results, conducted on the VerilogEval-Human benchmark suite, demonstrate that our framework significantly improves code quality, achieving nearly a 3.4$\times$ enhancement over prior methods. In the best-case scenario, functional pass rates of 77% for Verilog and 66% for VHDL were obtained, thus substantially improving the reliability of LLM-driven RTL code generation.
LEDRO: LLM-Enhanced Design Space Reduction and Optimization for Analog Circuits
Paper ↗
Abstract
Traditional approaches for designing analog circuits are time-consuming and require significant human expertise. Existing automation efforts using methods like Bayesian Optimization (BO) and Reinforcement Learning (RL) are sub-optimal and costly to generalize across different topologies and technology nodes. In our work, we introduce a novel approach, LEDRO, utilizing Large Language Models (LLMs) in conjunction with optimization techniques to iteratively refine the design space for analog circuit sizing. LEDRO is highly generalizable compared to other RL and BO baselines, eliminating the need for design annotation or model training for different topologies or technology nodes. We conduct a comprehensive evaluation of our proposed framework and baseline on 22 different Op-Amp topologies across four FinFET technology nodes. Results demonstrate the superior performance of LEDRO as it outperforms our best baseline by an average of 13% FoM improvement with 2.15x speed-up on low complexity Op-Amps and 48% FoM improvement with 1.7x speed-up on high complexity Op-Amps. This highlights LEDRO's effective performance, efficiency, and generalizability.
That Chip Has Sailed: A Critique of Unfounded Skepticism Around AI for Chip Design
Paper ↗
Abstract
In 2020, we introduced a deep reinforcement learning method capable of generating superhuman chip layouts, which we then published in Nature and open-sourced on GitHub. AlphaChip has inspired an explosion of work on AI for chip design, and has been deployed in state-of-the-art chips across Alphabet and extended by external chipmakers. Even so, a non-peer-reviewed invited paper at ISPD 2023 questioned its performance claims, despite failing to run our method as described in Nature. For example, it did not pre-train the RL method (removing its ability to learn from prior experience), used substantially fewer compute resources (20x fewer RL experience collectors and half as many GPUs), did not train to convergence (standard practice in machine learning), and evaluated on test cases that are not representative of modern chips. Recently, Igor Markov published a meta-analysis of three papers: our peer-reviewed Nature paper, the non-peer-reviewed ISPD paper, and Markov's own unpublished paper (though he does not disclose that he co-authored it). Although AlphaChip has already achieved widespread adoption and impact, we publish this response to ensure that no one is wrongly discouraged from innovating in this impactful area.
OpenLS-DGF: An Adaptive Open-Source Dataset Generation Framework for Machine Learning Tasks in Logic Synthesis
Paper ↗
Abstract
This paper introduces OpenLS-DGF, an adaptive logic synthesis dataset generation framework, to enhance machine learning~(ML) applications within the logic synthesis process. Previous dataset generation flows were tailored for specific tasks or lacked integrated machine learning capabilities. While OpenLS-DGF supports various machine learning tasks by encapsulating the three fundamental steps of logic synthesis: Boolean representation, logic optimization, and technology mapping. It preserves the original information in both Verilog and machine-learning-friendly GraphML formats. The verilog files offer semi-customizable capabilities, enabling researchers to insert additional steps and incrementally refine the generated dataset. Furthermore, OpenLS-DGF includes an adaptive circuit engine that facilitates the final dataset management and downstream tasks. The generated OpenLS-D-v1 dataset comprises 46 combinational designs from established benchmarks, totaling over 966,000 Boolean circuits. OpenLS-D-v1 supports integrating new data features, making it more versatile for new challenges. This paper demonstrates the versatility of OpenLS-D-v1 through four distinct downstream tasks: circuit classification, circuit ranking, quality of results (QoR) prediction, and probability prediction. Each task is chosen to represent essential steps of logic synthesis, and the experimental results show the generated dataset from OpenLS-DGF achieves prominent diversity and applicability. The source code and datasets are available at https://github.com/Logic-Factory/ACE/blob/master/OpenLS-DGF/readme.md.
CorrectBench: Automatic Testbench Generation with Functional Self-Correction using LLMs for HDL Design
Paper ↗
Abstract
Functional simulation is an essential step in digital hardware design. Recently, there has been a growing interest in leveraging Large Language Models (LLMs) for hardware testbench generation tasks. However, the inherent instability associated with LLMs often leads to functional errors in the generated testbenches. Previous methods do not incorporate automatic functional correction mechanisms without human intervention and still suffer from low success rates, especially for sequential tasks. To address this issue, we propose CorrectBench, an automatic testbench generation framework with functional self-validation and self-correction. Utilizing only the RTL specification in natural language, the proposed approach can validate the correctness of the generated testbenches with a success rate of 88.85%. Furthermore, the proposed LLM-based corrector employs bug information obtained during the self-validation process to perform functional self-correction on the generated testbenches. The comparative analysis demonstrates that our method achieves a pass ratio of 70.13% across all evaluated tasks, compared with the previous LLM-based testbench generation framework's 52.18% and a direct LLM-based generation method's 33.33%. Specifically in sequential circuits, our work's performance is 62.18% higher than previous work in sequential tasks and almost 5 times the pass ratio of the direct method. The codes and experimental results are open-sourced at the link: https://github.com/AutoBench/CorrectBench
AMSnet-KG: A Netlist Dataset for LLM-based AMS Circuit Auto-Design Using Knowledge Graph RAG
Paper ↗
Abstract
High-performance analog and mixed-signal (AMS) circuits are mainly full-custom designed, which is time-consuming and labor-intensive. A significant portion of the effort is experience-driven, which makes the automation of AMS circuit design a formidable challenge. Large language models (LLMs) have emerged as powerful tools for Electronic Design Automation (EDA) applications, fostering advancements in the automatic design process for large-scale AMS circuits. However, the absence of high-quality datasets has led to issues such as model hallucination, which undermines the robustness of automatically generated circuit designs. To address this issue, this paper introduces AMSnet-KG, a dataset encompassing various AMS circuit schematics and netlists. We construct a knowledge graph with annotations on detailed functional and performance characteristics. Facilitated by AMSnet-KG, we propose an automated AMS circuit generation framework that utilizes the comprehensive knowledge embedded in LLMs. We first formulate a design strategy (e.g., circuit architecture using a number of circuit components) based on required specifications. Next, matched circuit components are retrieved and assembled into a complete topology, and transistor sizing is obtained through Bayesian optimization. Simulation results of the netlist are fed back to the LLM for further topology refinement, ensuring the circuit design specifications are met. We perform case studies of operational amplifier and comparator design to verify the automatic design flow from specifications to netlists with minimal human effort. The dataset used in this paper will be open-sourced upon publishing of this paper.
MetRex: A Benchmark for Verilog Code Metric Reasoning Using LLMs
Paper ↗
Abstract
Large Language Models (LLMs) have been applied to various hardware design tasks, including Verilog code generation, EDA tool scripting, and RTL bug fixing. Despite this extensive exploration, LLMs are yet to be used for the task of post-synthesis metric reasoning and estimation of HDL designs. In this paper, we assess the ability of LLMs to reason about post-synthesis metrics of Verilog designs. We introduce MetRex, a large-scale dataset comprising 25,868 Verilog HDL designs and their corresponding post-synthesis metrics, namely area, delay, and static power. MetRex incorporates a Chain of Thought (CoT) template to enhance LLMs' reasoning about these metrics. Extensive experiments show that Supervised Fine-Tuning (SFT) boosts the LLM's reasoning capabilities on average by 37.0\%, 25.3\%, and 25.7\% on the area, delay, and static power, respectively. While SFT improves performance on our benchmark, it remains far from achieving optimal results, especially on complex problems. Comparing to state-of-the-art regression models, our approach delivers accurate post-synthesis predictions for 17.4\% more designs (within a 5\% error margin), in addition to offering a 1.7x speedup by eliminating the need for pre-processing. This work lays the groundwork for advancing LLM-based Verilog code metric reasoning.
P-MOSS: Learned Scheduling For Indexes Over NUMA Servers Using Low-Level Hardware Statistics
Paper ↗
Abstract
Ever since the Dennard scaling broke down in the early 2000s and the frequency of the CPU stalled, vendors have started to increase the core count in each CPU chip at the expense of introducing heterogeneity, thus ushering the era of NUMA processors. Since then, the heterogeneity in the design space of hardware has only increased to the point that DBMS performance may vary significantly up to an order of magnitude in modern servers. An important factor that affects performance includes the location of the logical cores where the DBMS queries are scheduled, and the locations of the data that the queries access. This paper introduces P-MOSS, a learned spatial scheduling framework that schedules query execution to certain logical cores, and places data accordingly to certain integrated memory controllers (IMC), to integrate hardware consciousness into the system. In the spirit of hardware-software synergy, P-MOSS solely guides its scheduling decision based on low-level hardware statistics collected by performance monitoring counters with the aid of a Decision Transformer. Experimental evaluation is performed in the context of the B-tree and R-tree indexes. Performance results demonstrate that P-MOSS has up to 6x improvement over traditional schedules in terms of query throughput.
Automatically Improving LLM-based Verilog Generation using EDA Tool Feedback
Paper ↗
Abstract
Traditionally, digital hardware designs are written in the Verilog hardware description language (HDL) and debugged manually by engineers. This can be time-consuming and error-prone for complex designs. Large Language Models (LLMs) are emerging as a potential tool to help generate fully functioning HDL code, but most works have focused on generation in the single-shot capacity: i.e., run and evaluate, a process that does not leverage debugging and, as such, does not adequately reflect a realistic development process. In this work, we evaluate the ability of LLMs to leverage feedback from electronic design automation (EDA) tools to fix mistakes in their own generated Verilog. To accomplish this, we present an open-source, highly customizable framework, AutoChip, which combines conversational LLMs with the output from Verilog compilers and simulations to iteratively generate and repair Verilog. To determine the success of these LLMs we leverage the VerilogEval benchmark set. We evaluate four state-of-the-art conversational LLMs, focusing on readily accessible commercial models. EDA tool feedback proved to be consistently more effective than zero-shot prompting only with GPT-4o, the most computationally complex model we evaluated. In the best case, we observed a 5.8% increase in the number of successful designs with a 34.2% decrease in cost over the best zero-shot results. Mixing smaller models with this larger model at the end of the feedback iterations resulted in equally as much success as with GPT-4o using feedback, but incurred 41.9% lower cost (corresponding to an overall decrease in cost over zero-shot by 89.6%).
DeepSeq2: Enhanced Sequential Circuit Learning with Disentangled Representations
Paper ↗
Abstract
Circuit representation learning is increasingly pivotal in Electronic Design Automation (EDA), serving various downstream tasks with enhanced model efficiency and accuracy. One notable work, DeepSeq, has pioneered sequential circuit learning by encoding temporal correlations. However, it suffers from significant limitations including prolonged execution times and architectural inefficiencies. To address these issues, we introduce DeepSeq2, a novel framework that enhances the learning of sequential circuits, by innovatively mapping it into three distinct embedding spaces-structure, function, and sequential behavior-allowing for a more nuanced representation that captures the inherent complexities of circuit dynamics. By employing an efficient Directed Acyclic Graph Neural Network (DAG-GNN) that circumvents the recursive propagation used in DeepSeq, DeepSeq2 significantly reduces execution times and improves model scalability. Moreover, DeepSeq2 incorporates a unique supervision mechanism that captures transitioning behaviors within circuits more effectively. DeepSeq2 sets a new benchmark in sequential circuit representation learning, outperforming prior works in power estimation and reliability analysis.
Neural Model Checking
Paper ↗
Abstract
We introduce a machine learning approach to model checking temporal logic, with application to formal hardware verification. Model checking answers the question of whether every execution of a given system satisfies a desired temporal logic specification. Unlike testing, model checking provides formal guarantees. Its application is expected standard in silicon design and the EDA industry has invested decades into the development of performant symbolic model checking algorithms. Our new approach combines machine learning and symbolic reasoning by using neural networks as formal proof certificates for linear temporal logic. We train our neural certificates from randomly generated executions of the system and we then symbolically check their validity using satisfiability solving which, upon the affirmative answer, establishes that the system provably satisfies the specification. We leverage the expressive power of neural networks to represent proof certificates as well as the fact that checking a certificate is much simpler than finding one. As a result, our machine learning procedure for model checking is entirely unsupervised, formally sound, and practically effective. We experimentally demonstrate that our method outperforms the state-of-the-art academic and commercial model checkers on a set of standard hardware designs written in SystemVerilog.
The Graph's Apprentice: Teaching an LLM Low Level Knowledge for Circuit Quality Estimation
Paper ↗
Abstract
Logic synthesis is a crucial phase in the circuit design process, responsible for transforming hardware description language (HDL) designs into optimized netlists. However, traditional logic synthesis methods are computationally intensive, restricting their iterative use in refining chip designs. Recent advancements in large language models (LLMs), particularly those fine-tuned on programming languages, present a promising alternative. This work proposes augmenting LLMs with predictor networks trained to estimate circuit quality directly from HDL code. To enhance performance, the model is regularized using embeddings from graph neural networks (GNNs) trained on Look-Up Table (LUT) graphs, thereby incorporating lower-level circuit insights. The proposed method demonstrates superior performance compared to existing graph-based RTL-level estimation techniques on the established benchmark OpenABCD, while providing instant feedback on HDL code quality.
SPICEPilot: Navigating SPICE Code Generation and Simulation with AI Guidance
Paper ↗
Abstract
Large Language Models (LLMs) have shown great potential in automating code generation; however, their ability to generate accurate circuit-level SPICE code remains limited due to a lack of hardware-specific knowledge. In this paper, we analyze and identify the typical limitations of existing LLMs in SPICE code generation. To address these limitations, we present SPICEPilot a novel Python-based dataset generated using PySpice, along with its accompanying framework. This marks a significant step forward in automating SPICE code generation across various circuit configurations. Our framework automates the creation of SPICE simulation scripts, introduces standardized benchmarking metrics to evaluate LLM's ability for circuit generation, and outlines a roadmap for integrating LLMs into the hardware design process. SPICEPilot is open-sourced under the permissive MIT license at https://github.com/ACADLab/SPICEPilot.git.
CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming
Paper ↗
Abstract
Recent advancements in Large Language Models (LLMs) have renewed interest in automatic programming language translation. Encoder-decoder transformer models, in particular, have shown promise in translating between different programming languages. However, translating between a language and its high-performance computing (HPC) extensions remains underexplored due to challenges such as complex parallel semantics. In this paper, we introduce CodeRosetta, an encoder-decoder transformer model designed specifically for translating between programming languages and their HPC extensions. CodeRosetta is evaluated on C++ to CUDA and Fortran to C++ translation tasks. It uses a customized learning framework with tailored pretraining and training objectives to effectively capture both code semantics and parallel structural nuances, enabling bidirectional translation. Our results show that CodeRosetta outperforms state-of-the-art baselines in C++ to CUDA translation by 2.9 BLEU and 1.72 CodeBLEU points while improving compilation accuracy by 6.05%. Compared to general closed-source LLMs, our method improves C++ to CUDA translation by 22.08 BLEU and 14.39 CodeBLEU, with 2.75% higher compilation accuracy. Finally, CodeRosetta exhibits proficiency in Fortran to parallel C++ translation, marking it, to our knowledge, as the first encoder-decoder model for this complex task, improving CodeBLEU by at least 4.63 points compared to closed-source and open-code LLMs.
LLM-Aided Efficient Hardware Design Automation
Paper ↗
Abstract
With the rapidly increasing complexity of modern chips, hardware engineers are required to invest more effort in tasks such as circuit design, verification, and physical implementation. These workflows often involve continuous modifications, which are labor-intensive and prone to errors. Therefore, there is an increasing need for more efficient and cost-effective Electronic Design Automation (EDA) solutions to accelerate new hardware development. Recently, large language models (LLMs) have made significant advancements in contextual understanding, logical reasoning, and response generation. Since hardware designs and intermediate scripts can be expressed in text format, it is reasonable to explore whether integrating LLMs into EDA could simplify and fully automate the entire workflow. Accordingly, this paper discusses such possibilities in several aspects, covering hardware description language (HDL) generation, code debugging, design verification, and physical implementation. Two case studies, along with their future outlook, are introduced to highlight the capabilities of LLMs in code repair and testbench generation. Finally, future directions and challenges are highlighted to further explore the potential of LLMs in shaping the next-generation EDA
Multi-objective Optimization in CPU Design Space Exploration: Attention is All You Need
Paper ↗
Abstract
Design space exploration (DSE) enables architects to systematically evaluate various design options, guiding decisions on the most suitable configurations to meet specific objectives such as optimizing performance, power, and area. However, the growing complexity of modern CPUs has dramatically increased the number of micro-architectural parameters and expanded the overall design space, making DSE more challenging and time-consuming. Existing DSE frameworks struggle in large-scale design spaces due to inaccurate models and limited insights into parameter impact, hindering efficient identification of optimal micro-architectures within tight timeframes. In this work, we introduce AttentionDSE. Its key idea is to use the attention mechanism to establish a direct mapping of micro-architectural parameters to their contributions to predicted performance. This approach enhances both the prediction accuracy and interpretability of the performance model. Furthermore, the weights are dynamically adjusted, enabling the model to respond to design changes and effectively pinpoint the key micro-architectural parameters/components responsible for performance bottlenecks. Thus, AttentionDSE accurately, purposefully, and rapidly discovers optimal designs. Experiments on SPEC 2017 demonstrate that AttentionDSE significantly reduces exploration time by over 80\% and achieves 3.9\% improvement in Pareto Hypervolume compared to state-of-the-art DSE frameworks while maintaining superior prediction accuracy and efficiency with an increasing number of parameters.
Multi-objective Optimization in CPU Design Space Exploration: Attention is All You Need
Paper ↗
Abstract
Design Space Exploration (DSE) is essential to modern CPU design, yet current frameworks struggle to scale and generalize in high-dimensional architectural spaces. As the dimensionality of design spaces continues to grow, existing DSE frameworks face three fundamental challenges: (1) reduced accuracy and poor scalability of surrogate models in large design spaces; (2) inefficient acquisition guided by hand-crafted heuristics or exhaustive search; (3) limited interpretability, making it hard to pinpoint architectural bottlenecks. In this work, we present \textbf{AttentionDSE}, the first end-to-end DSE framework that \emph{natively integrates} performance prediction and design guidance through an attention-based neural architecture. Unlike traditional DSE workflows that separate surrogate modeling from acquisition and rely heavily on hand-crafted heuristics, AttentionDSE establishes a unified, learning-driven optimization loop, in which attention weights serve a dual role: enabling accurate performance estimation and simultaneously exposing the performance bottleneck. This paradigm shift elevates attention from a passive representation mechanism to an active, interpretable driver of design decision-making. Key innovations include: (1) a \textbf{Perception-Driven Attention} mechanism that exploits architectural hierarchy and locality, scaling attention complexity from $\mathcal{O}(n^2)$ to $\mathcal{O}(n)$ via sliding windows; (2) an \textbf{Attention-aware Bottleneck Analysis} that automatically surfaces critical parameters for targeted optimization, eliminating the need for domain-specific heuristics. Evaluated on high-dimensional CPU design space using the SPEC CPU2017 benchmark suite, AttentionDSE achieves up to \textbf{3.9\% higher Pareto Hypervolume} and over \textbf{80\% reduction in exploration time} compared to state-of-the-art baselines.
Automated Placement of Analog Integrated Circuits using Priority-based Constructive Heuristic
Paper ↗
Abstract
This paper presents a heuristic approach for solving the placement of Analog and Mixed-Signal Integrated Circuits. Placement is a crucial step in the physical design of integrated circuits. During this step, designers choose the position and variant of each circuit device. We focus on the specific class of analog placement, which requires so-called pockets, their possible merging, and parametrizable minimum distances between devices, which are features mostly omitted in recent research and literature. We formulate the problem using Integer Linear Programming and propose a priority-based constructive heuristic inspired by algorithms for the Facility Layout Problem. Our solution minimizes the perimeter of the circuit's bounding box and the approximated wire length. Multiple variants of the devices with different dimensions are considered. Furthermore, we model constraints crucial for the placement problem, such as symmetry groups and blockage areas. Our outlined improvements make the heuristic suitable to handle complex rules of placement. With a search guided either by a Genetic Algorithm or a Covariance Matrix Adaptation Evolution Strategy, we show the quality of the proposed method on both synthetically generated and real-life industrial instances accompanied by manually created designs. Furthermore, we apply reinforcement learning to control the hyper-parameters of the genetic algorithm. Synthetic instances with more than 200 devices demonstrate that our method can tackle problems more complex than typical industry examples. We also compare our method with results achieved by contemporary state-of-the-art methods on the MCNC and GSRC datasets.
FVEval: Understanding Language Model Capabilities in Formal Verification of Digital Hardware
Paper ↗
Abstract
The remarkable reasoning and code generation capabilities of large language models (LLMs) have spurred significant interest in applying LLMs to enable task automation in digital chip design. In particular, recent work has investigated early ideas of applying these models to formal verification (FV), an approach to verifying hardware implementations that can provide strong guarantees of confidence but demands significant amounts of human effort. While the value of LLM-driven automation is evident, our understanding of model performance, however, has been hindered by the lack of holistic evaluation. In response, we present FVEval, the first comprehensive benchmark and evaluation framework for characterizing LLM performance in tasks pertaining to FV. The benchmark consists of three sub-tasks that measure LLM capabilities at different levels: from the generation of SystemVerilog assertions (SVAs) given natural language descriptions to reasoning about the design RTL and suggesting assertions directly without additional human input. As test instances, we present both collections of expert-written verification collateral and methodologies to scalably generate synthetic examples aligned with industrial FV workflows. A wide range of existing LLMs, both proprietary and open-source, are evaluated against FVEval, based on which we investigate where today's LLMs stand and how we might further enable their application toward improving productivity in digital FV. Our benchmark and evaluation code is available at \url{https://github.com/NVlabs/FVEval}.
Machine Learning-based feasibility estimation of digital blocks in BCD technology
Paper ↗
Abstract
Analog-on-Top Mixed Signal (AMS) Integrated Circuit (IC) design is a time-consuming process predominantly carried out by hand. Within this flow, usually, some area is reserved by the top-level integrator for the placement of digital blocks. Specific features of the area, such as size and shape, have a relevant impact on the possibility of implementing the digital logic with the required functionality. We present a Machine Learning (ML)-based evaluation methodology for predicting the feasibility of digital implementation using a set of high-level features. This approach aims to avoid time-consuming Place-and-Route trials, enabling rapid feedback between Digital and Analog Back-End designers during top-level placement.
CAFEEN: A Cooperative Approach for Energy Efficient NoCs with Multi-Agent Reinforcement Learning
Paper ↗
Abstract
In emerging high-performance Network-on-Chip (NoC) architectures, efficient power management is crucial to minimize energy consumption. We propose a novel framework called CAFEEN that employs both heuristic-based fine-grained and machine learning-based coarse-grained power-gating for energy-efficient NoCs. CAFEEN uses a fine-grained method to activate only essential NoC buffers during lower network loads. It switches to a coarse-grained method at peak loads to minimize compounding wake-up overhead using multi-agent reinforcement learning. Results show that CAFEEN adaptively balances power-efficiency with performance, reducing total energy by 2.60x for single application workloads and 4.37x for multi-application workloads, compared to state-of-the-art NoC power-gating frameworks.
Optimizing High-Level Synthesis Designs with Retrieval-Augmented Large Language Models
Paper ↗
Abstract
High-level synthesis (HLS) allows hardware designers to create hardware designs with high-level programming languages like C/C++/OpenCL, which greatly improves hardware design productivity. However, existing HLS flows require programmers' hardware design expertise and rely on programmers' manual code transformations and directive annotations to guide compiler optimizations. Optimizing HLS designs requires non-trivial HLS expertise and tedious iterative process in HLS code optimization. Automating HLS code optimizations has become a burning need. Recently, large language models (LLMs) trained on massive code and programming tasks have demonstrated remarkable proficiency in comprehending code, showing the ability to handle domain-specific programming queries directly without labor-intensive fine-tuning. In this work, we propose a novel retrieval-augmented LLM-based approach to effectively optimize high-level synthesis (HLS) programs. Our proposed method leverages few-shot learning, enabling large language models to adopt domain-specific knowledge through natural language prompts. We propose a unique framework, Retrieve Augmented Large Language Model Aided Design (RALAD), designed to enhance LLMs' performance in HLS code optimization tasks. RALAD employs advanced embedding techniques and top-\emph{k} search algorithms to dynamically source relevant knowledge from extensive databases, thereby providing contextually appropriate responses to complex programming queries. Our implementation of RALAD on two specialized domains, utilizing comparatively smaller language models, achieves an impressive 80\% success rate in compilation tasks and outperforms general LLMs by 3.7 -- 19$\times$ in latency improvement.
A Benchmark on Directed Graph Representation Learning in Hardware Designs
Paper ↗
Abstract
To keep pace with the rapid advancements in design complexity within modern computing systems, directed graph representation learning (DGRL) has become crucial, particularly for encoding circuit netlists, computational graphs, and developing surrogate models for hardware performance prediction. However, DGRL remains relatively unexplored, especially in the hardware domain, mainly due to the lack of comprehensive and user-friendly benchmarks. This study presents a novel benchmark comprising five hardware design datasets and 13 prediction tasks spanning various levels of circuit abstraction. We evaluate 21 DGRL models, employing diverse graph neural networks and graph transformers (GTs) as backbones, enhanced by positional encodings (PEs) tailored for directed graphs. Our results highlight that bidirected (BI) message passing neural networks (MPNNs) and robust PEs significantly enhance model performance. Notably, the top-performing models include PE-enhanced GTs interleaved with BI-MPNN layers and BI-Graph Isomorphism Network, both surpassing baselines across the 13 tasks. Additionally, our investigation into out-of-distribution (OOD) performance emphasizes the urgent need to improve OOD generalization in DGRL models. This benchmark, implemented with a modular codebase, streamlines the evaluation of DGRL models for both hardware and ML practitioners
ORAssistant: A Custom RAG-based Conversational Assistant for OpenROAD
Paper ↗
Abstract
Open-source Electronic Design Automation (EDA) tools are rapidly transforming chip design by addressing key barriers of commercial EDA tools such as complexity, costs, and access. Recent advancements in Large Language Models (LLMs) have further enhanced efficiency in chip design by providing user assistance across a range of tasks like setup, decision-making, and flow automation. This paper introduces ORAssistant, a conversational assistant for OpenROAD, based on Retrieval-Augmented Generation (RAG). ORAssistant aims to improve the user experience for the OpenROAD flow, from RTL-GDSII by providing context-specific responses to common user queries, including installation, command usage, flow setup, and execution, in prose format. Currently, ORAssistant integrates OpenROAD, OpenROAD-flow-scripts, Yosys, OpenSTA, and KLayout. The data model is built from publicly available documentation and GitHub resources. The proposed architecture is scalable, supporting extensions to other open-source tools, operating modes, and LLM models. We use Google Gemini as the base LLM model to build and test ORAssistant. Early evaluation results of the RAG-based model show notable improvements in performance and accuracy compared to non-fine-tuned LLMs.
Location is Key: Leveraging Large Language Model for Functional Bug Localization in Verilog
Paper ↗
Abstract
Bug localization in Verilog code is a crucial and time-consuming task during the verification of hardware design. Since introduction, Large Language Models (LLMs) have showed their strong programming capabilities. However, no work has yet considered using LLMs for bug localization in Verilog code. This paper presents Location-is-Key, an opensource LLM solution to locate functional errors in Verilog snippets. LiK achieves high localization accuracy, with a pass@1 localization accuracy of 93.3% on our test dataset based on RTLLM, surpassing GPT-4's 77.9% and comparable to Claude-3.5's 90.8%. Additionally, the bug location obtained by LiK significantly improves GPT-3.5's bug repair efficiency (Functional pass@1 increased from 40.39% to 58.92%), highlighting the importance of bug localization in LLM-based Verilog debugging. Compared to existing methods, LiK only requires the design specification and the erroneous code snippet, without the need for testbenches, assertions, or any other EDA tools. This research demonstrates the feasibility of using LLMs for Verilog error localization, thus providing a new direction for automatic Verilog code debugging.
AmpAgent: An LLM-based Multi-Agent System for Multi-stage Amplifier Schematic Design from Literature for Process and Performance Porting
Paper ↗
Abstract
Multi-stage amplifiers are widely applied in analog circuits. However, their large number of components, complex transfer functions, and intricate pole-zero distributions necessitate extensive manpower for derivation and param sizing to ensure their stability. In order to achieve efficient derivation of the transfer function and simplify the difficulty of circuit design, we propose AmpAgent: a multi-agent system based on large language models (LLMs) for efficiently designing such complex amplifiers from literature with process and performance porting. AmpAgent is composed of three agents: Literature Analysis Agent, Mathematics Reasoning Agent and Device Sizing Agent. They are separately responsible for retrieving key information (e.g. formulas and transfer functions) from the literature, decompose the whole circuit's design problem by deriving the key formulas, and address the decomposed problem iteratively. AmpAgent was employed in the schematic design of seven types of multi-stage amplifiers with different compensation techniques. In terms of design efficiency, AmpAgent has reduced the number of iterations by 1.32$ \sim $4${\times}$ and execution time by 1.19$ \sim $2.99${\times}$ compared to conventional optimization algorithms, with a success rate increased by 1.03$ \sim $6.79${\times}$. In terms of circuit performance, it has improved by 1.63$ \sim $27.25${\times}$ compared to the original literature. The findings suggest that LLMs could play a crucial role in the field of complex analog circuit schematic design, as well as process and performance porting.
Learning to Compare Hardware Designs for High-Level Synthesis
Paper ↗
Abstract
High-level synthesis (HLS) is an automated design process that transforms high-level code into hardware designs, enabling the rapid development of hardware accelerators. HLS relies on pragmas, which are directives inserted into the source code to guide the synthesis process, and pragmas have various settings and values that significantly impact the resulting hardware design. State-of-the-art ML-based HLS methods, such as HARP, first train a deep learning model, typically based on graph neural networks (GNNs) applied to graph-based representations of the source code and pragmas. They then perform design space exploration (DSE) to explore the pragma design space, rank candidate designs using the model, and return the top designs. However, traditional DSE methods face challenges due to the highly nonlinear relationship between pragma settings and performance metrics, along with complex interactions between pragmas that affect performance in non-obvious ways. To address these challenges, we propose compareXplore, a novel approach that learns to compare hardware designs for effective HLS optimization. CompareXplore introduces a hybrid loss function that combines pairwise preference learning with pointwise performance prediction, enabling the model to capture both relative preferences and absolute performance. Moreover, we introduce a novel node difference attention module that focuses on the most informative differences between designs, enabling the model to identify critical pragmas impacting performance. CompareXplore adopts a two-stage DSE, where a pointwise prediction model is used for the initial design pruning, followed by a pairwise comparison stage for precise performance verification. In extensive experiments, compareXplore achieves significant improvements in ranking metrics and generates high-quality HLS results for the selected designs, outperforming the existing SOTA method.
CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair
Paper ↗
Abstract
Despite the significant progress made in code generation with large language models, challenges persist, especially with hardware description languages such as Verilog. This paper first presents an analysis of fine-tuned LLMs on Verilog coding, with synthetic data from prior methods. We identify two main issues: difficulties in handling non-textual representations (Karnaugh maps, state-transition diagrams and waveforms) and significant variability during training with models randomly making "minor" mistakes. To address these limitations, we enhance data curation by creating correct-by-construction data targeting non-textual representations. Additionally, we introduce an automated framework that generates error reports from various model checkpoints and injects these errors into open-source code to create targeted code repair data. Our fine-tuned Starcoder2-15B outperforms prior state-of-the-art results by 3.8%, 10.9%, 6.6% for pass@1 on VerilogEval-Machine, VerilogEval-Human, and RTLLM.
Bayer-type Vis-NIR Routing via Inverse Design for Submicron-pixel Image Sensing Chip
Paper ↗
Abstract
With the advent of high-precision nanoscale lithography technology, high-resolution image sensing has experienced rapid development in recent years. Currently, mainstream commercial image sensors predominantly utilize Bayer array color filters to implement RGB colorful imaging strategies. However, as pixel sizes transition into the submicron dimensions, traditional dye filters used in image sensors have long been hampered by limited optical efficiency, suboptimal signal-to-noise ratios, and significant difficulties in miniaturization. In this work, a novel 4-channel RGB-IR color router for image sensing, distinct from the traditional absorption-transmission mechanisms, was proposed through inverse design methodologies. Utilizing genetic algorithms and DCGAN models, approximately 20,000 random color routing structures were generated and trained. From these, an optimized spectral splitting structure with a minimal periodic size of 1.6 um * 1.6 um was identified. This structure achieves peak optical efficiencies 1.7 times greater than those of dye filters, while also offering superior color imaging quality and signal intensity. This innovative design approach, leveraging deep learning integration, demonstrates an on-chip strategy for color realization in 4-channel image sensors, and holds significant promise for enhancing the development of next-generation high-performance image sensing chip systems.
Logic Synthesis Optimization with Predictive Self-Supervision via Causal Transformers
Paper ↗
Abstract
Contemporary hardware design benefits from the abstraction provided by high-level logic gates, streamlining the implementation of logic circuits. Logic Synthesis Optimization (LSO) operates at one level of abstraction within the Electronic Design Automation (EDA) workflow, targeting improvements in logic circuits with respect to performance metrics such as size and speed in the final layout. Recent trends in the field show a growing interest in leveraging Machine Learning (ML) for EDA, notably through ML-guided logic synthesis utilizing policy-based Reinforcement Learning (RL) methods.Despite these advancements, existing models face challenges such as overfitting and limited generalization, attributed to constrained public circuits and the expressiveness limitations of graph encoders. To address these hurdles, and tackle data scarcity issues, we introduce LSOformer, a novel approach harnessing Autoregressive transformer models and predictive SSL to predict the trajectory of Quality of Results (QoR). LSOformer integrates cross-attention modules to merge insights from circuit graphs and optimization sequences, thereby enhancing prediction accuracy for QoR metrics. Experimental studies validate the effectiveness of LSOformer, showcasing its superior performance over baseline architectures in QoR prediction tasks, where it achieves improvements of 5.74%, 4.35%, and 17.06% on the EPFL, OABCD, and proprietary circuits datasets, respectively, in inductive setup.
Optimal Workload Placement on Multi-Instance GPUs
Paper ↗
Abstract
There is an urgent and pressing need to optimize usage of Graphical Processing Units (GPUs), which have arguably become one of the most expensive and sought after IT resources. To help with this goal, several of the current generation of GPUs support a partitioning feature, called Multi-Instance GPU (MIG) to allow multiple workloads to share a GPU, albeit with some constraints. In this paper we investigate how to optimize the placement of Large Language Model (LLM)-based AI Inferencing workloads on GPUs. We first identify and present several use cases that are encountered in practice that require workloads to be efficiently placed or migrated to other GPUs to make room for incoming workloads. The overarching goal is to use as few GPUs as possible and to further minimize memory and compute wastage on GPUs that are utilized. We have developed two approaches to address this problem: an optimization method and a heuristic method. We benchmark these with two workload scheduling heuristics for multiple use cases. Our results show up to 2.85x improvement in the number of GPUs used and up to 70% reduction in GPU wastage over baseline heuristics. We plan to enable the SRE community to leverage our proposed method in production environments.
MTLSO: A Multi-Task Learning Approach for Logic Synthesis Optimization
Paper ↗
Abstract
Electronic Design Automation (EDA) is essential for IC design and has recently benefited from AI-based techniques to improve efficiency. Logic synthesis, a key EDA stage, transforms high-level hardware descriptions into optimized netlists. Recent research has employed machine learning to predict Quality of Results (QoR) for pairs of And-Inverter Graphs (AIGs) and synthesis recipes. However, the severe scarcity of data due to a very limited number of available AIGs results in overfitting, significantly hindering performance. Additionally, the complexity and large number of nodes in AIGs make plain GNNs less effective for learning expressive graph-level representations. To tackle these challenges, we propose MTLSO - a Multi-Task Learning approach for Logic Synthesis Optimization. On one hand, it maximizes the use of limited data by training the model across different tasks. This includes introducing an auxiliary task of binary multi-label graph classification alongside the primary regression task, allowing the model to benefit from diverse supervision sources. On the other hand, we employ a hierarchical graph representation learning strategy to improve the model's capacity for learning expressive graph-level representations of large AIGs, surpassing traditional plain GNNs. Extensive experiments across multiple datasets and against state-of-the-art baselines demonstrate the superiority of our method, achieving an average performance gain of 8.22\% for delay and 5.95\% for area.
AIvril: AI-Driven RTL Generation With Verification In-The-Loop
Paper ↗
Abstract
Large Language Models (LLMs) are computational models capable of performing complex natural language processing tasks. Leveraging these capabilities, LLMs hold the potential to transform the entire hardware design stack, with predictions suggesting that front-end and back-end tasks could be fully automated in the near future. Currently, LLMs show great promise in streamlining Register Transfer Level (RTL) generation, enhancing efficiency, and accelerating innovation. However, their probabilistic nature makes them prone to inaccuracies - a significant drawback in RTL design, where reliability and precision are essential. To address these challenges, this paper introduces AIvril, an advanced framework designed to enhance the accuracy and reliability of RTL-aware LLMs. AIvril employs a multi-agent, LLM-agnostic system for automatic syntax correction and functional verification, significantly reducing - and in many cases, completely eliminating - instances of erroneous code generation. Experimental results conducted on the VerilogEval-Human dataset show that our framework improves code quality by nearly 2x when compared to previous works, while achieving an 88.46% success rate in meeting verification objectives. This represents a critical step toward automating and optimizing hardware design workflows, offering a more dependable methodology for AI-driven RTL design.
VLSI Hypergraph Partitioning with Deep Learning
Paper ↗
Abstract
Partitioning is a known problem in computer science and is critical in chip design workflows, as advancements in this area can significantly influence design quality and efficiency. Deep Learning (DL) techniques, particularly those involving Graph Neural Networks (GNNs), have demonstrated strong performance in various node, edge, and graph prediction tasks using both inductive and transductive learning methods. A notable area of recent interest within GNNs are pooling layers and their application to graph partitioning. While these methods have yielded promising results across social, computational, and other random graphs, their effectiveness has not yet been explored in the context of VLSI hypergraph netlists. In this study, we introduce a new set of synthetic partitioning benchmarks that emulate real-world netlist characteristics and possess a known upper bound for solution cut quality. We distinguish these benchmarks with the prior work and evaluate existing state-of-the-art partitioning algorithms alongside GNN-based approaches, highlighting their respective advantages and disadvantages.
Generation of Compiler Backends from Formal Models of Hardware
Paper ↗
Abstract
Compilers convert between representations -- usually, from higher-level, human writable code to lower-level, machine-readable code. A compiler backend is the portion of the compiler containing optimizations and code generation routines for a specific hardware target. In this dissertation, I advocate for a specific way of building compiler backends: namely, by automatically generating them from explicit, formal models of hardware using automated reasoning algorithms. I describe how automatically generating compilers from formal models of hardware leads to increased optimization ability, stronger correctness guarantees, and reduced development time for compiler backends. As evidence, I present two case studies: first, Glenside, which uses equality saturation to increase the 3LA compiler's ability to offload operations to machine learning accelerators, and second, Lakeroad, a technology mapper for FPGAs which uses program synthesis and semantics extracted from Verilog to map hardware designs to complex, programmable hardware primitives.
SPICED: Syntactical Bug and Trojan Pattern Identification in A/MS Circuits using LLM-Enhanced Detection
Paper ↗
Abstract
Analog and mixed-signal (A/MS) integrated circuits (ICs) are crucial in modern electronics, playing key roles in signal processing, amplification, sensing, and power management. Many IC companies outsource manufacturing to third-party foundries, creating security risks such as stealthy analog Trojans. Traditional detection methods, including embedding circuit watermarks or conducting hardware-based monitoring, often impose significant area and power overheads, and may not effectively identify all types of Trojans. To address these shortcomings, we propose SPICED, a Large Language Model (LLM)-based framework that operates within the software domain, eliminating the need for hardware modifications for Trojan detection and localization. This is the first work using LLM-aided techniques for detecting and localizing syntactical bugs and analog Trojans in circuit netlists, requiring no explicit training and incurring zero area overhead. Our framework employs chain-of-thought reasoning and few-shot examples to teach anomaly detection rules to LLMs. With the proposed method, we achieve an average Trojan coverage of 93.32% and an average true positive rate of 93.4% in identifying Trojan-impacted nodes for the evaluated analog benchmark circuits. These experimental results validate the effectiveness of LLMs in detecting and locating both syntactical bugs and Trojans within analog netlists.
Intelligent OPC Engineer Assistant for Semiconductor Manufacturing
Paper ↗
Abstract
Advancements in chip design and manufacturing have enabled the processing of complex tasks such as deep learning and natural language processing, paving the way for the development of artificial general intelligence (AGI). AI, on the other hand, can be leveraged to innovate and streamline semiconductor technology from planning and implementation to manufacturing. In this paper, we present \textit{Intelligent OPC Engineer Assistant}, an AI/LLM-powered methodology designed to solve the core manufacturing-aware optimization problem known as optical proximity correction (OPC). The methodology involves a reinforcement learning-based OPC recipe search and a customized multi-modal agent system for recipe summarization. Experiments demonstrate that our methodology can efficiently build OPC recipes on various chip designs with specially handled design topologies, a task that typically requires the full-time effort of OPC engineers with years of experience.
Revisiting VerilogEval: A Year of Improvements in Large-Language Models for Hardware Code Generation
Paper ↗
Abstract
The application of large-language models (LLMs) to digital hardware code generation is an emerging field, with most LLMs primarily trained on natural language and software code. Hardware code like Verilog constitutes a small portion of training data, and few hardware benchmarks exist. The open-source VerilogEval benchmark, released in November 2023, provided a consistent evaluation framework for LLMs on code completion tasks. Since then, both commercial and open models have seen significant development. In this work, we evaluate new commercial and open models since VerilogEval's original release-including GPT-4o, GPT-4 Turbo, Llama3.1 (8B/70B/405B), Llama3 70B, Mistral Large, DeepSeek Coder (33B and 6.7B), CodeGemma 7B, and RTL-Coder-against an improved VerilogEval benchmark suite. We find measurable improvements in state-of-the-art models: GPT-4o achieves a 63% pass rate on specification-to-RTL tasks. The recently released and open Llama3.1 405B achieves a 58% pass rate, almost matching GPT-4o, while the smaller domain-specific RTL-Coder 6.7B models achieve an impressive 34% pass rate. Additionally, we enhance VerilogEval's infrastructure by automatically classifying failures, introducing in-context learning support, and extending the tasks to specification-to-RTL translation. We find that prompt engineering remains crucial for achieving good pass rates and varies widely with model and task. A benchmark infrastructure that allows for prompt engineering and failure analysis is essential for continued model development and deployment.
Are LLMs Any Good for High-Level Synthesis?
Paper ↗
Abstract
The increasing complexity and demand for faster, energy-efficient hardware designs necessitate innovative High-Level Synthesis (HLS) methodologies. This paper explores the potential of Large Language Models (LLMs) to streamline or replace the HLS process, leveraging their ability to understand natural language specifications and refactor code. We survey the current research and conduct experiments comparing Verilog designs generated by a standard HLS tool (Vitis HLS) with those produced by LLMs translating C code or natural language specifications. Our evaluation focuses on quantifying the impact on performance, power, and resource utilization, providing an assessment of the efficiency of LLM-based approaches. This study aims to illuminate the role of LLMs in HLS, identifying promising directions for optimized hardware design in applications such as AI acceleration, embedded systems, and high-performance computing.
ShortCircuit: AlphaZero-Driven Circuit Design
Paper ↗
Abstract
Chip design relies heavily on generating Boolean circuits, such as AND-Inverter Graphs (AIGs), from functional descriptions like truth tables. This generation operation is a key process in logic synthesis, a primary chip design stage. While recent advances in deep learning have aimed to accelerate circuit design, these efforts have mostly focused on tasks other than synthesis, and traditional heuristic methods have plateaued. In this paper, we introduce ShortCircuit, a novel transformer-based architecture that leverages the structural properties of AIGs and performs efficient space exploration. Contrary to prior approaches attempting end-to-end generation of logic circuits using deep networks, ShortCircuit employs a two-phase process combining supervised with reinforcement learning to enhance generalization to unseen truth tables. We also propose an AlphaZero variant to handle the double exponentially large state space and the reward sparsity, enabling the discovery of near-optimal designs. To evaluate the generative performance of our model , we extract 500 truth tables from a set of 20 real-world circuits. ShortCircuit successfully generates AIGs for $98\%$ of the 8-input test truth tables, and outperforms the state-of-the-art logic synthesis tool, ABC, by $18.62\%$ in terms of circuits size.
Efficient Task Transfer for HLS DSE
Paper ↗
Abstract
There have been several recent works proposed to utilize model-based optimization methods to improve the productivity of using high-level synthesis (HLS) to design domain-specific architectures. They would replace the time-consuming performance estimation or simulation of design with a proxy model, and automatically insert pragmas to guide hardware optimizations. In this work, we address the challenges associated with high-level synthesis (HLS) design space exploration (DSE) through the evolving landscape of HLS tools. As these tools develop, the quality of results (QoR) from synthesis can vary significantly, complicating the maintenance of optimal design strategies across different toolchains. We introduce Active-CEM, a task transfer learning scheme that leverages a model-based explorer designed to adapt efficiently to changes in toolchains. This approach optimizes sample efficiency by identifying high-quality design configurations under a new toolchain without requiring extensive re-evaluation. We further refine our methodology by incorporating toolchain-invariant modeling. This allows us to predict QoR changes more accurately despite shifts in the black-box implementation of the toolchains. Experiment results on the HLSyn benchmark transitioning to new toolchain show an average performance improvement of 1.58$\times$ compared to AutoDSE and a 1.2$\times$ improvement over HARP, while also increasing the sample efficiency by 5.26$\times$, and reducing the runtime by 2.7$\times$.
VerilogCoder: Autonomous Verilog Coding Agents with Graph-based Planning and Abstract Syntax Tree (AST)-based Waveform Tracing Tool
Paper ↗
Abstract
Due to the growing complexity of modern Integrated Circuits (ICs), automating hardware design can prevent a significant amount of human error from the engineering process and result in less errors. Verilog is a popular hardware description language for designing and modeling digital systems; thus, Verilog generation is one of the emerging areas of research to facilitate the design process. In this work, we propose VerilogCoder, a system of multiple Artificial Intelligence (AI) agents for Verilog code generation, to autonomously write Verilog code and fix syntax and functional errors using collaborative Verilog tools (i.e., syntax checker, simulator, and waveform tracer). Firstly, we propose a task planner that utilizes a novel Task and Circuit Relation Graph retrieval method to construct a holistic plan based on module descriptions. To debug and fix functional errors, we develop a novel and efficient abstract syntax tree (AST)-based waveform tracing tool, which is integrated within the autonomous Verilog completion flow. The proposed methodology successfully generates 94.2% syntactically and functionally correct Verilog code, surpassing the state-of-the-art methods by 33.9% on the VerilogEval-Human v2 benchmark.
HLSPilot: LLM-based High-Level Synthesis
Paper ↗
Abstract
Large language models (LLMs) have catalyzed an upsurge in automatic code generation, garnering significant attention for register transfer level (RTL) code generation. Despite the potential of RTL code generation with natural language, it remains error-prone and limited to relatively small modules because of the substantial semantic gap between natural language expressions and hardware design intent. In response to the limitations, we propose a methodology that reduces the semantic gaps by utilizing C/C++ for generating hardware designs via High-Level Synthesis (HLS) tools. Basically, we build a set of C-to-HLS optimization strategies catering to various code patterns, such as nested loops and local arrays. Then, we apply these strategies to sequential C/C++ code through in-context learning, which provides the LLMs with exemplary C/C++ to HLS prompts. With this approach, HLS designs can be generated effectively. Since LLMs still face problems in determining the optimized pragma parameters precisely, we have a design space exploration (DSE) tool integrated for pragma parameter tuning. Furthermore, we also employ profiling tools to pinpoint the performance bottlenecks within a program and selectively convert bottleneck components to HLS code for hardware acceleration. By combining the LLM-based profiling, C/C++ to HLS translation, and DSE, we have established HLSPilot, the first LLM-enabled high-level synthesis framework, which can fully automate the high-level application acceleration on hybrid CPU-FPGA architectures. According to our experiments on real-world application benchmarks, HLSPilot achieve comparable performance in general and can even outperform manually crafted counterparts, thereby underscoring the substantial promise of LLM-assisted hardware designs.
LAAG-RV: LLM Assisted Assertion Generation for RTL Design Verification
Paper ↗
Abstract
Writing SystemVerilog Assertions (SVA) is an important but complex step in verifying Register Transfer Level (RTL) designs. Conventionally, experts need to understand the design specifications and write the SVA assertions, which is time-consuming and error-prone. However, with the recent advancement of transformer models, the Large Language Models (LLMs) assisted assertion generation for design verification is gaining interest in recent times. Motivated by this, we proposed a novel LLM-based framework, LAAG-RV, to generate SVA from the natural language specifications of the design. Our framework provides a one-time Verilog loop for signal synchronization in the generated SVA to improve the generated assertion quality. For our experiments, we created a custom LLM based on OpenAI GPT-4. Furthermore, we developed test cases to validate the LLM-generated assertions. Initial observations show that some generated assertions contain issues and did not pass all the test cases. However, by iteratively prompting the LLMs using carefully crafted manual prompts derived from test case failures in a simulator, the framework can generate correct SVAs. Our results on OpenTitan designs demonstrate that LLMs significantly simplify the process of generating assertions, making it efficient and less error-prone.
LLM-Aided Compilation for Tensor Accelerators
Paper ↗
Abstract
Hardware accelerators, in particular accelerators for tensor processing, have many potential application domains. However, they currently lack the software infrastructure to support the majority of domains outside of deep learning. Furthermore, a compiler that can easily be updated to reflect changes at both application and hardware levels would enable more agile development and design space exploration of accelerators, allowing hardware designers to realize closer-to-optimal performance. In this work, we discuss how large language models (LLMs) could be leveraged to build such a compiler. Specifically, we demonstrate the ability of GPT-4 to achieve high pass rates in translating code to the Gemmini accelerator, and prototype a technique for decomposing translation into smaller, more LLM-friendly steps. Additionally, we propose a 2-phase workflow for utilizing LLMs to generate hardware-optimized code.
Evaluating Large Language Models for Automatic Register Transfer Logic Generation via High-Level Synthesis
Paper ↗
Abstract
The ever-growing popularity of large language models (LLMs) has resulted in their increasing adoption for hardware design and verification. Prior research has attempted to assess the capability of LLMs to automate digital hardware design by producing superior-quality Register Transfer Logic (RTL) descriptions, particularly in Verilog. However, these tests have revealed that Verilog code production using LLMs at current state-of-the-art lack sufficient functional correctness to be practically viable, compared to automatic generation of programs in general-purpose programming languages such as C, C++, Python, etc. With this as the key insight, in this paper we assess the performance of a two-stage software pipeline for automated Verilog RTL generation: LLM based automatic generation of annotated C++ code suitable for high-level synthesis (HLS), followed by HLS to generate Verilog RTL. We have benchmarked the performance of our proposed scheme using the open-source VerilogEval dataset, for four different industry-scale LLMs, and the Vitis HLS tool. Our experimental results demonstrate that our two-step technique substantially outperforms previous proposed techniques of direct Verilog RTL generation by LLMs in terms of average functional correctness rates, reaching score of 0.86 in pass@1 metric.
Quantum noise modeling through Reinforcement Learning
Paper ↗
Abstract
In the current era of quantum computing, robust and efficient tools are essential to bridge the gap between simulations and quantum hardware execution. In this work, we introduce a machine learning approach to characterize the noise impacting a quantum chip and emulate it during simulations. Our algorithm leverages reinforcement learning, offering increased flexibility in reproducing various noise models compared to conventional techniques such as randomized benchmarking or heuristic noise models. The effectiveness of the RL agent has been validated through simulations and testing on real superconducting qubits. Additionally, we provide practical use-case examples for the study of renowned quantum algorithms.
Automated Physical Design Watermarking Leveraging Graph Neural Networks
Paper ↗
Abstract
This paper presents AutoMarks, an automated and transferable watermarking framework that leverages graph neural networks to reduce the watermark search overheads during the placement stage. AutoMarks's novel automated watermark search is accomplished by (i) constructing novel graph and node features with physical, semantic, and design constraint-aware representation; (ii) designing a data-efficient sampling strategy for watermarking fidelity label collection; and (iii) leveraging a graph neural network to learn the connectivity between cells and predict the watermarking fidelity on unseen layouts. Extensive evaluations on ISPD'15 and ISPD'19 benchmarks demonstrate that our proposed automated methodology: (i) is capable of finding quality-preserving watermarks in a short time; and (ii) is transferable across various designs, i.e., AutoMarks trained on one layout is generalizable to other benchmark circuits. AutoMarks is also resilient against potential watermark removal and forging attacks
RoSE-Opt: Robust and Efficient Analog Circuit Parameter Optimization with Knowledge-infused Reinforcement Learning
Paper ↗
Abstract
This paper proposes a learning framework, RoSE-Opt, to achieve robust and efficient analog circuit parameter optimization. RoSE-Opt has two important features. First, it incorporates key domain knowledge of analog circuit design, such as circuit topology, couplings between circuit specifications, and variations of process, supply voltage, and temperature, into the learning loop. This strategy facilitates the training of an artificial agent capable of achieving design goals by identifying device parameters that are optimal and robust. Second, it exploits a two-level optimization method, that is, integrating Bayesian optimization (BO) with reinforcement learning (RL) to improve sample efficiency. In particular, BO is used for a coarse yet quick search of an initial starting point for optimization. This sets a solid foundation to efficiently train the RL agent with fewer samples. Experimental evaluations on benchmarking circuits show promising sample efficiency, extraordinary figure-of-merit in terms of design efficiency and design success rate, and Pareto optimality in circuit performance of our framework, compared to previous methods. Furthermore, this work thoroughly studies the performance of different RL optimization algorithms, such as Deep Deterministic Policy Gradients (DDPG) with an off-policy learning mechanism and Proximal Policy Optimization (PPO) with an on-policy learning mechanism. This investigation provides users with guidance on choosing the appropriate RL algorithms to optimize the device parameters of analog circuits. Finally, our study also demonstrates RoSE-Opt's promise in parasitic-aware device optimization for analog circuits. In summary, our work reports a knowledge-infused BO-RL design automation framework for reliable and efficient optimization of analog circuits' device parameters.
Non-Overlapping Placement of Macro Cells based on Reinforcement Learning in Chip Design
Paper ↗
Abstract
Due to the increasing complexity of chip design, existing placement methods still have many shortcomings in dealing with macro cells coverage and optimization efficiency. Aiming at the problems of layout overlap, inferior performance, and low optimization efficiency in existing chip design methods, this paper proposes an end-to-end placement method, SRLPlacer, based on reinforcement learning. First, the placement problem is transformed into a Markov decision process by establishing the coupling relationship graph model between macro cells to learn the strategy for optimizing layouts. Secondly, the whole placement process is optimized after integrating the standard cell layout. By assessing on the public benchmark ISPD2005, the proposed SRLPlacer can effectively solve the overlap problem between macro cells while considering routing congestion and shortening the total wire length to ensure routability. Codes are available at https://github.com/zhouyusd/SRLPlacer.
HDL-GPT: High-Quality HDL is All You Need
Paper ↗
Abstract
This paper presents Hardware Description Language Generative Pre-trained Transformers (HDL-GPT), a novel approach that leverages the vast repository of open-source High Definition Language (HDL) codes to train superior quality large code models. The core premise of this paper is the hypothesis that high-quality HDL is all you need to create models with exceptional performance and broad zero-shot generalization abilities. The paper elucidates the methods employed for the curation and augmentation of large corpora from open-source HDL code, transforming highly variable quality data into high-quality data through careful prompting and context maintenance. We demonstrate that the careful selection, filtering, and augmentation of data across HDLs can yield powerful models that surpass current state-of-the-art models. We also explore the impact of different fine-tuning methods on the quality of results. We describe experimental results across a range of fine-tuned SOTA LLMs, substantiating our claims. We demonstrate improvements of 50% to 200% over SOTA HDL models on current benchmarks in tasks ranging from HDL circuit explanations, code generation, formal and simulation testbench creation, triaging bugs, and fixing them. HDL-GPT opens new avenues for the development of advanced model training techniques for circuit design tasks.
MapTune: Advancing ASIC Technology Mapping via Reinforcement Learning Guided Library Tuning
Paper ↗
Abstract
Technology mapping involves mapping logical circuits to a library of cells. Traditionally, the full technology library is used, leading to a large search space and potential overhead. Motivated by randomly sampled technology mapping case studies, we propose MapTune framework that addresses this challenge by utilizing reinforcement learning to make design-specific choices during cell selection. By learning from the environment, MapTune refines the cell selection process, resulting in a reduced search space and potentially improved mapping quality. The effectiveness of MapTune is evaluated on a wide range of benchmarks, different technology libraries and technology mappers. The experimental results demonstrate that MapTune achieves higher mapping accuracy and reducing delay/area across diverse circuit designs, technology libraries and mappers. The paper also discusses the Pareto-Optimal exploration and confirms the perpetual delay-area trade-off. Conducted on benchmark suites ISCAS 85/89, ITC/ISCAS 99, VTR8.0 and EPFL benchmarks, the post-technology mapping and post-sizing quality-of-results (QoR) have been significantly improved, with average Area-Delay Product (ADP) improvement of 22.54\% among all different exploration settings in MapTune. The improvements are consistently remained for four different technologies (7nm, 45nm, 130nm, and 180 nm) and two different mappers.
Utilizing Generative Adversarial Networks for Image Data Augmentation and Classification of Semiconductor Wafer Dicing Induced Defects
Paper ↗
Abstract
In semiconductor manufacturing, the wafer dicing process is central yet vulnerable to defects that significantly impair yield - the proportion of defect-free chips. Deep neural networks are the current state of the art in (semi-)automated visual inspection. However, they are notoriously known to require a particularly large amount of data for model training. To address these challenges, we explore the application of generative adversarial networks (GAN) for image data augmentation and classification of semiconductor wafer dicing induced defects to enhance the variety and balance of training data for visual inspection systems. With this approach, synthetic yet realistic images are generated that mimic real-world dicing defects. We employ three different GAN variants for high-resolution image synthesis: Deep Convolutional GAN (DCGAN), CycleGAN, and StyleGAN3. Our work-in-progress results demonstrate that improved classification accuracies can be obtained, showing an average improvement of up to 23.1 % from 65.1 % (baseline experiment) to 88.2 % (DCGAN experiment) in balanced accuracy, which may enable yield optimization in production.
Rome was Not Built in a Single Step: Hierarchical Prompting for LLM-based Chip Design
Paper ↗
Abstract
Large Language Models (LLMs) are effective in computer hardware synthesis via hardware description language (HDL) generation. However, LLM-assisted approaches for HDL generation struggle when handling complex tasks. We introduce a suite of hierarchical prompting techniques which facilitate efficient stepwise design methods, and develop a generalizable automation pipeline for the process. To evaluate these techniques, we present a benchmark set of hardware designs which have solutions with or without architectural hierarchy. Using these benchmarks, we compare various open-source and proprietary LLMs, including our own fine-tuned Code Llama-Verilog model. Our hierarchical methods automatically produce successful designs for complex hardware modules that standard flat prompting methods cannot achieve, allowing smaller open-source LLMs to compete with large proprietary models. Hierarchical prompting reduces HDL generation time and yields savings on LLM costs. Our experiments detail which LLMs are capable of which applications, and how to apply hierarchical methods in various modes. We explore case studies of generating complex cores using automatic scripted hierarchical prompts, including the first-ever LLM-designed processor with no human feedback. Tools for the Recurrent Optimization via Machine Editing (ROME) method can be found at https://github.com/ajn313/ROME-LLM
AutoVCoder: A Systematic Framework for Automated Verilog Code Generation using LLMs
Paper ↗
Abstract
Recently, the use of large language models (LLMs) for software code generation, e.g., C/C++ and Python, has proven a great success. However, LLMs still suffer from low syntactic and functional correctness when it comes to the generation of register-transfer level (RTL) code, such as Verilog. To address this issue, in this paper, we develop AutoVCoder, a systematic open-source framework that significantly improves the LLMs' correctness of generating Verilog code and enhances the quality of its output at the same time. Our framework integrates three novel techniques, including a high-quality hardware dataset generation approach, a two-round LLM fine-tuning method and a domain-specific retrieval-augmented generation (RAG) mechanism. Experimental results demonstrate that AutoVCoder outperforms both industrial and academic LLMs in Verilog code generation. Specifically, AutoVCoder shows a 0.5% and 2.2% improvement in functional correctness on the EvalMachine and EvalHuman benchmarks compared with BetterV, and also achieves a 3.4% increase in syntax correctness and a 3.4% increase in functional correctness on the RTLLM benchmark compared with RTLCoder.
Large Language Model for Verilog Generation with Code-Structure-Guided Reinforcement Learning
Paper ↗
Abstract
Recent advancements in large language models (LLMs) have sparked significant interest in the automatic generation of Register Transfer Level (RTL) designs, particularly using Verilog. Current research on this topic primarily focuses on pre-training and instruction tuning, but the effectiveness of these methods is constrained by the limited availability of training data, as public Verilog code is far less abundant than software code. In particular, these methods struggle to effectively capture Verilog parallel code structures, which fundamentally differ from the imperative, sequential control flow typical in most software programming languages. This paper introduces VeriSeek, an LLM enhanced by reinforcement learning using a limited amount of high-quality training data to achieve high Verilog code generation performance. Our reinforcement learning approach employs code structure information as feedback signals to refine the pre-trained model, enabling it to effectively learn important patterns from Verilog code with parallel structures. Experiments show that VeriSeek outperforms state-of-the-art methods across multiple benchmarks.
Generative AI Augmented Induction-based Formal Verification
Paper ↗
Abstract
Generative Artificial Intelligence (GenAI) has demonstrated its capabilities in the present world that reduce human effort significantly. It utilizes deep learning techniques to create original and realistic content in terms of text, images, code, music, and video. Researchers have also shown the capabilities of modern Large Language Models (LLMs) used by GenAI models that can be used to aid hardware development. Formal verification is a mathematical-based proof method used to exhaustively verify the correctness of a design. In this paper, we demonstrate how GenAI can be used in induction-based formal verification to increase the verification throughput.
ChipXplore: Natural Language Exploration of Hardware Designs and Libraries
Paper ↗
Abstract
Hardware design workflows rely on Process Design Kits (PDKs) from different fabrication nodes, each containing standard cell libraries optimized for speed, power, or density. Engineers typically navigate between the design and target PDK to make informed decisions, such as selecting gates for area optimization or enhancing the speed of the critical path. However, this process is often manual, time-consuming, and prone to errors. To address this, we present ChipXplore, a multi-agent collaborative framework powered by large language models that enables engineers to query hardware designs and PDKs using natural language. By exploiting the structured nature of PDK and hardware design data, ChipXplore retrieves relevant information through text-to-SQL and text-to-Cypher customized workflows. The framework achieves an execution accuracy of 97.39\% in complex natural language queries and improves productivity by making retrieval 5.63x faster while reducing errors by 5.25x in user studies. Compared to generic workflows, ChipXplore's customized workflow is capable of orchestrating reasoning and planning over multiple databases, improving accuracy by 29.78\%. ChipXplore lays the foundation for building autonomous agents capable of tackling diverse physical design tasks that require PDK and hardware design awareness.
IICPilot: An Intelligent Integrated Circuit Backend Design Framework Using Open EDA
Paper ↗
Abstract
Open-source EDA tools are rapidly advancing, fostering collaboration, innovation, and knowledge sharing within the EDA community. However, the growing complexity of these tools, characterized by numerous design parameters and heuristics, poses a significant barrier to their widespread adoption. This complexity is particularly pronounced in integrated circuit (IC) backend designs, which place substantial demands on engineers' expertise in EDA tools. To tackle this challenge, we introduce IICPilot, an intelligent IC backend design system based on LLM technology. IICPilot automates various backend design procedures, including script generation, EDA tool invocation, design space exploration of EDA parameters, container-based computing resource allocation, and exception management. By automating these tasks, IICPilot significantly lowers the barrier to entry for open-source EDA tools. Specifically, IICPilot utilizes LangChain's multi-agent framework to efficiently handle distinct design tasks, enabling flexible enhancements independently. Moreover, IICPilot separates the backend design workflow from specific open-source EDA tools through a unified EDA calling interface. This approach allows seamless integration with different open-source EDA tools like OpenROAD and iEDA, streamlining the backend design and optimization across the EDA tools.
SENTAUR: Security EnhaNced Trojan Assessment Using LLMs Against Undesirable Revisions
Paper ↗
Abstract
A globally distributed IC supply chain brings risks due to untrusted third parties. The risks span inadvertent use of hardware Trojan (HT), inserted Intellectual Property (3P-IP) or Electronic Design Automation (EDA) flows. HT can introduce stealthy HT behavior, prevent an IC work as intended, or leak sensitive data via side channels. To counter HTs, rapidly examining HT scenarios is a key requirement. While Trust-Hub benchmarks are a good starting point to assess defenses, they encompass a small subset of manually created HTs within the expanse of HT designs. Further, the HTs may disappear during synthesis. We propose a large language model (LLM) framework SENTAUR to generate a suite of legitimate HTs for a Register Transfer Level (RTL) design by learning its specifications, descriptions, and natural language descriptions of HT effects. Existing tools and benchmarks are limited; they need a learning period to construct an ML model to mimic the threat model and are difficult to reproduce. SENTAUR can swiftly produce HT instances by leveraging LLMs without any learning period and sanitizing the HTs facilitating their rapid assessment. Evaluation of SENTAUR involved generating effective, synthesizable, and practical HTs from TrustHub and elsewhere, investigating impacts of payloads/triggers at the RTL. While our evaluation focused on HT insertion, SENTAUR can generalize to automatically transform an RTL code to have defined functional modifications.
Chip Placement with Diffusion Models
Paper ↗
Abstract
Macro placement is a vital step in digital circuit design that defines the physical location of large collections of components, known as macros, on a 2D chip. Because key performance metrics of the chip are determined by the placement, optimizing it is crucial. Existing learning-based methods typically fall short because of their reliance on reinforcement learning (RL), which is slow and struggles to generalize, requiring online training on each new circuit. Instead, we train a diffusion model capable of placing new circuits zero-shot, using guided sampling in lieu of RL to optimize placement quality. To enable such models to train at scale, we designed a capable yet efficient architecture for the denoising model, and propose a novel algorithm to generate large synthetic datasets for pre-training. To allow zero-shot transfer to real circuits, we empirically study the design decisions of our dataset generation algorithm, and identify several key factors enabling generalization. When trained on our synthetic data, our models generate high-quality placements on unseen, realistic circuits, achieving competitive performance on placement benchmarks compared to state-of-the-art methods.
CodeV: Empowering LLMs with HDL Generation through Multi-Level Summarization
Paper ↗
Abstract
The design flow of processors, particularly in hardware description languages (HDL) like Verilog and Chisel, is complex and costly. While recent advances in large language models (LLMs) have significantly improved coding tasks in software languages such as Python, their application in HDL generation remains limited due to the scarcity of high-quality HDL data. Traditional methods of adapting LLMs for hardware design rely on synthetic HDL datasets, which often suffer from low quality because even advanced LLMs like GPT perform poorly in the HDL domain. Moreover, these methods focus solely on chat tasks and the Verilog language, limiting their application scenarios. In this paper, we observe that: (1) HDL code collected from the real world is of higher quality than code generated by LLMs. (2) LLMs like GPT-3.5 excel in summarizing HDL code rather than generating it. (3) An explicit language tag can help LLMs better adapt to the target language when there is insufficient data. Based on these observations, we propose an efficient LLM fine-tuning pipeline for HDL generation that integrates a multi-level summarization data synthesis process with a novel Chat-FIM-Tag supervised fine-tuning method. The pipeline enhances the generation of HDL code from natural language descriptions and enables the handling of various tasks such as chat and infilling incomplete code. Utilizing this pipeline, we introduce CodeV, a series of HDL generation LLMs. Among them, CodeV-All not only possesses a more diverse range of language abilities, i.e. Verilog and Chisel, and a broader scope of tasks, i.e. Chat and fill-in-middle (FIM), but it also achieves performance on VerilogEval that is comparable to or even surpasses that of CodeV-Verilog fine-tuned on Verilog only, making them the first series of open-source LLMs designed for multi-scenario HDL generation.
DeepGate3: Towards Scalable Circuit Representation Learning
Paper ↗
Abstract
Circuit representation learning has shown promising results in advancing the field of Electronic Design Automation (EDA). Existing models, such as DeepGate Family, primarily utilize Graph Neural Networks (GNNs) to encode circuit netlists into gate-level embeddings. However, the scalability of GNN-based models is fundamentally constrained by architectural limitations, impacting their ability to generalize across diverse and complex circuit designs. To address these challenges, we introduce DeepGate3, an enhanced architecture that integrates Transformer modules following the initial GNN processing. This novel architecture not only retains the robust gate-level representation capabilities of its predecessor, DeepGate2, but also enhances them with the ability to model subcircuits through a novel pooling transformer mechanism. DeepGate3 is further refined with multiple innovative supervision tasks, significantly enhancing its learning process and enabling superior representation of both gate-level and subcircuit structures. Our experiments demonstrate marked improvements in scalability and generalizability over traditional GNN-based approaches, establishing a significant step forward in circuit representation learning technology.
Deep Inverse Design for High-Level Synthesis
Paper ↗
Abstract
High-level synthesis (HLS) has significantly advanced the automation of digital circuits design, yet the need for expertise and time in pragma tuning remains challenging. Existing solutions for the design space exploration (DSE) adopt either heuristic methods, lacking essential information for further optimization potential, or predictive models, missing sufficient generalization due to the time-consuming nature of HLS and the exponential growth of the design space. To address these challenges, we propose Deep Inverse Design for HLS (DID4HLS), a novel approach that integrates graph neural networks and generative models. DID4HLS iteratively optimizes hardware designs aimed at compute-intensive algorithms by learning conditional distributions of design features from post-HLS data. Compared to four state-of-the-art DSE baselines, our method achieved an average improvement of 42.8% on average distance to reference set (ADRS) compared to the best-performing baselines across six benchmarks, while demonstrating high robustness and efficiency. The code is available at https://github.com/PingChang818/DID4HLS.
Natural language is not enough: Benchmarking multi-modal generative AI for Verilog generation
Paper ↗
Abstract
Natural language interfaces have exhibited considerable potential in the automation of Verilog generation derived from high-level specifications through the utilization of large language models, garnering significant attention. Nevertheless, this paper elucidates that visual representations contribute essential contextual information critical to design intent for hardware architectures possessing spatial complexity, potentially surpassing the efficacy of natural-language-only inputs. Expanding upon this premise, our paper introduces an open-source benchmark for multi-modal generative models tailored for Verilog synthesis from visual-linguistic inputs, addressing both singular and complex modules. Additionally, we introduce an open-source visual and natural language Verilog query language framework to facilitate efficient and user-friendly multi-modal queries. To evaluate the performance of the proposed multi-modal hardware generative AI in Verilog generation tasks, we compare it with a popular method that relies solely on natural language. Our results demonstrate a significant accuracy improvement in the multi-modal generated Verilog compared to queries based solely on natural language. We hope to reveal a new approach to hardware design in the large-hardware-design-model era, thereby fostering a more diversified and productive approach to hardware design.
INSIGHT: Universal Neural Simulator for Analog Circuits Harnessing Autoregressive Transformers
Paper ↗
Abstract
Analog front-end design heavily relies on specialized human expertise and costly trial-and-error simulations, which motivated many prior works on analog design automation. However, efficient and effective exploration of the vast and complex design space remains constrained by the time-consuming nature of SPICE simulations, making effective design automation a challenging endeavor. In this paper, we introduce INSIGHT, a GPU-powered, technology-agnostic, effective universal neural simulator in the analog front-end design automation loop. INSIGHT accurately predicts the performance metrics of analog circuits across various technologies with just a few microseconds of inference time. Notably, its autoregressive capabilities enable INSIGHT to accurately predict simulation-costly critical transient specifications leveraging less expensive performance metric information. The low cost and high fidelity feature make INSIGHT a good substitute for standard simulators in analog front-end optimization frameworks. INSIGHT is compatible with any optimization framework, facilitating enhanced design space exploration for sample efficiency through sophisticated offline learning and adaptation techniques. Our experiments demonstrate that INSIGHT-M, a model-based batch reinforcement learning sizing framework with INSIGHT as the accurate surrogate, only requires < 20 real-time simulations with 100-1000x lower simulation costs and significant speedup over existing sizing methods.
Studying the Degradation of Propagation Delay on FPGAs at the European XFEL
Paper ↗
Abstract
An increasing number of unhardened commercial-off-the-shelf embedded devices are deployed under harsh operating conditions and in highly-dependable systems. Due to the mechanisms of hardware degradation that affect these devices, ageing detection and monitoring are crucial to prevent critical failures. In this paper, we empirically study the propagation delay of 298 naturally-aged FPGA devices that are deployed in the European XFEL particle accelerator. Based on in-field measurements, we find that operational devices show significantly slower switching frequencies than unused chips, and that increased gamma and neutron radiation doses correlate with increased hardware degradation. Furthermore, we demonstrate the feasibility of developing machine learning models that estimate the switching frequencies of the devices based on historical and environmental data.
GOALPlace: Begin with the End in Mind
Paper ↗
Abstract
Co-optimizing placement with congestion is integral to achieving high-quality designs. This paper presents GOALPlace, a new learning-based general approach to improving placement congestion by controlling cell density. Our method efficiently learns from an EDA tool's post-route optimized results and uses an empirical Bayes technique to adapt this goal/target to a specific placer's solutions, effectively beginning with the end in mind. It enhances correlation with the long-running heuristics of the tool's router and timing-opt engine -- while solving placement globally without expensive incremental congestion estimation and mitigation methods. A statistical analysis with a new hierarchical netlist clustering establishes the importance of density and the potential for an adequate cell density target across placements. Our experiments show that our method, integrated as a demonstration inside an academic GPU-accelerated global placer, consistently produces macro and standard cell placements of superior or comparable quality to commercial tools. Our empirical Bayes methodology also allows a substantial quality improvement over state-of-the-art academic mixed-size placers, achieving up to 10x fewer design rule check (DRC) violations, a 5% decrease in wirelength, and a 30% and 60% reduction in worst and total negative slack (WNS/TNS).
AutoBench: Automatic Testbench Generation and Evaluation Using LLMs for HDL Design
Paper ↗
Abstract
In digital circuit design, testbenches constitute the cornerstone of simulation-based hardware verification. Traditional methodologies for testbench generation during simulation-based hardware verification still remain partially manual, resulting in inefficiencies in testing various scenarios and requiring expensive time from designers. Large Language Models (LLMs) have demonstrated their potential in automating the circuit design flow. However, directly applying LLMs to generate testbenches suffers from a low pass rate. To address this challenge, we introduce AutoBench, the first LLM-based testbench generator for digital circuit design, which requires only the description of the design under test (DUT) to automatically generate comprehensive testbenches. In AutoBench, a hybrid testbench structure and a self-checking system are realized using LLMs. To validate the generated testbenches, we also introduce an automated testbench evaluation framework to evaluate the quality of generated testbenches from multiple perspectives. Experimental results demonstrate that AutoBench achieves a 57% improvement in the testbench pass@1 ratio compared with the baseline that directly generates testbenches using LLMs. For 75 sequential circuits, AutoBench successfully has a 3.36 times testbench pass@1 ratio compared with the baseline. The source codes and experimental results are open-sourced at this link: https://github.com/AutoBench/AutoBench
NeuroSteiner: A Graph Transformer for Wirelength Estimation
Paper ↗
Abstract
A core objective of physical design is to minimize wirelength (WL) when placing chip components on a canvas. Computing the minimal WL of a placement requires finding rectilinear Steiner minimum trees (RSMTs), an NP-hard problem. We propose NeuroSteiner, a neural model that distills GeoSteiner, an optimal RSMT solver, to navigate the cost--accuracy frontier of WL estimation. NeuroSteiner is trained on synthesized nets labeled by GeoSteiner, alleviating the need to train on real chip designs. Moreover, NeuroSteiner's differentiability allows to place by minimizing WL through gradient descent. On ISPD 2005 and 2019, NeuroSteiner can obtain 0.3% WL error while being 60% faster than GeoSteiner, or 0.2% and 30%.
Classification-Based Automatic HDL Code Generation Using LLMs
Paper ↗
Abstract
While large language models (LLMs) have demonstrated the ability to generate hardware description language (HDL) code for digital circuits, they still suffer from the hallucination problem, which leads to the generation of incorrect HDL code or misunderstanding of specifications. In this work, we introduce a human-expert-inspired method to mitigate the hallucination of LLMs and improve the performance in HDL code generation. We first let LLMs classify the type of the circuit based on the specifications. Then, according to the type of the circuit, we split the tasks into several sub-procedures, including information extraction and human-like design flow using Electronic Design Automation (EDA) tools. Besides, we also use a search method to mitigate the variation in code generation. Experimental results show that our method can significantly improve the functional correctness of the generated Verilog and reduce the hallucination of LLMs.
Efficient Inverse Design of Plasmonic Patch Nanoantennas using Deep Learning
Paper ↗
Abstract
Plasmonic nanoantennas with suitable far-field characteristics are of huge interest for utilization in optical wireless links, inter-/intra-chip communications, LiDARs, and photonic integrated circuits due to their exceptional modal confinement. Despite its success in shaping robust antenna design theories in radio frequency and millimeter-wave regimes, conventional transmission line theory finds its validity diminished in the optical frequencies, leading to a noticeable void in a generalized theory for antenna design in the optical domain. By utilizing neural networks and through a one-time training of the network, one can transform the plasmonic nanoantennas design into an automated, data-driven task. In this work, we have developed a multi-head deep convolutional neural network serving as an efficient inverse-design framework for plasmonic patch nanoantennas. Our framework is designed with the main goal of determining the optimal geometries of nanoantennas to achieve the desired (inquired by the designer) S 11 and radiation pattern simultaneously. The proposed approach preserves the one-to-many mappings, enabling us to generate diverse designs. In addition, apart from the primary fabrication limitations that were considered while generating the dataset, further design and fabrication constraints can also be applied after the training process. In addition to possessing an exceptionally rapid surrogate solver capable of predicting S 11 and radiation patterns throughout the entire design frequency spectrum, we are introducing what we believe to be the pioneering inverse design network.
Benchmarking End-To-End Performance of AI-Based Chip Placement Algorithms
Paper ↗
Abstract
The increasing complexity of modern very-large-scale integration (VLSI) design highlights the significance of Electronic Design Automation (EDA) technologies. Chip placement is a critical step in the EDA workflow, which positions chip modules on the canvas with the goal of optimizing performance, power, and area (PPA) metrics of final chip designs. Recent advances have demonstrated the great potential of AI-based algorithms in enhancing chip placement. However, due to the lengthy workflow of chip design, the evaluations of these algorithms often focus on intermediate surrogate metrics, which are easy to compute but frequently reveal a substantial misalignment with the end-to-end performance (i.e., the final design PPA). To address this challenge, we introduce ChiPBench, which can effectively facilitate research in chip placement within the AI community. ChiPBench is a comprehensive benchmark specifically designed to evaluate the effectiveness of existing AI-based chip placement algorithms in improving final design PPA metrics. Specifically, we have gathered 20 circuits from various domains (e.g., CPU, GPU, and microcontrollers). These designs are compiled by executing the workflow from the verilog source code, which preserves necessary physical implementation kits, enabling evaluations for the placement algorithms on their impacts on the final design PPA. We executed six state-of-the-art AI-based chip placement algorithms on these designs and plugged the results of each single-point algorithm into the physical implementation workflow to obtain the final PPA results. Experimental results show that even if intermediate metric of a single-point algorithm is dominant, while the final PPA results are unsatisfactory. We believe that our benchmark will serve as an effective evaluation framework to bridge the gap between academia and industry.
Towards CPU Performance Prediction: New Challenge Benchmark Dataset and Novel Approach
Paper ↗
Abstract
The server central processing unit (CPU) market continues to exhibit robust demand due to the rising global need for computing power. Against this backdrop, CPU benchmark performance prediction is crucial for architecture designers. It offers profound insights for optimizing system designs and significantly reduces the time required for benchmark testing. However, the current research suffers from a lack of a unified, standard and a comprehensive dataset covering various CPU benchmark suites on real machines. Additionally, the traditional simulation-based methods suffer from slow simulation speeds. Furthermore, traditional machine learning approaches not only struggle to process complex features across various hardware configurations but also fall short in achieving sufficient accuracy. To bridge these gaps, we firstly perform a streamlined data preprocessing and reorganize our in-house datasets gathered from a variety CPU models of 4th Generation Intel Xeon Scalable Processors on various benchmark suites. We then propose Nova CPU Performance Predictor (NCPP), a deep learning model with attention mechanisms, specifically designed to predict CPU performance across various benchmarks. Our model effectively captures key hardware configurations affecting performance in across various benchmarks. Moreover, we compare eight mainstream machine learning methods, demonstrating the significant advantages of our model in terms of accuracy and explainability over existing approaches. Finally, our results provide new perspectives and practical strategies for hardware designers. To foster further research and collaboration, we \textit{\textbf{open-source}} the model \url{https://github.com/xiaoman-liu/NCPP}
Global calibration of large-scale photonic integrated circuits
Paper ↗
Abstract
The growing maturity of photonic integrated circuit (PIC) fabrication technology enables the high integration of an increasing number of optical components onto a single chip. With the incremental circuit complexity, the calibration of active phase shifters in a large-scale PIC becomes a crucially important issue. The traditional one-by-one calibration techniques encounter significant hurdles with the propagation of calibration errors, and achieving the decoupling of all phase shifters for independent calibration is not straightforward. To address this issue, we propose a global calibration approach for large-scale PIC. Our method utilizes a custom network to simultaneously learn the nonlinear phase-current relations for all thermo-optic phase shifters on the PIC by minimizing the negative likelihood of the measurement datasets. Moreover, the reflectivities of all static beam splitter components can also be synchronizedly extracted using this calibration method. As an example, a quantum walk PIC with a circuit depth of 12 is calibrated, and a programmable discrete-time quantum walk is experimentally demonstrated. These results will greatly benefit the applications of large-scale PICs in photonic quantum information processing.
Hierarchical Decoupling Capacitor Optimization for Power Distribution Network of 2.5D ICs with Co-Analysis of Frequency and Time Domains Based on Deep Reinforcement Learning
Paper ↗
Abstract
With the growing need for higher memory bandwidth and computation density, 2.5D design, which involves integrating multiple chiplets onto an interposer, emerges as a promising solution. However, this integration introduces significant challenges due to increasing data rates and a large number of I/Os, necessitating advanced optimization of the power distribution networks (PDNs) both on-chip and on-interposer to mitigate the small signal noise and simultaneous switching noise (SSN). Traditional PDN optimization strategies in 2.5D systems primarily focus on reducing impedance by integrating decoupling capacitors (decaps) to lessen small signal noises. Unfortunately, relying solely on frequency-domain analysis has been proven inadequate for addressing coupled SSN, as indicated by our experimental results. In this work, we introduce a novel two-phase optimization flow using deep reinforcement learning to tackle both the on-chip small signal noise and SSN. Initially, we optimize the impedance in the frequency domain to maintain the small signal noise within acceptable limits while avoiding over-design. Subsequently, in the time domain, we refine the PDN to minimize the voltage violation integral (VVI), a more accurate measure of SSN severity. To the best of our knowledge, this is the first dual-domain optimization strategy that simultaneously addresses both the small signal noise and SSN propagation through strategic decap placement in on-chip and on-interposer PDNs, offering a significant step forward in the design of robust PDNs for 2.5D integrated systems.
MG-Verilog: Multi-grained Dataset Towards Enhanced LLM-assisted Verilog Generation
Paper ↗
Abstract
Large Language Models (LLMs) have recently shown promise in streamlining hardware design processes by encapsulating vast amounts of domain-specific data. In addition, they allow users to interact with the design processes through natural language instructions, thus making hardware design more accessible to developers. However, effectively leveraging LLMs in hardware design necessitates providing domain-specific data during inference (e.g., through in-context learning), fine-tuning, or pre-training. Unfortunately, existing publicly available hardware datasets are often limited in size, complexity, or detail, which hinders the effectiveness of LLMs in hardware design tasks. To address this issue, we first propose a set of criteria for creating high-quality hardware datasets that can effectively enhance LLM-assisted hardware design. Based on these criteria, we propose a Multi-Grained-Verilog (MG-Verilog) dataset, which encompasses descriptions at various levels of detail and corresponding code samples. To benefit the broader hardware design community, we have developed an open-source infrastructure that facilitates easy access, integration, and extension of the dataset to meet specific project needs. Furthermore, to fully exploit the potential of the MG-Verilog dataset, which varies in complexity and detail, we introduce a balanced fine-tuning scheme. This scheme serves as a unique use case to leverage the diverse levels of detail provided by the dataset. Extensive experiments demonstrate that the proposed dataset and fine-tuning scheme consistently improve the performance of LLMs in hardware design tasks.
LASSI: An LLM-based Automated Self-Correcting Pipeline for Translating Parallel Scientific Codes
Paper ↗
Abstract
This paper addresses the problem of providing a novel approach to sourcing significant training data for LLMs focused on science and engineering. In particular, a crucial challenge is sourcing parallel scientific codes in the ranges of millions to billions of codes. To tackle this problem, we propose an automated pipeline framework called LASSI, designed to translate between parallel programming languages by bootstrapping existing closed- or open-source LLMs. LASSI incorporates autonomous enhancement through self-correcting loops where errors encountered during the compilation and execution of generated code are fed back to the LLM through guided prompting for debugging and refactoring. We highlight the bi-directional translation of existing GPU benchmarks between OpenMP target offload and CUDA to validate LASSI. The results of evaluating LASSI with different application codes across four LLMs demonstrate the effectiveness of LASSI for generating executable parallel codes, with 80% of OpenMP to CUDA translations and 85% of CUDA to OpenMP translations producing the expected output. We also observe approximately 78% of OpenMP to CUDA translations and 62% of CUDA to OpenMP translations execute within 10% of or at a faster runtime than the original benchmark code in the same language.
Reconfigurable Intelligent Surfaces for 6G Mobile Networks: An Industry R&D Perspective
Paper ↗
Abstract
The reconfigurable intelligent surface (RIS) technology is a potential solution to enhance network capacity and coverage without significant investment in additional infrastructure in 6G networks. This work highlights the interest of the mobile communication industry in RIS, and discusses the development of liquid crystal-based RIS for improved energy efficiency and coverage in the millimeter-wave band. Furthermore, the paper discusses perspectives and insights from an industry R&D point of view, addressing relevant use cases, technical requirements, implementation challenges, and practical considerations for RIS deployment optimization in the context of 6G networks. A hardware design of an RIS with liquid crystal at 28 GHz is presented. A propagation model for RIS as a new part of the system architecture is discussed, with approaches of semi-empirical models, geometric models, and their combination through the application of artificial intelligence/machine learning. Finally, a channel model for deployment optimization and dimensioning is presented, with the findings that a rather large RIS is favorable for coverage improvement, as well as greater attenuation at higher frequencies combined with a smaller RIS size.
ASCENT: Amplifying Power Side-Channel Resilience via Learning & Monte-Carlo Tree Search
Paper ↗
Abstract
Power side-channel (PSC) analysis is pivotal for securing cryptographic hardware. Prior art focused on securing gate-level netlists obtained as-is from chip design automation, neglecting all the complexities and potential side-effects for security arising from the design automation process. That is, automation traditionally prioritizes power, performance, and area (PPA), sidelining security. We propose a "security-first" approach, refining the logic synthesis stage to enhance the overall resilience of PSC countermeasures. We introduce ASCENT, a learning-and-search-based framework that (i) drastically reduces the time for post-design PSC evaluation and (ii) explores the security-vs-PPA design space. Thus, ASCENT enables an efficient exploration of a large number of candidate netlists, leading to an improvement in PSC resilience compared to regular PPA-optimized netlists. ASCENT is up to 120x faster than traditional PSC analysis and yields a 3.11x improvement for PSC resilience of state-of-the-art PSC countermeasures
Meta Large Language Model Compiler: Foundation Models of Compiler Optimization
Paper ↗
Abstract
Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of software engineering and coding tasks. However, their application in the domain of code and compiler optimization remains underexplored. Training LLMs is resource-intensive, requiring substantial GPU hours and extensive data collection, which can be prohibitive. To address this gap, we introduce Meta Large Language Model Compiler (LLM Compiler), a suite of robust, openly available, pre-trained models specifically designed for code optimization tasks. Built on the foundation of Code Llama, LLM Compiler enhances the understanding of compiler intermediate representations (IRs), assembly language, and optimization techniques. The model has been trained on a vast corpus of 546 billion tokens of LLVM-IR and assembly code and has undergone instruction fine-tuning to interpret compiler behavior. LLM Compiler is released under a bespoke commercial license to allow wide reuse and is available in two sizes: 7 billion and 13 billion parameters. We also present fine-tuned versions of the model, demonstrating its enhanced capabilities in optimizing code size and disassembling from x86_64 and ARM assembly back into LLVM-IR. These achieve 77% of the optimising potential of an autotuning search, and 45% disassembly round trip (14% exact match). This release aims to provide a scalable, cost-effective foundation for further research and development in compiler optimization by both academic researchers and industry practitioners.
LayoutCopilot: An LLM-powered Multi-agent Collaborative Framework for Interactive Analog Layout Design
Paper ↗
Abstract
Analog layout design heavily involves interactive processes between humans and design tools. Electronic Design Automation (EDA) tools for this task are usually designed to use scripting commands or visualized buttons for manipulation, especially for interactive automation functionalities, which have a steep learning curve and cumbersome user experience, making a notable barrier to designers' adoption. Aiming to address such a usability issue, this paper introduces LayoutCopilot, a pioneering multi-agent collaborative framework powered by Large Language Models (LLMs) for interactive analog layout design. LayoutCopilot simplifies human-tool interaction by converting natural language instructions into executable script commands, and it interprets high-level design intents into actionable suggestions, significantly streamlining the design process. Experimental results demonstrate the flexibility, efficiency, and accessibility of LayoutCopilot in handling real-world analog designs.
ADO-LLM: Analog Design Bayesian Optimization with In-Context Learning of Large Language Models
Paper ↗
Abstract
Analog circuit design requires substantial human expertise and involvement, which is a significant roadblock to design productivity. Bayesian Optimization (BO), a popular machine learning based optimization strategy, has been leveraged to automate analog design given its applicability across various circuit topologies and technologies. Traditional BO methods employ black box Gaussian Process surrogate models and optimized labeled data queries to find optimization solutions by trading off between exploration and exploitation. However, the search for the optimal design solution in BO can be expensive from both a computational and data usage point of view, particularly for high dimensional optimization problems. This paper presents ADO-LLM, the first work integrating large language models (LLMs) with Bayesian Optimization for analog design optimization. ADO-LLM leverages the LLM's ability to infuse domain knowledge to rapidly generate viable design points to remedy BO's inefficiency in finding high value design areas specifically under the limited design space coverage of the BO's probabilistic surrogate model. In the meantime, sampling of design points evaluated in the iterative BO process provides quality demonstrations for the LLM to generate high quality design points while leveraging infused broad design knowledge. Furthermore, the diversity brought by BO's exploration enriches the contextual understanding of the LLM and allows it to more broadly search in the design space and prevent repetitive and redundant suggestions. We evaluate the proposed framework on two different types of analog circuits and demonstrate notable improvements in design efficiency and effectiveness.
AssertionBench: A Benchmark to Evaluate Large-Language Models for Assertion Generation
Paper ↗
Abstract
Assertions have been the de facto collateral for simulation-based and formal verification of hardware designs for over a decade. The quality of hardware verification, \ie, detection and diagnosis of corner-case design bugs, is critically dependent on the quality of the assertions. There has been a considerable amount of research leveraging a blend of data-driven statistical analysis and static analysis to generate high-quality assertions from hardware design source code and design execution trace data. Despite such concerted effort, all prior research struggles to scale to industrial-scale large designs, generates too many low-quality assertions, often fails to capture subtle and non-trivial design functionality, and does not produce any easy-to-comprehend explanations of the generated assertions to understand assertions' suitability to different downstream validation tasks. Recently, with the advent of Large-Language Models (LLMs), there has been a widespread effort to leverage prompt engineering to generate assertions. However, there is little effort to quantitatively establish the effectiveness and suitability of various LLMs for assertion generation. In this paper, we present AssertionBench, a novel benchmark to evaluate LLMs' effectiveness for assertion generation quantitatively. AssertioBench contains 100 curated Verilog hardware designs from OpenCores and formally verified assertions for each design generated from GoldMine and HARM. We use AssertionBench to compare state-of-the-art LLMs to assess their effectiveness in inferring functionally correct assertions for hardware designs. Our experiments demonstrate how LLMs perform relative to each other, the benefits of using more in-context exemplars in generating a higher fraction of functionally correct assertions, and the significant room for improvement for LLM-based assertion generators.
LLM-Aided Testbench Generation and Bug Detection for Finite-State Machines
Paper ↗
Abstract
This work investigates the potential of tailoring Large Language Models (LLMs), specifically GPT3.5 and GPT4, for the domain of chip testing. A key aspect of chip design is functional testing, which relies on testbenches to evaluate the functionality and coverage of Register-Transfer Level (RTL) designs. We aim to enhance testbench generation by incorporating feedback from commercial-grade Electronic Design Automation (EDA) tools into LLMs. Through iterative feedback from these tools, we refine the testbenches to achieve improved test coverage. Our case studies present promising results, demonstrating that this approach can effectively enhance test coverage. By integrating EDA tool feedback, the generated testbenches become more accurate in identifying potential issues in the RTL design. Furthermore, we extended our study to use this enhanced test coverage framework for detecting bugs in the RTL implementations
PIC2O-Sim: A Physics-Inspired Causality-Aware Dynamic Convolutional Neural Operator for Ultra-Fast Photonic Device FDTD Simulation
Paper ↗
Abstract
The finite-difference time-domain (FDTD) method, which is important in photonic hardware design flow, is widely adopted to solve time-domain Maxwell equations. However, FDTD is known for its prohibitive runtime cost, taking minutes to hours to simulate a single device. Recently, AI has been applied to realize orders-of-magnitude speedup in partial differential equation (PDE) solving. However, AI-based FDTD solvers for photonic devices have not been clearly formulated. Directly applying off-the-shelf models to predict the optical field dynamics shows unsatisfying fidelity and efficiency since the model primitives are agnostic to the unique physical properties of Maxwell equations and lack algorithmic customization. In this work, we thoroughly investigate the synergy between neural operator designs and the physical property of Maxwell equations and introduce a physics-inspired AI-based FDTD prediction framework PIC2O-Sim which features a causality-aware dynamic convolutional neural operator as its backbone model that honors the space-time causality constraints via careful receptive field configuration and explicitly captures the permittivity-dependent light propagation behavior via an efficient dynamic convolution operator. Meanwhile, we explore the trade-offs among prediction scalability, fidelity, and efficiency via a multi-stage partitioned time-bundling technique in autoregressive prediction. Multiple key techniques have been introduced to mitigate iterative error accumulation while maintaining efficiency advantages during autoregressive field prediction. Extensive evaluations on three challenging photonic device simulation tasks have shown the superiority of our PIC2O-Sim method, showing 51.2% lower roll-out prediction error, 23.5 times fewer parameters than state-of-the-art neural operators, providing 300-600x higher simulation speed than an open-source FDTD numerical solver.
Can Low-Rank Knowledge Distillation in LLMs be Useful for Microelectronic Reasoning?
Paper ↗
Abstract
In this work, we present empirical results regarding the feasibility of using offline large language models (LLMs) in the context of electronic design automation (EDA). The goal is to investigate and evaluate a contemporary language model's (Llama-2-7B) ability to function as a microelectronic Q & A expert as well as its reasoning, and generation capabilities in solving microelectronic-related problems. Llama-2-7B was tested across a variety of adaptation methods, including introducing a novel low-rank knowledge distillation (LoRA-KD) scheme. Our experiments produce both qualitative and quantitative results.
Large Reasoning Models for 3D Floorplanning in EDA: Learning from Imperfections
Paper ↗
Abstract
In this paper, we introduce Dreamweaver, which belongs to a new class of auto-regressive decision-making models known as large reasoning models (LRMs). Dreamweaver is designed to improve 3D floorplanning in electronic design automation (EDA) via an architecture that melds advancements in sequence-to-sequence reinforcement learning algorithms. A significant advantage of our approach is its ability to effectively reason over large discrete action spaces, which is essential for handling the numerous potential positions for various functional blocks in floorplanning. Additionally, Dreamweaver demonstrates strong performance even when trained on entirely random trajectories, showcasing its capacity to leverage sub-optimal or non-expert trajectories to enhance its results. This innovative approach contributes to streamlining the integrated circuit (IC) design flow and reducing the high computational costs typically associated with floorplanning. We evaluate its performance against a current state-of-the-art method, highlighting notable improvements.
Cross-Modality Program Representation Learning for Electronic Design Automation with High-Level Synthesis
Paper ↗
Abstract
In recent years, domain-specific accelerators (DSAs) have gained popularity for applications such as deep learning and autonomous driving. To facilitate DSA designs, programmers use high-level synthesis (HLS) to compile a high-level description written in C/C++ into a design with low-level hardware description languages that eventually synthesize DSAs on circuits. However, creating a high-quality HLS design still demands significant domain knowledge, particularly in microarchitecture decisions expressed as \textit{pragmas}. Thus, it is desirable to automate such decisions with the help of machine learning for predicting the quality of HLS designs, requiring a deeper understanding of the program that consists of original code and pragmas. Naturally, these programs can be considered as sequence data. In addition, these programs can be compiled and converted into a control data flow graph (CDFG). But existing works either fail to leverage both modalities or combine the two in shallow or coarse ways. We propose ProgSG, a model that allows interaction between the source code sequence modality and the graph modality in a deep and fine-grained way. To alleviate the scarcity of labeled designs, a pre-training method is proposed based on a suite of compiler's data flow analysis tasks. Experimental results show that ProgSG reduces the RMSE of design performance predictions by up to $22\%$, and identifies designs with an average of $1.10\times$ and $1.26\times$ (up to $8.17\times$ and $13.31\times$) performance improvement in design space exploration (DSE) task compared to HARP and AutoDSE, respectively.
CircuitVAE: Efficient and Scalable Latent Circuit Optimization
Paper ↗
Abstract
Automatically designing fast and space-efficient digital circuits is challenging because circuits are discrete, must exactly implement the desired logic, and are costly to simulate. We address these challenges with CircuitVAE, a search algorithm that embeds computation graphs in a continuous space and optimizes a learned surrogate of physical simulation by gradient descent. By carefully controlling overfitting of the simulation surrogate and ensuring diverse exploration, our algorithm is highly sample-efficient, yet gracefully scales to large problem instances and high sample budgets. We test CircuitVAE by designing binary adders across a large range of sizes, IO timing constraints, and sample budgets. Our method excels at designing large circuits, where other algorithms struggle: compared to reinforcement learning and genetic algorithms, CircuitVAE typically finds 64-bit adders which are smaller and faster using less than half the sample budget. We also find CircuitVAE can design state-of-the-art adders in a real-world chip, demonstrating that our method can outperform commercial tools in a realistic setting.
Brief research of traditional and AI-based models for IMD2 cancellation
Paper ↗
Abstract
Due to the limited isolation of duplexer's stopband transceivers operating in frequency division duplex (FDD) encounter a leakage of the transmitted signal onto the receiving path. Leakage signal with the combination of the second-order nonlinearity of the low noise amplifier (LNA) and receiver down-conversion mixer may lead to second-order intermodulation distortion (IMD2) generation thus greatly reducing the receiver sensitivity. Cancellation of undesirable interferences based on adaptation of traditional models such as memoryless and memory polynomials, spline polynomial based Hammerstein and Wiener-Hammerstein models proved its efficiency in case of well-known nonlinearity nature. On the other hand, currently there is an intensive research in the field of nonlinearity detection by means of neural network (NN) structures. NN-based IMD cancellers are effective in the case of unknown interference content due to their high generalization ability. Therefore, NN approach can provide universal model, which is capable of IMD suppression even in case it is hard to separate intermodulation products generated by LNA, down-conversion mixer or even power amplifier in transmitter path. Nevertheless, such structures suffer from high complexity and can`t be implemented in hardware. Current paper presents low-complexity feed-forward NN-based model, which successfully competes with traditional architectures in terms of computational complexity. The testbench results demonstrate the acceptable performance of provided model, which can be equal to the polynomial nonlinear canceler's performance at a reduced computational cost. Current paper provides performance and required resources comparison of traditional memory polynomial-based scheme and NN-based model for IMD2 cancellation.
LLM-Enhanced Bayesian Optimization for Efficient Analog Layout Constraint Generation
Paper ↗
Abstract
Analog layout synthesis faces significant challenges due to its dependence on manual processes, considerable time requirements, and performance instability. Current Bayesian Optimization (BO)-based techniques for analog layout synthesis, despite their potential for automation, suffer from slow convergence and extensive data needs, limiting their practical application. This paper presents the \texttt{LLANA} framework, a novel approach that leverages Large Language Models (LLMs) to enhance BO by exploiting the few-shot learning abilities of LLMs for more efficient generation of analog design-dependent parameter constraints. Experimental results demonstrate that \texttt{LLANA} not only achieves performance comparable to state-of-the-art (SOTA) BO methods but also enables a more effective exploration of the analog circuit design space, thanks to LLM's superior contextual understanding and learning efficiency. The code is available at https://github.com/dekura/LLANA.
Differentiable Combinatorial Scheduling at Scale
Paper ↗
Abstract
This paper addresses the complex issue of resource-constrained scheduling, an NP-hard problem that spans critical areas including chip design and high-performance computing. Traditional scheduling methods often stumble over scalability and applicability challenges. We propose a novel approach using a differentiable combinatorial scheduling framework, utilizing Gumbel-Softmax differentiable sampling technique. This new technical allows for a fully differentiable formulation of linear programming (LP) based scheduling, extending its application to a broader range of LP formulations. To encode inequality constraints for scheduling tasks, we introduce \textit{constrained Gumbel Trick}, which adeptly encodes arbitrary inequality constraints. Consequently, our method facilitates an efficient and scalable scheduling via gradient descent without the need for training data. Comparative evaluations on both synthetic and real-world benchmarks highlight our capability to significantly improve the optimization efficiency of scheduling, surpassing state-of-the-art solutions offered by commercial and open-source solvers such as CPLEX, Gurobi, and CP-SAT in the majority of the designs.
VHDL-Eval: A Framework for Evaluating Large Language Models in VHDL Code Generation
Paper ↗
Abstract
With the unprecedented advancements in Large Language Models (LLMs), their application domains have expanded to include code generation tasks across various programming languages. While significant progress has been made in enhancing LLMs for popular programming languages, there exists a notable gap in comprehensive evaluation frameworks tailored for Hardware Description Languages (HDLs), particularly VHDL. This paper addresses this gap by introducing a comprehensive evaluation framework designed specifically for assessing LLM performance in VHDL code generation task. We construct a dataset for evaluating LLMs on VHDL code generation task. This dataset is constructed by translating a collection of Verilog evaluation problems to VHDL and aggregating publicly available VHDL problems, resulting in a total of 202 problems. To assess the functional correctness of the generated VHDL code, we utilize a curated set of self-verifying testbenches specifically designed for those aggregated VHDL problem set. We conduct an initial evaluation of different LLMs and their variants, including zero-shot code generation, in-context learning (ICL), and Parameter-efficient fine-tuning (PEFT) methods. Our findings underscore the considerable challenges faced by existing LLMs in VHDL code generation, revealing significant scope for improvement. This study emphasizes the necessity of supervised fine-tuning code generation models specifically for VHDL, offering potential benefits to VHDL designers seeking efficient code generation solutions.
RoutePlacer: An End-to-End Routability-Aware Placer with Graph Neural Network
Paper ↗
Abstract
Placement is a critical and challenging step of modern chip design, with routability being an essential indicator of placement quality. Current routability-oriented placers typically apply an iterative two-stage approach, wherein the first stage generates a placement solution, and the second stage provides non-differentiable routing results to heuristically improve the solution quality. This method hinders jointly optimizing the routability aspect during placement. To address this problem, this work introduces RoutePlacer, an end-to-end routability-aware placement method. It trains RouteGNN, a customized graph neural network, to efficiently and accurately predict routability by capturing and fusing geometric and topological representations of placements. Well-trained RouteGNN then serves as a differentiable approximation of routability, enabling end-to-end gradient-based routability optimization. In addition, RouteGNN can improve two-stage placers as a plug-and-play alternative to external routers. Our experiments on DREAMPlace, an open-source AI4EDA platform, show that RoutePlacer can reduce Total Overflow by up to 16% while maintaining routed wirelength, compared to the state-of-the-art; integrating RouteGNN within two-stage placers leads to a 44% reduction in Total Overflow without compromising wirelength.
Ask-EDA: A Design Assistant Empowered by LLM, Hybrid RAG and Abbreviation De-hallucination
Paper ↗
Abstract
Electronic design engineers are challenged to find relevant information efficiently for a myriad of tasks within design construction, verification and technology development. Large language models (LLM) have the potential to help improve productivity by serving as conversational agents that effectively function as subject-matter experts. In this paper we demonstrate Ask-EDA, a chat agent designed to serve as a 24x7 expert available to provide guidance to design engineers. Ask-EDA leverages LLM, hybrid retrieval augmented generation (RAG) and abbreviation de-hallucination (ADH) techniques to deliver more relevant and accurate responses. We curated three evaluation datasets, namely q2a-100, cmds-100 and abbr-100. Each dataset is tailored to assess a distinct aspect: general design question answering, design command handling and abbreviation resolution. We demonstrated that hybrid RAG offers over a 40% improvement in Recall on the q2a-100 dataset and over a 60% improvement on the cmds-100 dataset compared to not using RAG, while ADH yields over a 70% enhancement in Recall on the abbr-100 dataset. The evaluation results show that Ask-EDA can effectively respond to design-related inquiries.
VerilogReader: LLM-Aided Hardware Test Generation
Paper ↗
Abstract
Test generation has been a critical and labor-intensive process in hardware design verification. Recently, the emergence of Large Language Model (LLM) with their advanced understanding and inference capabilities, has introduced a novel approach. In this work, we investigate the integration of LLM into the Coverage Directed Test Generation (CDG) process, where the LLM functions as a Verilog Reader. It accurately grasps the code logic, thereby generating stimuli that can reach unexplored code branches. We compare our framework with random testing, using our self-designed Verilog benchmark suite. Experiments demonstrate that our framework outperforms random testing on designs within the LLM's comprehension scope. Our work also proposes prompt engineering optimizations to augment LLM's understanding scope and accuracy.
Towards LLM-Powered Verilog RTL Assistant: Self-Verification and Self-Correction
Paper ↗
Abstract
We explore the use of Large Language Models (LLMs) to generate high-quality Register-Transfer Level (RTL) code with minimal human interference. The traditional RTL design workflow requires human experts to manually write high-quality RTL code, which is time-consuming and error-prone. With the help of emerging LLMs, developers can describe their requirements to LLMs which then generate corresponding code in Python, C, Java, and more. Adopting LLMs to generate RTL design in hardware description languages is not trivial, given the complex nature of hardware design and the generated design has to meet the timing and physical constraints. We propose VeriAssist, an LLM-powered programming assistant for Verilog RTL design workflow. VeriAssist takes RTL design descriptions as input and generates high-quality RTL code with corresponding test benches. VeriAssist enables the LLM to self-correct and self-verify the generated code by adopting an automatic prompting system and integrating RTL simulator in the code generation loop. To generate an RTL design, VeriAssist first generates the initial RTL code and corresponding test benches, followed by a self-verification step that walks through the code with test cases to reason the code behavior at different time steps, and finally it self-corrects the code by reading the compilation and simulation results and generating final RTL code that fixes errors in compilation and simulation. This design fully leverages the LLMs' capabilities on multi-turn interaction and chain-of-thought reasoning to improve the quality of the generated code. We evaluate VeriAssist with various benchmark suites and find it significantly improves both syntax and functionality correctness over existing LLM implementations, thus minimizing human intervention and making RTL design more accessible to novice designers.
Efficient Stimuli Generation using Reinforcement Learning in Design Verification
Paper ↗
Abstract
The increasing design complexity of System-on-Chips (SoCs) has led to significant verification challenges, particularly in meeting coverage targets within a timely manner. At present, coverage closure is heavily dependent on constrained random and coverage driven verification methodologies where the randomized stimuli are bounded to verify certain scenarios and to reach coverage goals. This process is said to be exhaustive and to consume a lot of project time. In this paper, a novel methodology is proposed to generate efficient stimuli with the help of Reinforcement Learning (RL) to reach the maximum code coverage of the Design Under Verification (DUV). Additionally, an automated framework is created using metamodeling to generate a SystemVerilog testbench and an RL environment for any given design. The proposed approach is applied to various designs and the produced results proves that the RL agent provides effective stimuli to achieve code coverage faster in comparison with baseline random simulations. Furthermore, various RL agents and reward schemes are analyzed in our work.
Artificial Intelligence Satellite Telecommunication Testbed using Commercial Off-The-Shelf Chipsets
Paper ↗
Abstract
The Artificial Intelligence Satellite Telecommunications Testbed (AISTT), part of the ESA project SPAICE, is focused on the transformation of the satellite payload by using artificial intelligence (AI) and machine learning (ML) methodologies over available commercial off-the-shelf (COTS) AI-capable chips for onboard processing. The objectives include validating artificial intelligence-driven SATCOM scenarios such as interference detection, spectrum sharing, radio resource management, decoding, and beamforming. The study highlights hardware selection and payload architecture. Preliminary results show that ML models significantly improve signal quality, spectral efficiency, and throughput compared to conventional payload. Moreover, the testbed aims to evaluate the performance and the use of AI-capable COTS chips in onboard SATCOM contexts.
RTL-Repo: A Benchmark for Evaluating LLMs on Large-Scale RTL Design Projects
Paper ↗
Abstract
Large Language Models (LLMs) have demonstrated potential in assisting with Register Transfer Level (RTL) design tasks. Nevertheless, there remains to be a significant gap in benchmarks that accurately reflect the complexity of real-world RTL projects. To address this, this paper presents RTL-Repo, a benchmark specifically designed to evaluate LLMs on large-scale RTL design projects. RTL-Repo includes a comprehensive dataset of more than 4000 Verilog code samples extracted from public GitHub repositories, with each sample providing the full context of the corresponding repository. We evaluate several state-of-the-art models on the RTL-Repo benchmark, including GPT-4, GPT-3.5, Starcoder2, alongside Verilog-specific models like VeriGen and RTLCoder, and compare their performance in generating Verilog code for complex projects. The RTL-Repo benchmark provides a valuable resource for the hardware design community to assess and compare LLMs' performance in real-world RTL design scenarios and train LLMs specifically for Verilog code generation in complex, multi-file RTL projects. RTL-Repo is open-source and publicly available on Github.
SynthAI: A Multi Agent Generative AI Framework for Automated Modular HLS Design Generation
Paper ↗
Abstract
In this paper, we introduce SynthAI, a new method for the automated creation of High-Level Synthesis (HLS) designs. SynthAI integrates ReAct agents, Chain-of-Thought (CoT) prompting, web search technologies, and the Retrieval-Augmented Generation (RAG) framework within a structured decision graph. This innovative approach enables the systematic decomposition of complex hardware design tasks into multiple stages and smaller, manageable modules. As a result, SynthAI produces synthesizable designs that closely adhere to user-specified design objectives and functional requirements. We further validate the capabilities of SynthAI through several case studies, highlighting its proficiency in generating complex, multi-module logic designs from a single initial prompt. The SynthAI code is provided via the following repo: \url{https://github.com/sarashs/FPGA_AGI}
Improving Simulation Regression Efficiency using a Machine Learning-based Method in Design Verification
Paper ↗
Abstract
The verification throughput is becoming a major challenge bottleneck, since the complexity and size of SoC designs are still ever increasing. Simply adding more CPU cores and running more tests in parallel will not scale anymore. This paper discusses various methods of improving verification throughput: ranking and the new machine learning (ML) based technology introduced by Cadence i.e. Xcelium ML. Both methods aim at getting comparable coverage in less CPU time by applying more efficient stimulus. Ranking selects specific seeds that simply turned out to come up with the largest coverage in previous simulations, while Xcelium ML generates optimized patterns as a result of finding correlations between randomization points and achieved coverage of previous regressions. Quantified results as well as pros & cons of each approach are discussed in this paper at the example of three actual industry projects. Both Xcelium ML and Ranking methods gave comparable compression & speedup factors around 3 consistently. But the optimized ML based regressions simulated new random scenarios occasionally producing a coverage regain of more than 100%. Finally, a methodology is proposed to use Xcelium ML efficiently throughout the product development.
Large Language Model (LLM) for Standard Cell Layout Design Optimization
Paper ↗
Abstract
Standard cells are essential components of modern digital circuit designs. With process technologies advancing toward 2nm, more routability issues have arisen due to the decreasing number of routing tracks, increasing number and complexity of design rules, and strict patterning rules. The state-of-the-art standard cell design automation framework is able to automatically design standard cell layouts in advanced nodes, but it is still struggling to generate highly competitive Performance-Power-Area (PPA) and routable cell layouts for complex sequential cell designs. Consequently, a novel and efficient methodology incorporating the expertise of experienced human designers to incrementally optimize the PPA of cell layouts is highly necessary and essential. High-quality device clustering, with consideration of netlist topology, diffusion sharing/break and routability in the layouts, can reduce complexity and assist in finding highly competitive PPA, and routable layouts faster. In this paper, we leverage the natural language and reasoning ability of Large Language Model (LLM) to generate high-quality cluster constraints incrementally to optimize the cell layout PPA and debug the routability with ReAct prompting. On a benchmark of sequential standard cells in 2nm, we demonstrate that the proposed method not only achieves up to 19.4% smaller cell area, but also generates 23.5% more LVS/DRC clean cell layouts than previous work. In summary, the proposed method not only successfully reduces cell area by 4.65% on average, but also is able to fix routability in the cell layout designs.
AnalogCoder: Analog Circuit Design via Training-Free Code Generation
Paper ↗
Abstract
Analog circuit design is a significant task in modern chip technology, focusing on the selection of component types, connectivity, and parameters to ensure proper circuit functionality. Despite advances made by Large Language Models (LLMs) in digital circuit design, the complexity and scarcity of data in analog circuitry pose significant challenges. To mitigate these issues, we introduce AnalogCoder, the first training-free LLM agent for designing analog circuits through Python code generation. Firstly, AnalogCoder incorporates a feedback-enhanced flow with tailored domain-specific prompts, enabling the automated and self-correcting design of analog circuits with a high success rate. Secondly, it proposes a circuit tool library to archive successful designs as reusable modular sub-circuits, simplifying composite circuit creation. Thirdly, extensive experiments on a benchmark designed to cover a wide range of analog circuit tasks show that AnalogCoder outperforms other LLM-based methods. It has successfully designed 20 circuits, 5 more than standard GPT-4o. We believe AnalogCoder can significantly improve the labor-intensive chip design process, enabling non-experts to design analog circuits efficiently.
Self-HWDebug: Automation of LLM Self-Instructing for Hardware Security Verification
Paper ↗
Abstract
The rise of instruction-tuned Large Language Models (LLMs) marks a significant advancement in artificial intelligence (AI) (tailored to respond to specific prompts). Despite their popularity, applying such models to debug security vulnerabilities in hardware designs, i.e., register transfer language (RTL) modules, particularly at system-on-chip (SoC) level, presents considerable challenges. One of the main issues lies in the need for precisely designed instructions for pinpointing and mitigating the vulnerabilities, which requires substantial time and expertise from human experts. In response to this challenge, this paper proposes Self-HWDebug, an innovative framework that leverages LLMs to automatically create required debugging instructions. In Self-HWDebug, a set of already identified bugs from the most critical hardware common weakness enumeration (CWE) listings, along with mitigation resolutions, is provided to the framework, followed by prompting the LLMs to generate targeted instructions for such mitigation. The LLM-generated instructions are subsequently used as references to address vulnerabilities within the same CWE category but in totally different designs, effectively demonstrating the framework's ability to extend solutions across related security issues. Self-HWDebug significantly reduces human intervention by using the model's own output to guide debugging. Through comprehensive testing, Self-HWDebug proves not only to reduce experts' effort/time but also to even improve the quality of the debugging process.
Automated Hardware Logic Obfuscation Framework Using GPT
Paper ↗
Abstract
Obfuscation stands as a promising solution for safeguarding hardware intellectual property (IP) against a spectrum of threats including reverse engineering, IP piracy, and tampering. In this paper, we introduce Obfus-chat, a novel framework leveraging Generative Pre-trained Transformer (GPT) models to automate the obfuscation process. The proposed framework accepts hardware design netlists and key sizes as inputs, and autonomously generates obfuscated code tailored to enhance security. To evaluate the effectiveness of our approach, we employ the Trust-Hub Obfuscation Benchmark for comparative analysis. We employed SAT attacks to assess the security of the design, along with functional verification procedures to ensure that the obfuscated design remains consistent with the original. Our results demonstrate the efficacy and efficiency of the proposed framework in fortifying hardware IP against potential threats, thus providing a valuable contribution to the field of hardware security.
SMLP: Symbolic Machine Learning Prover (User Manual)
Paper ↗
Abstract
SMLP: Symbolic Machine Learning Prover an open source tool for exploration and optimization of systems represented by machine learning models. SMLP uses symbolic reasoning for ML model exploration and optimization under verification and stability constraints, based on SMT, constraint and NN solvers. In addition its exploration methods are guided by probabilistic and statistical methods. SMLP is a general purpose tool that requires only data suitable for ML modelling in the csv format (usually samples of the system's input/output). SMLP has been applied at Intel for analyzing and optimizing hardware designs at the analog level. Currently SMLP supports NNs, polynomial and tree models, and uses SMT solvers for reasoning and optimization at the backend, integration of specialized NN solvers is in progress.
Sensitivity Analysis for Active Sampling, with Applications to the Simulation of Analog Circuits
Paper ↗
Abstract
We propose an active sampling flow, with the use-case of simulating the impact of combined variations on analog circuits. In such a context, given the large number of parameters, it is difficult to fit a surrogate model and to efficiently explore the space of design features. By combining a drastic dimension reduction using sensitivity analysis and Bayesian surrogate modeling, we obtain a flexible active sampling flow. On synthetic and real datasets, this flow outperforms the usual Monte-Carlo sampling which often forms the foundation of design space exploration.
LLMs and the Future of Chip Design: Unveiling Security Risks and Building Trust
Paper ↗
Abstract
Chip design is about to be revolutionized by the integration of large language, multimodal, and circuit models (collectively LxMs). While exploring this exciting frontier with tremendous potential, the community must also carefully consider the related security risks and the need for building trust into using LxMs for chip design. First, we review the recent surge of using LxMs for chip design in general. We cover state-of-the-art works for the automation of hardware description language code generation and for scripting and guidance of essential but cumbersome tasks for electronic design automation tools, e.g., design-space exploration, tuning, or designer training. Second, we raise and provide initial answers to novel research questions on critical issues for security and trustworthiness of LxM-powered chip design from both the attack and defense perspectives.
MEIC: Re-thinking RTL Debug Automation using LLMs
Paper ↗
Abstract
The deployment of Large Language Models (LLMs) for code debugging (e.g., C and Python) is widespread, benefiting from their ability to understand and interpret intricate concepts. However, in the semiconductor industry, utilising LLMs to debug Register Transfer Level (RTL) code is still insufficient, largely due to the underrepresentation of RTL-specific data in training sets. This work introduces a novel framework, Make Each Iteration Count (MEIC), which contrasts with traditional one-shot LLM-based debugging methods that heavily rely on prompt engineering, model tuning, and model training. MEIC utilises LLMs in an iterative process to overcome the limitation of LLMs in RTL code debugging, which is suitable for identifying and correcting both syntax and function errors, while effectively managing the uncertainties inherent in LLM operations. To evaluate our framework, we provide an open-source dataset comprising 178 common RTL programming errors. The experimental results demonstrate that the proposed debugging framework achieves fix rate of 93% for syntax errors and 78% for function errors, with up to 48x speedup in debugging processes when compared with experienced engineers. The Repo. of dataset and code: https://anonymous.4open.science/r/Verilog-Auto-Debug-6E7F/.
Scalable and Effective Arithmetic Tree Generation for Adder and Multiplier Designs
Paper ↗
Abstract
Across a wide range of hardware scenarios, the computational efficiency and physical size of the arithmetic units significantly influence the speed and footprint of the overall hardware system. Nevertheless, the effectiveness of prior arithmetic design techniques proves inadequate, as it does not sufficiently optimize speed and area, resulting in a reduced processing rate and larger module size. To boost the arithmetic performance, in this work, we focus on the two most common and fundamental arithmetic modules: adders and multipliers. We cast the design tasks as single-player tree generation games, leveraging reinforcement learning techniques to optimize their arithmetic tree structures. Such a tree generation formulation allows us to efficiently navigate the vast search space and discover superior arithmetic designs that improve computational efficiency and hardware size within just a few hours. For adders, our approach discovers designs of 128-bit adders that achieve Pareto optimality in theoretical metrics. Compared with the state-of-the-art PrefixRL, our method decreases computational delay and hardware size by up to 26% and 30%, respectively. For multipliers, when compared to RL-MUL, our approach increases speed and reduces size by as much as 49% and 45%. Moreover, the inherent flexibility and scalability of our method enable us to deploy our designs into cutting-edge technologies, as we show that they can be seamlessly integrated into 7nm technology. We believe our work will offer valuable insights into hardware design, further accelerating speed and reducing size through the refined search space and our tree generation methodologies. See our introduction video at https://bit.ly/ArithmeticTree. Codes are released at https://github.com/laiyao1/ArithmeticTree.
FloorSet -- a VLSI Floorplanning Dataset with Design Constraints of Real-World SoCs
Paper ↗
Abstract
Floorplanning for systems-on-a-chip (SoCs) and its sub-systems is a crucial and non-trivial step of the physical design flow. It represents a difficult combinatorial optimization problem. A typical large scale SoC with 120 partitions generates a search-space of nearly 10E250. As novel machine learning (ML) approaches emerge to tackle such problems, there is a growing need for a modern benchmark that comprises a large training dataset and performance metrics that better reflect real-world constraints and objectives compared to existing benchmarks. To address this need, we present FloorSet -- two comprehensive datasets of synthetic fixed-outline floorplan layouts that reflect the distribution of real SoCs. Each dataset has 1M training samples and 100 test samples where each sample is a synthetic floor-plan. FloorSet-Prime comprises fully-abutted rectilinear partitions and near-optimal wire-length. A simplified dataset that reflects early design phases, FloorSet-Lite comprises rectangular partitions, with under 5 percent white-space and near-optimal wire-length. Both datasets define hard constraints seen in modern design flows such as shape constraints, edge-affinity, grouping constraints, and pre-placement constraints. FloorSet is intended to spur fundamental research on large-scale constrained optimization problems. Crucially, FloorSet alleviates the core issue of reproducibility in modern ML driven solutions to such problems. FloorSet is available as an open-source repository for the research community.
ILILT: Implicit Learning of Inverse Lithography Technologies
Paper ↗
Abstract
Lithography, transferring chip design masks to the silicon wafer, is the most important phase in modern semiconductor manufacturing flow. Due to the limitations of lithography systems, Extensive design optimizations are required to tackle the design and silicon mismatch. Inverse lithography technology (ILT) is one of the promising solutions to perform pre-fabrication optimization, termed mask optimization. Because of mask optimization problems' constrained non-convexity, numerical ILT solvers rely heavily on good initialization to avoid getting stuck on sub-optimal solutions. Machine learning (ML) techniques are hence proposed to generate mask initialization for ILT solvers with one-shot inference, targeting faster and better convergence during ILT. This paper addresses the question of \textit{whether ML models can directly generate high-quality optimized masks without engaging ILT solvers in the loop}. We propose an implicit learning ILT framework: ILILT, which leverages the implicit layer learning method and lithography-conditioned inputs to ground the model. Trained to understand the ILT optimization procedure, ILILT can outperform the state-of-the-art machine learning solutions, significantly improving efficiency and quality.
EDA Corpus: A Large Language Model Dataset for Enhanced Interaction with OpenROAD
Paper ↗
Abstract
Large language models (LLMs) serve as powerful tools for design, providing capabilities for both task automation and design assistance. Recent advancements have shown tremendous potential for facilitating LLM integration into the chip design process; however, many of these works rely on data that are not publicly available and/or not permissively licensed for use in LLM training and distribution. In this paper, we present a solution aimed at bridging this gap by introducing an open-source dataset tailored for OpenROAD, a widely adopted open-source EDA toolchain. The dataset features over 1000 data points and is structured in two formats: (i) a pairwise set comprised of question prompts with prose answers, and (ii) a pairwise set comprised of code prompts and their corresponding OpenROAD scripts. By providing this dataset, we aim to facilitate LLM-focused research within the EDA domain. The dataset is available at https://github.com/OpenROAD-Assistant/EDA-Corpus.
Natural Language to Verilog: Design of a Recurrent Spiking Neural Network using Large Language Models and ChatGPT
Paper ↗
Abstract
This paper investigates the use of Large Language Models (LLMs) and natural language prompts to generate hardware description code, namely Verilog. Building on our prior work, we employ OpenAI's ChatGPT4 and natural language prompts to synthesize an RTL Verilog module of a programmable recurrent spiking neural network, while also generating test benches to assess the system's correctness. The resultant design was validated in three simple machine learning tasks, the exclusive OR, the IRIS flower classification and the MNIST hand-written digit classification. Furthermore, the design was validated on a Field-Programmable Gate Array (FPGA) and subsequently synthesized in the SkyWater 130 nm technology by using an open-source electronic design automation flow. The design was submitted to Efabless Tiny Tapeout 6.
HLSFactory: A Framework Empowering High-Level Synthesis Datasets for Machine Learning and Beyond
Paper ↗
Abstract
Machine learning (ML) techniques have been applied to high-level synthesis (HLS) flows for quality-of-result (QoR) prediction and design space exploration (DSE). Nevertheless, the scarcity of accessible high-quality HLS datasets and the complexity of building such datasets present challenges. Existing datasets have limitations in terms of benchmark coverage, design space enumeration, vendor extensibility, or lack of reproducible and extensible software for dataset construction. Many works also lack user-friendly ways to add more designs, limiting wider adoption of such datasets. In response to these challenges, we introduce HLSFactory, a comprehensive framework designed to facilitate the curation and generation of high-quality HLS design datasets. HLSFactory has three main stages: 1) a design space expansion stage to elaborate single HLS designs into large design spaces using various optimization directives across multiple vendor tools, 2) a design synthesis stage to execute HLS and FPGA tool flows concurrently across designs, and 3) a data aggregation stage for extracting standardized data into packaged datasets for ML usage. This tripartite architecture ensures broad design space coverage via design space expansion and supports multiple vendor tools. Users can contribute to each stage with their own HLS designs and synthesis results and extend the framework itself with custom frontends and tool flows. We also include an initial set of built-in designs from common HLS benchmarks curated open-source HLS designs. We showcase the versatility and multi-functionality of our framework through seven case studies: I) ML model for QoR prediction; II) Design space sampling; III) Fine-grained parallelism backend speedup; IV) Targeting Intel's HLS flow; V) Adding new auxiliary designs; VI) Integrating published HLS data; VII) HLS tool version regression benchmarking.
Evolutionary Large Language Models for Hardware Security: A Comparative Survey
Paper ↗
Abstract
Automating hardware (HW) security vulnerability detection and mitigation during the design phase is imperative for two reasons: (i) It must be before chip fabrication, as post-fabrication fixes can be costly or even impractical; (ii) The size and complexity of modern HW raise concerns about unknown vulnerabilities compromising CIA triad. While Large Language Models (LLMs) can revolutionize both HW design and testing processes, within the semiconductor context, LLMs can be harnessed to automatically rectify security-relevant vulnerabilities inherent in HW designs. This study explores the seeds of LLM integration in register transfer level (RTL) designs, focusing on their capacity for autonomously resolving security-related vulnerabilities. The analysis involves comparing methodologies, assessing scalability, interpretability, and identifying future research directions. Potential areas for exploration include developing specialized LLM architectures for HW security tasks and enhancing model performance with domain-specific knowledge, leading to reliable automated security measurement and risk mitigation associated with HW vulnerabilities.
Digital ASIC Design with Ongoing LLMs: Strategies and Prospects
Paper ↗
Abstract
The escalating complexity of modern digital systems has imposed significant challenges on integrated circuit (IC) design, necessitating tools that can simplify the IC design flow. The advent of Large Language Models (LLMs) has been seen as a promising development, with the potential to automate the generation of Hardware Description Language (HDL) code, thereby streamlining digital IC design. However, the practical application of LLMs in this area faces substantial hurdles. Notably, current LLMs often generate HDL code with small but critical syntax errors and struggle to accurately convey the high-level semantics of circuit designs. These issues significantly undermine the utility of LLMs for IC design, leading to misinterpretations and inefficiencies. In response to these challenges, this paper presents targeted strategies to harness the capabilities of LLMs for digital ASIC design. We outline approaches that improve the reliability and accuracy of HDL code generation by LLMs. As a practical demonstration of these strategies, we detail the development of a simple three-phase Pulse Width Modulation (PWM) generator. This project, part of the "Efabless AI-Generated Open-Source Chip Design Challenge," successfully passed the Design Rule Check (DRC) and was fabricated, showcasing the potential of LLMs to enhance digital ASIC design. This work underscores the feasibility and benefits of integrating LLMs into the IC design process, offering a novel approach to overcoming the complexities of modern digital systems.
Evaluating LLMs for Hardware Design and Test
Paper ↗
Abstract
Large Language Models (LLMs) have demonstrated capabilities for producing code in Hardware Description Languages (HDLs). However, most of the focus remains on their abilities to write functional code, not test code. The hardware design process consists of both design and test, and so eschewing validation and verification leaves considerable potential benefit unexplored, given that a design and test framework may allow for progress towards full automation of the digital design pipeline. In this work, we perform one of the first studies exploring how a LLM can both design and test hardware modules from provided specifications. Using a suite of 8 representative benchmarks, we examined the capabilities and limitations of the state-of-the-art conversational LLMs when producing Verilog for functional and verification purposes. We taped out the benchmarks on a Skywater 130nm shuttle and received the functional chip.
Skip the Benchmark: Generating System-Level High-Level Synthesis Data using Generative Machine Learning
Paper ↗
Abstract
High-Level Synthesis (HLS) Design Space Exploration (DSE) is a widely accepted approach for efficiently exploring Pareto-optimal and optimal hardware solutions during the HLS process. Several HLS benchmarks and datasets are available for the research community to evaluate their methodologies. Unfortunately, these resources are limited and may not be sufficient for complex, multi-component system-level explorations. Generating new data using existing HLS benchmarks can be cumbersome, given the expertise and time required to effectively generate data for different HLS designs and directives. As a result, synthetic data has been used in prior work to evaluate system-level HLS DSE. However, the fidelity of the synthetic data to real data is often unclear, leading to uncertainty about the quality of system-level HLS DSE. This paper proposes a novel approach, called Vaegan, that employs generative machine learning to generate synthetic data that is robust enough to support complex system-level HLS DSE experiments that would be unattainable with only the currently available data. We explore and adapt a Variational Autoencoder (VAE) and Generative Adversarial Network (GAN) for this task and evaluate our approach using state-of-the-art datasets and metrics. We compare our approach to prior works and show that Vaegan effectively generates synthetic HLS data that closely mirrors the ground truth's distribution.
Efficient Verification of a RADAR SoC Using Formal and Simulation-Based Methods
Paper ↗
Abstract
As the demand for Internet of Things (IoT) and Human-to-Machine Interaction (HMI) increases, modern System-on-Chips (SoCs) offering such solutions are becoming increasingly complex. This intricate design poses significant challenges for verification, particularly when time-to-market is a crucial factor for consumer electronics products. This paper presents a case study based on our work to verify a complex Radio Detection And Ranging (RADAR) based SoC that performs on-chip sensing of human motion with millimetre accuracy. We leverage both formal and simulation-based methods to complement each other and achieve verification sign-off with high confidence. While employing a requirements-driven flow approach, we demonstrate the use of different verification methods to cater to multiple requirements and highlight our know-how from the project. Additionally, we used Machine Learning (ML) based methods, specifically the Xcelium ML tool from Cadence, to improve verification throughput.
Predicting Accurate Hot Spots in a More Than Ten-Thousand-Core GPU with a Million-Time Speedup over FEM Enabled by a Physics-based Learning Algorithm
Paper ↗
Abstract
The classical proper orthogonal decomposition (POD) with the Galerkin projection (GP) has been revised for chip-level thermal simulation of microprocessors with a large number of cores. An ensemble POD-GP methodology (EnPOD-GP) is introduced to significantly improve the training effectiveness and prediction accuracy by dividing a large number of heat sources into heat source blocks (HSBs) each of which may contains one or a very small number of heat sources. Although very accurate, efficient and robust to any power map, EnPOD-GP suffers from intensive training for microprocessors with an enormous number of cores. A local-domain EnPOD-GP model (LEnPOD-GP) is thus proposed to further minimize the training burden. LEnPOD-GP utilizes the concepts of local domain truncation and generic building blocks to reduce the massive training data. LEnPOD-GP has been demonstrated on thermal simulation of NVIDIA Tesla Volta GV100, a GPU with more than 13,000 cores including FP32, FP64, INT32, and Tensor Cores. Due to the domain truncation for LEnPOD-GP, the least square error (LSE) is degraded but is still as small as 1.6% over the entire space and below 1.4% in the device layer when using 4 modes per HSB. When only the maximum temperature of the entire GPU is of interest, LEnPOD-GP offers a computing speed 1.1 million times faster than the FEM with a maximum error near 1.2 degrees over the entire simulation time.
CreativEval: Evaluating Creativity of LLM-Based Hardware Code Generation
Paper ↗
Abstract
Large Language Models (LLMs) have proved effective and efficient in generating code, leading to their utilization within the hardware design process. Prior works evaluating LLMs' abilities for register transfer level code generation solely focus on functional correctness. However, the creativity associated with these LLMs, or the ability to generate novel and unique solutions, is a metric not as well understood, in part due to the challenge of quantifying this quality. To address this research gap, we present CreativeEval, a framework for evaluating the creativity of LLMs within the context of generating hardware designs. We quantify four creative sub-components, fluency, flexibility, originality, and elaboration, through various prompting and post-processing techniques. We then evaluate multiple popular LLMs (including GPT models, CodeLlama, and VeriGen) upon this creativity metric, with results indicating GPT-3.5 as the most creative model in generating hardware designs.
A Multi-Expert Large Language Model Architecture for Verilog Code Generation
Paper ↗
Abstract
Recently, there has been a surging interest in using large language models (LLMs) for Verilog code generation. However, the existing approaches are limited in terms of the quality of the generated Verilog code. To address such limitations, this paper introduces an innovative multi-expert LLM architecture for Verilog code generation (MEV-LLM). Our architecture uniquely integrates multiple LLMs, each specifically fine-tuned with a dataset that is categorized with respect to a distinct level of design complexity. It allows more targeted learning, directly addressing the nuances of generating Verilog code for each category. Empirical evidence from experiments highlights notable improvements in terms of the percentage of generated Verilog outputs that are syntactically and functionally correct. These findings underscore the efficacy of our approach, promising a forward leap in the field of automated hardware design through machine learning.
Late Breaking Results: Fast System Technology Co-Optimization Framework for Emerging Technology Based on Graph Neural Networks
Paper ↗
Abstract
This paper proposes a fast system technology co-optimization (STCO) framework that optimizes power, performance, and area (PPA) for next-generation IC design, addressing the challenges and opportunities presented by novel materials and device architectures. We focus on accelerating the technology level of STCO using AI techniques, by employing graph neural network (GNN)-based approaches for both TCAD simulation and cell library characterization, which are interconnected through a unified compact model, collectively achieving over a 100X speedup over traditional methods. These advancements enable comprehensive STCO iterations with runtime speedups ranging from 1.9X to 14.1X and supports both emerging and traditional technologies.
Beyond Random Inputs: A Novel ML-Based Hardware Fuzzing
Paper ↗
Abstract
Modern computing systems heavily rely on hardware as the root of trust. However, their increasing complexity has given rise to security-critical vulnerabilities that cross-layer at-tacks can exploit. Traditional hardware vulnerability detection methods, such as random regression and formal verification, have limitations. Random regression, while scalable, is slow in exploring hardware, and formal verification techniques are often concerned with manual effort and state explosions. Hardware fuzzing has emerged as an effective approach to exploring and detecting security vulnerabilities in large-scale designs like modern processors. They outperform traditional methods regarding coverage, scalability, and efficiency. However, state-of-the-art fuzzers struggle to achieve comprehensive coverage of intricate hardware designs within a practical timeframe, often falling short of a 70% coverage threshold. We propose a novel ML-based hardware fuzzer, ChatFuzz, to address this challenge. Ourapproach leverages LLMs like ChatGPT to understand processor language, focusing on machine codes and generating assembly code sequences. RL is integrated to guide the input generation process by rewarding the inputs using code coverage metrics. We use the open-source RISCV-based RocketCore processor as our testbed. ChatFuzz achieves condition coverage rate of 75% in just 52 minutes compared to a state-of-the-art fuzzer, which requires a lengthy 30-hour window to reach a similar condition coverage. Furthermore, our fuzzer can attain 80% coverage when provided with a limited pool of 10 simulation instances/licenses within a 130-hour window. During this time, it conducted a total of 199K test cases, of which 6K produced discrepancies with the processor's golden model. Our analysis identified more than 10 unique mismatches, including two new bugs in the RocketCore and discrepancies from the RISC-V ISA Simulator.
LLM-aided explanations of EDA synthesis errors
Paper ↗
Abstract
Training new engineers in digital design is a challenge, particularly when it comes to teaching the complex electronic design automation (EDA) tooling used in this domain. Learners will typically deploy designs in the Verilog and VHDL hardware description languages to Field Programmable Gate Arrays (FPGAs) from Altera (Intel) and Xilinx (AMD) via proprietary closed-source toolchains (Quartus Prime and Vivado, respectively). These tools are complex and difficult to use -- yet, as they are the tools used in industry, they are an essential first step in this space. In this work, we examine how recent advances in artificial intelligence may be leveraged to address aspects of this challenge. Specifically, we investigate if Large Language Models (LLMs), which have demonstrated text comprehension and question-answering capabilities, can be used to generate novice-friendly explanations of compile-time synthesis error messages from Quartus Prime and Vivado. To perform this study we generate 936 error message explanations using three OpenAI LLMs over 21 different buggy code samples. These are then graded for relevance and correctness, and we find that in approximately 71% of cases the LLMs give correct & complete explanations suitable for novice learners.
LLM-aided explanations of EDA synthesis errors
Paper ↗
Abstract
Training new engineers in digital design is a challenge, particularly when it comes to teaching the complex electronic design automation (EDA) tooling used in this domain. Learners will typically deploy designs in the Verilog and VHDL hardware description languages to Field Programmable Gate Arrays (FPGAs) from Altera (Intel) and Xilinx (AMD) via proprietary closed-source toolchains (Quartus Prime and Vivado, respectively). These tools are complex and difficult to use -- yet, as they are the tools used in industry, they are an essential first step in this space. In this work, we examine how recent advances in artificial intelligence may be leveraged to address aspects of this challenge. Specifically, we investigate if Large Language Models (LLMs), which have demonstrated text comprehension and question-answering capabilities, can be used to generate novice-friendly explanations of compile-time synthesis error messages from Quartus Prime and Vivado. To perform this study we generate 936 error message explanations using three OpenAI LLMs over 21 different buggy code samples. These are then graded for relevance and correctness, and we find that in approximately 71% of cases the LLMs give correct & complete explanations suitable for novice learners.
DE-HNN: An effective neural model for Circuit Netlist representation
Paper ↗
Abstract
The run-time for optimization tools used in chip design has grown with the complexity of designs to the point where it can take several days to go through one design cycle which has become a bottleneck. Designers want fast tools that can quickly give feedback on a design. Using the input and output data of the tools from past designs, one can attempt to build a machine learning model that predicts the outcome of a design in significantly shorter time than running the tool. The accuracy of such models is affected by the representation of the design data, which is usually a netlist that describes the elements of the digital circuit and how they are connected. Graph representations for the netlist together with graph neural networks have been investigated for such models. However, the characteristics of netlists pose several challenges for existing graph learning frameworks, due to the large number of nodes and the importance of long-range interactions between nodes. To address these challenges, we represent the netlist as a directed hypergraph and propose a Directional Equivariant Hypergraph Neural Network (DE-HNN) for the effective learning of (directed) hypergraphs. Theoretically, we show that our DE-HNN can universally approximate any node or hyperedge based function that satisfies certain permutation equivariant and invariant properties natural for directed hypergraphs. We compare the proposed DE-HNN with several State-of-the-art (SOTA) machine learning models for (hyper)graphs and netlists, and show that the DE-HNN significantly outperforms them in predicting the outcome of optimized place-and-route tools directly from the input netlists. Our source code and the netlists data used are publicly available at https://github.com/YusuLab/chips.git
Logic Optimization Meets SAT: A Novel Framework for Circuit-SAT Solving
Paper ↗
Abstract
The Circuit Satisfiability (CSAT) problem, a variant of the Boolean Satisfiability (SAT) problem, plays a critical role in integrated circuit design and verification. However, existing SAT solvers, optimized for Conjunctive Normal Form (CNF), often struggle with the intrinsic complexity of circuit structures when directly applied to CSAT instances. To address this challenge, we propose a novel preprocessing framework that leverages advanced logic synthesis techniques and a reinforcement learning (RL) agent to optimize CSAT problem instances. The framework introduces a cost-customized Look-Up Table (LUT) mapping strategy that prioritizes solving efficiency, effectively transforming circuits into simplified forms tailored for SAT solvers. Our method achieves significant runtime reductions across diverse industrial-scale CSAT benchmarks, seamlessly integrating with state-of-the-art SAT solvers. Extensive experimental evaluations demonstrate up to 63\% reduction in solving time compared to conventional approaches, highlighting the potential of EDA-driven innovations to advance SAT-solving capabilities.
Annotating Slack Directly on Your Verilog: Fine-Grained RTL Timing Evaluation for Early Optimization
Paper ↗
Abstract
In digital IC design, compared with post-synthesis netlists or layouts, the early register-transfer level (RTL) stage offers greater optimization flexibility for both designers and EDA tools. However, timing information is typically unavailable at this early stage. Some recent machine learning (ML) solutions propose to predict the total negative slack (TNS) and worst negative slack (WNS) of an entire design at the RTL stage, but the fine-grained timing information of individual registers remains unavailable. In this work, we address the unique challenges of RTL timing prediction and introduce our solution named RTL-Timer. To the best of our knowledge, this is the first fine-grained general timing estimator applicable to any given design. RTL-Timer explores multiple promising RTL representations and proposes customized loss functions to capture the maximum arrival time at register endpoints. RTL-Timer's fine-grained predictions are further applied to guide optimization in a standard synthesis flow. The average results on unknown test designs demonstrate a correlation above 0.89, contributing around 3% WNS and 10% TNS improvement after optimization.
SIP: Autotuning GPU Native Schedules via Stochastic Instruction Perturbation
Paper ↗
Abstract
Large language models (LLMs) have become a significant workload since their appearance. However, they are also computationally expensive as they have billions of parameters and are trained with massive amounts of data. Thus, recent works have developed dedicated CUDA kernels for LLM training and inference instead of relying on compilergenerated ones, so that hardware resources are as fully utilized as possible. In this work, we explore the possibility of GPU native instruction optimization to further push the CUDA kernels to extreme performance. Contrary to prior works, we adopt an automatic optimization approach by defining a search space of possible GPU native instruction schedules, and then we apply stochastic search to perform optimization. Experiments show that SIP can further improve CUDA kernel throughput by automatically discovering better GPU native instruction schedules and the optimized schedules are tested by 10 million test samples.
SIP: Autotuning GPU Native Schedules via Stochastic Instruction Perturbation
Paper ↗
Abstract
Large language models (LLMs) have become a significant workload since their appearance. However, they are also computationally expensive as they have billions of parameters and are trained with massive amounts of data. Thus, recent works have developed dedicated CUDA kernels for LLM training and inference instead of relying on compilergenerated ones, so that hardware resources are as fully utilized as possible. In this work, we explore the possibility of GPU native instruction optimization to further push the CUDA kernels to extreme performance. Contrary to prior works, we adopt an automatic optimization approach by defining a search space of possible GPU native instruction schedules, and then we apply stochastic search to perform optimization. Experiments show that SIP can further improve CUDA kernel throughput by automatically discovering better GPU native instruction schedules and the optimized schedules are tested by 10 million test samples.
DL2Fence: Integrating Deep Learning and Frame Fusion for Enhanced Detection and Localization of Refined Denial-of-Service in Large-Scale NoCs
Paper ↗
Abstract
This study introduces a refined Flooding Injection Rate-adjustable Denial-of-Service (DoS) model for Network-on-Chips (NoCs) and more importantly presents DL2Fence, a novel framework utilizing Deep Learning (DL) and Frame Fusion (2F) for DoS detection and localization. Two Convolutional Neural Networks models for classification and segmentation were developed to detect and localize DoS respectively. It achieves detection and localization accuracies of 95.8% and 91.7%, and precision rates of 98.5% and 99.3% in a 16x16 mesh NoC. The framework's hardware overhead notably decreases by 76.3% when scaling from 8x8 to 16x16 NoCs, and it requires 42.4% less hardware compared to state-of-the-arts. This advancement demonstrates DL2Fence's effectiveness in balancing outstanding detection performance in large-scale NoCs with extremely low hardware overhead.
Thermal Crosstalk Modelling and Compensation Methods for Programmable Photonic Integrated Circuits
Paper ↗
Abstract
Photonic integrated circuits play an important role in the field of optical computing, promising faster and more energy-efficient operations compared to their digital counterparts. This advantage stems from the inherent suitability of optical signals to carry out matrix multiplication. However, even deterministic phenomena such as thermal crosstalk make precise programming of photonic chips a challenging task. Here, we train and experimentally evaluate three models incorporating varying degrees of physics intuition to predict the effect of thermal crosstalk in different locations of an integrated programmable photonic mesh. We quantify the effect of thermal crosstalk by the resonance wavelength shift in the power spectrum of a microring resonator implemented in the chip, achieving modelling errors <0.5 pm. We experimentally validate the models through compensation of the crosstalk-induced wavelength shift. Finally, we evaluate the generalization capabilities of one of the models by employing it to predict and compensate for the effect of thermal crosstalk for parts of the chip it was not trained on, revealing root-mean-square-errors of <2.0 pm.
HDLdebugger: Streamlining HDL debugging with Large Language Models
Paper ↗
Abstract
In the domain of chip design, Hardware Description Languages (HDLs) play a pivotal role. However, due to the complex syntax of HDLs and the limited availability of online resources, debugging HDL codes remains a difficult and time-intensive task, even for seasoned engineers. Consequently, there is a pressing need to develop automated HDL code debugging models, which can alleviate the burden on hardware engineers. Despite the strong capabilities of Large Language Models (LLMs) in generating, completing, and debugging software code, their utilization in the specialized field of HDL debugging has been limited and, to date, has not yielded satisfactory results. In this paper, we propose an LLM-assisted HDL debugging framework, namely HDLdebugger, which consists of HDL debugging data generation via a reverse engineering approach, a search engine for retrieval-augmented generation, and a retrieval-augmented LLM fine-tuning approach. Through the integration of these components, HDLdebugger can automate and streamline HDL debugging for chip design. Our comprehensive experiments, conducted on an HDL code dataset sourced from Huawei, reveal that HDLdebugger outperforms 13 cutting-edge LLM baselines, displaying exceptional effectiveness in HDL code debugging.
Advanced Knowledge Extraction of Physical Design Drawings, Translation and conversion to CAD formats using Deep Learning
Paper ↗
Abstract
The maintenance, archiving and usage of the design drawings is cumbersome in physical form in different industries for longer period. It is hard to extract information by simple scanning of drawing sheets. Converting them to their digital formats such as Computer-Aided Design (CAD), with needed knowledge extraction can solve this problem. The conversion of these machine drawings to its digital form is a crucial challenge which requires advanced techniques. This research proposes an innovative methodology utilizing Deep Learning methods. The approach employs object detection model, such as Yolov7, Faster R-CNN, to detect physical drawing objects present in the images followed by, edge detection algorithms such as canny filter to extract and refine the identified lines from the drawing region and curve detection techniques to detect circle. Also ornaments (complex shapes) within the drawings are extracted. To ensure comprehensive conversion, an Optical Character Recognition (OCR) tool is integrated to identify and extract the text elements from the drawings. The extracted data which includes the lines, shapes and text is consolidated and stored in a structured comma separated values(.csv) file format. The accuracy and the efficiency of conversion is evaluated. Through this, conversion can be automated to help organizations enhance their productivity, facilitate seamless collaborations and preserve valuable design information in a digital format easily accessible. Overall, this study contributes to the advancement of CAD conversions, providing accurate results from the translating process. Future research can focus on handling diverse drawing types, enhanced accuracy in shape and line detection and extraction.
Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework
Paper ↗
Abstract
Recent advances in large language models have demonstrated their potential for automated generation of hardware description language (HDL) code from high-level prompts. Researchers have utilized fine-tuning to enhance the ability of these large language models (LLMs) in the field of Chip Design. However, the lack of Verilog data hinders further improvement in the quality of Verilog generation by LLMs. Additionally, the absence of a Verilog and Electronic Design Automation (EDA) script data augmentation framework significantly increases the time required to prepare the training dataset for LLM trainers. This paper proposes an automated design-data augmentation framework, which generates high-volume and high-quality natural language aligned with Verilog and EDA scripts. For Verilog generation, it translates Verilog files to an abstract syntax tree and then maps nodes to natural language with a predefined template. For Verilog repair, it uses predefined rules to generate the wrong verilog file and then pairs EDA Tool feedback with the right and wrong verilog file. For EDA Script generation, it uses existing LLM(GPT-3.5) to obtain the description of the Script. To evaluate the effectiveness of our data augmentation method, we finetune Llama2-13B and Llama2-7B models using the dataset generated by our augmentation framework. The results demonstrate a significant improvement in the Verilog generation tasks with LLMs. Moreover, the accuracy of Verilog generation surpasses that of the current state-of-the-art open-source Verilog generation model, increasing from 58.8% to 70.6% with the same benchmark. Our 13B model (ChipGPT-FT) has a pass rate improvement compared with GPT-3.5 in Verilog generation and outperforms in EDA script (i.e., SiliconCompiler) generation with only 200 EDA script data.
DG-RePlAce: A Dataflow-Driven GPU-Accelerated Analytical Global Placement Framework for Machine Learning Accelerators
Paper ↗
Abstract
Global placement is a fundamental step in VLSI physical design. The wide use of 2D processing element (PE) arrays in machine learning accelerators poses new challenges of scalability and Quality of Results (QoR) for state-of-the-art academic global placers. In this work, we develop DG-RePlAce, a new and fast GPU-accelerated global placement framework built on top of the OpenROAD infrastructure, which exploits the inherent dataflow and datapath structures of machine learning accelerators. Experimental results with a variety of machine learning accelerators using a commercial 12nm enablement show that, compared with RePlAce (DREAMPlace), our approach achieves an average reduction in routed wirelength by 10% (7%) and total negative slack (TNS) by 31% (34%), with faster global placement and on-par total runtimes relative to DREAMPlace. Empirical studies on the TILOS MacroPlacement Benchmarks further demonstrate that post-route improvements over RePlAce and DREAMPlace may reach beyond the motivating application to machine learning accelerators.
AutoHLS: Learning to Accelerate Design Space Exploration for HLS Designs
Paper ↗
Abstract
High-level synthesis (HLS) is a design flow that leverages modern language features and flexibility, such as complex data structures, inheritance, templates, etc., to prototype hardware designs rapidly. However, exploring various design space parameters can take much time and effort for hardware engineers to meet specific design specifications. This paper proposes a novel framework called AutoHLS, which integrates a deep neural network (DNN) with Bayesian optimization (BO) to accelerate HLS hardware design optimization. Our tool focuses on HLS pragma exploration and operation transformation. It utilizes integrated DNNs to predict synthesizability within a given FPGA resource budget. We also investigate the potential of emerging quantum neural networks (QNNs) instead of classical DNNs for the AutoHLS pipeline. Our experimental results demonstrate up to a 70-fold speedup in exploration time.
Learning-driven Physically-aware Large-scale Circuit Gate Sizing
Paper ↗
Abstract
Gate sizing plays an important role in timing optimization after physical design. Existing machine learning-based gate sizing works cannot optimize timing on multiple timing paths simultaneously and neglect the physical constraint on layouts. They cause sub-optimal sizing solutions and low-efficiency issues when compared with commercial gate sizing tools. In this work, we propose a learning-driven physically-aware gate sizing framework to optimize timing performance on large-scale circuits efficiently. In our gradient descent optimization-based work, for obtaining accurate gradients, a multi-modal gate sizing-aware timing model is achieved via learning timing information on multiple timing paths and physical information on multiple-scaled layouts jointly. Then, gradient generation based on the sizing-oriented estimator and adaptive back-propagation are developed to update gate sizes. Our results demonstrate that our work achieves higher timing performance improvements in a faster way compared with the commercial gate sizing tool.
The Dawn of AI-Native EDA: Opportunities and Challenges of Large Circuit Models
Paper ↗
Abstract
Within the Electronic Design Automation (EDA) domain, AI-driven solutions have emerged as formidable tools, yet they typically augment rather than redefine existing methodologies. These solutions often repurpose deep learning models from other domains, such as vision, text, and graph analytics, applying them to circuit design without tailoring to the unique complexities of electronic circuits. Such an AI4EDA approach falls short of achieving a holistic design synthesis and understanding, overlooking the intricate interplay of electrical, logical, and physical facets of circuit data. This paper argues for a paradigm shift from AI4EDA towards AI-native EDA, integrating AI at the core of the design process. Pivotal to this vision is the development of a multimodal circuit representation learning technique, poised to provide a comprehensive understanding by harmonizing and extracting insights from varied data sources, such as functional specifications, RTL designs, circuit netlists, and physical layouts. We champion the creation of large circuit models (LCMs) that are inherently multimodal, crafted to decode and express the rich semantics and structures of circuit data, thus fostering more resilient, efficient, and inventive design methodologies. Embracing this AI-native philosophy, we foresee a trajectory that transcends the current innovation plateau in EDA, igniting a profound shift-left in electronic design methodology. The envisioned advancements herald not just an evolution of existing EDA tools but a revolution, giving rise to novel instruments of design tools that promise to radically enhance design productivity and inaugurate a new epoch where the optimization of circuit performance, power, and area (PPA) is achieved not incrementally, but through leaps that redefine the benchmarks of electronic systems' capabilities.
From English to ASIC: Hardware Implementation with Large Language Model
Paper ↗
Abstract
In the realm of ASIC engineering, the landscape has been significantly reshaped by the rapid development of LLM, paralleled by an increase in the complexity of modern digital circuits. This complexity has escalated the requirements for HDL coding, necessitating a higher degree of precision and sophistication. However, challenges have been faced due to the less-than-optimal performance of modern language models in generating hardware description code, a situation further exacerbated by the scarcity of the corresponding high-quality code datasets. These challenges have highlighted the gap between the potential of LLMs to revolutionize digital circuit design and their current capabilities in accurately interpreting and implementing hardware specifications. To address these challenges, a strategy focusing on the fine-tuning of the leading-edge nature language model and the reshuffling of the HDL code dataset has been developed. The fine-tuning aims to enhance models' proficiency in generating precise and efficient ASIC design, while the dataset reshuffling is intended to broaden the scope and improve the quality of training material. The model demonstrated significant improvements compared to the base model, with approximately 10% to 20% increase in accuracy across a wide range of temperature for the pass@1 metric. This approach is expected to facilitate a simplified and more efficient LLM-assisted framework for complex circuit design, leveraging their capabilities to meet the sophisticated demands of HDL coding and thus streamlining the ASIC development process.
Less is More: Hop-Wise Graph Attention for Scalable and Generalizable Learning on Circuits
Paper ↗
Abstract
While graph neural networks (GNNs) have gained popularity for learning circuit representations in various electronic design automation (EDA) tasks, they face challenges in scalability when applied to large graphs and exhibit limited generalizability to new designs. These limitations make them less practical for addressing large-scale, complex circuit problems. In this work we propose HOGA, a novel attention-based model for learning circuit representations in a scalable and generalizable manner. HOGA first computes hop-wise features per node prior to model training. Subsequently, the hop-wise features are solely used to produce node representations through a gated self-attention module, which adaptively learns important features among different hops without involving the graph topology. As a result, HOGA is adaptive to various structures across different circuits and can be efficiently trained in a distributed manner. To demonstrate the efficacy of HOGA, we consider two representative EDA tasks: quality of results (QoR) prediction and functional reasoning. Our experimental results indicate that (1) HOGA reduces estimation error over conventional GNNs by 46.76% for predicting QoR after logic synthesis; (2) HOGA improves 10.0% reasoning accuracy over GNNs for identifying functional blocks on unseen gate-level netlists after complex technology mapping; (3) The training time for HOGA almost linearly decreases with an increase in computing resources.
Go Beyond Black-box Policies: Rethinking the Design of Learning Agent for Interpretable and Verifiable HVAC Control
Paper ↗
Abstract
Recent research has shown the potential of Model-based Reinforcement Learning (MBRL) to enhance energy efficiency of Heating, Ventilation, and Air Conditioning (HVAC) systems. However, existing methods rely on black-box thermal dynamics models and stochastic optimizers, lacking reliability guarantees and posing risks to occupant health. In this work, we overcome the reliability bottleneck by redesigning HVAC controllers using decision trees extracted from existing thermal dynamics models and historical data. Our decision tree-based policies are deterministic, verifiable, interpretable, and more energy-efficient than current MBRL methods. First, we introduce a novel verification criterion for RL agents in HVAC control based on domain knowledge. Second, we develop a policy extraction procedure that produces a verifiable decision tree policy. We found that the high dimensionality of the thermal dynamics model input hinders the efficiency of policy extraction. To tackle the dimensionality challenge, we leverage importance sampling conditioned on historical data distributions, significantly improving policy extraction efficiency. Lastly, we present an offline verification algorithm that guarantees the reliability of a control policy. Extensive experiments show that our method saves 68.4% more energy and increases human comfort gain by 14.8% compared to the state-of-the-art method, in addition to an 1127x reduction in computation overhead. Our code and data are available at https://github.com/ryeii/Veri_HVAC
On Robustness and Generalization of ML-Based Congestion Predictors to Valid and Imperceptible Perturbations
Paper ↗
Abstract
There is substantial interest in the use of machine learning (ML)-based techniques throughout the electronic computer-aided design (CAD) flow, particularly methods based on deep learning. However, while deep learning methods have achieved state-of-the-art performance in several applications, recent work has demonstrated that neural networks are generally vulnerable to small, carefully chosen perturbations of their input (e.g. a single pixel change in an image). In this work, we investigate robustness in the context of ML-based EDA tools -- particularly for congestion prediction. As far as we are aware, we are the first to explore this concept in the context of ML-based EDA. We first describe a novel notion of imperceptibility designed specifically for VLSI layout problems defined on netlists and cell placements. Our definition of imperceptibility is characterized by a guarantee that a perturbation to a layout will not alter its global routing. We then demonstrate that state-of-the-art CNN and GNN-based congestion models exhibit brittleness to imperceptible perturbations. Namely, we show that when a small number of cells (e.g. 1%-5% of cells) have their positions shifted such that a measure of global congestion is guaranteed to remain unaffected (e.g. 1% of the design adversarially shifted by 0.001% of the layout space results in a predicted decrease in congestion of up to 90%, while no change in congestion is implied by the perturbation). In other words, the quality of a predictor can be made arbitrarily poor (i.e. can be made to predict that a design is "congestion-free") for an arbitrary input layout. Next, we describe a simple technique to train predictors that improves robustness to these perturbations. Our work indicates that CAD engineers should be cautious when integrating neural network-based mechanisms in EDA flows to ensure robust and high-quality results.
PreRoutGNN for Timing Prediction with Order Preserving Partition: Global Circuit Pre-training, Local Delay Learning and Attentional Cell Modeling
Paper ↗
Abstract
Pre-routing timing prediction has been recently studied for evaluating the quality of a candidate cell placement in chip design. It involves directly estimating the timing metrics for both pin-level (slack, slew) and edge-level (net delay, cell delay), without time-consuming routing. However, it often suffers from signal decay and error accumulation due to the long timing paths in large-scale industrial circuits. To address these challenges, we propose a two-stage approach. First, we propose global circuit training to pre-train a graph auto-encoder that learns the global graph embedding from circuit netlist. Second, we use a novel node updating scheme for message passing on GCN, following the topological sorting sequence of the learned graph embedding and circuit graph. This scheme residually models the local time delay between two adjacent pins in the updating sequence, and extracts the lookup table information inside each cell via a new attention mechanism. To handle large-scale circuits efficiently, we introduce an order preserving partition scheme that reduces memory consumption while maintaining the topological dependencies. Experiments on 21 real world circuits achieve a new SOTA R2 of 0.93 for slack prediction, which is significantly surpasses 0.59 by previous SOTA method. Code will be available at: https://github.com/Thinklab-SJTU/EDA-AI.
Automated Design and Optimization of Distributed Filtering Circuits via Reinforcement Learning
Paper ↗
Abstract
Designing distributed filter circuits (DFCs) is complex and time-consuming, involving setting and optimizing multiple hyperparameters. Traditional optimization methods, such as using the commercial finite element solver HFSS (High-Frequency Structure Simulator) to enumerate all parameter combinations with fixed steps and then simulate each combination, are not only time-consuming and labor-intensive but also rely heavily on the expertise and experience of electronics engineers, making it difficult to adapt to rapidly changing design requirements. Additionally, these commercial tools struggle with precise adjustments when parameters are sensitive to numerical changes, resulting in limited optimization effectiveness. This study proposes a novel end-to-end automated method for DFC design. The proposed method harnesses reinforcement learning (RL) algorithms, eliminating the dependence on the design experience of engineers. Thus, it significantly reduces the subjectivity and constraints associated with circuit design. The experimental findings demonstrate clear improvements in design efficiency and quality when comparing the proposed method with traditional engineer-driven methods. Furthermore, the proposed method achieves superior performance when designing complex or rapidly evolving DFCs, highlighting the substantial potential of RL in circuit design automation. In particular, compared to the existing DFC automation design method CircuitGNN, our method achieves an average performance improvement of 8.72%. Additionally, the execution efficiency of our method is 2000 times higher than CircuitGNN on the CPU and 241 times higher on the GPU.
A Neuro-Symbolic Approach to Multi-Agent RL for Interpretability and Probabilistic Decision Making
Paper ↗
Abstract
Multi-agent reinforcement learning (MARL) is well-suited for runtime decision-making in optimizing the performance of systems where multiple agents coexist and compete for shared resources. However, applying common deep learning-based MARL solutions to real-world problems suffers from issues of interpretability, sample efficiency, partial observability, etc. To address these challenges, we present an event-driven formulation, where decision-making is handled by distributed co-operative MARL agents using neuro-symbolic methods. The recently introduced neuro-symbolic Logical Neural Networks (LNN) framework serves as a function approximator for the RL, to train a rules-based policy that is both logical and interpretable by construction. To enable decision-making under uncertainty and partial observability, we developed a novel probabilistic neuro-symbolic framework, Probabilistic Logical Neural Networks (PLNN), which combines the capabilities of logical reasoning with probabilistic graphical models. In PLNN, the upward/downward inference strategy, inherited from LNN, is coupled with belief bounds by setting the activation function for the logical operator associated with each neural network node to a probability-respecting generalization of the Fr\'echet inequalities. These PLNN nodes form the unifying element that combines probabilistic logic and Bayes Nets, permitting inference for variables with unobserved states. We demonstrate our contributions by addressing key MARL challenges for power sharing in a system-on-chip application.
IR-Aware ECO Timing Optimization Using Reinforcement Learning
Paper ↗
Abstract
Engineering change orders (ECOs) in late stages make minimal design fixes to recover from timing shifts due to excessive IR drops. This paper integrates IR-drop-aware timing analysis and ECO timing optimization using reinforcement learning (RL). The method operates after physical design and power grid synthesis, and rectifies IR-drop-induced timing degradation through gate sizing. It incorporates the Lagrangian relaxation (LR) technique into a novel RL framework, which trains a relational graph convolutional network (R-GCN) agent to sequentially size gates to fix timing violations. The R-GCN agent outperforms a classical LR-only algorithm: in an open 45nm technology, it (a) moves the Pareto front of the delay-power tradeoff curve to the left (b) saves runtime over the prior approaches by running fast inference using trained models, and (c) reduces the perturbation to placement by sizing fewer cells. The RL model is transferable across timing specifications and to unseen designs with fine tuning.
Optimizing Predictive AI in Physical Design Flows with Mini Pixel Batch Gradient Descent
Paper ↗
Abstract
Exploding predictive AI has enabled fast yet effective evaluation and decision-making in modern chip physical design flows. State-of-the-art frameworks typically include the objective of minimizing the mean square error (MSE) between the prediction and the ground truth. We argue the averaging effect of MSE induces limitations in both model training and deployment, and good MSE behavior does not guarantee the capability of these models to assist physical design flows which are likely sabotaged due to a small portion of prediction error. To address this, we propose mini-pixel batch gradient descent (MPGD), a plug-and-play optimization algorithm that takes the most informative entries into consideration, offering probably faster and better convergence. Experiments on representative benchmark suits show the significant benefits of MPGD on various physical design prediction tasks using CNN or Graph-based models.
A Lightweight Inception Boosted U-Net Neural Network for Routability Prediction
Paper ↗
Abstract
As the modern CPU, GPU, and NPU chip design complexity and transistor counts keep increasing, and with the relentless shrinking of semiconductor technology nodes to nearly 1 nanometer, the placement and routing have gradually become the two most pivotal processes in modern very-large-scale-integrated (VLSI) circuit back-end design. How to evaluate routability efficiently and accurately in advance (at the placement and global routing stages) has grown into a crucial research area in the field of artificial intelligence (AI) assisted electronic design automation (EDA). In this paper, we propose a novel U-Net variant model boosted by an Inception embedded module to predict Routing Congestion (RC) and Design Rule Checking (DRC) hotspots. Experimental results on the recently published CircuitNet dataset benchmark show that our proposed method achieves up to 5% (RC) and 20% (DRC) rate reduction in terms of Avg-NRMSE (Average Normalized Root Mean Square Error) compared to the classic architecture. Furthermore, our approach consistently outperforms the prior model on the SSIM (Structural Similarity Index Measure) metric.
LIPSTICK: Corruptibility-Aware and Explainable Graph Neural Network-based Oracle-Less Attack on Logic Locking
Paper ↗
Abstract
In a zero-trust fabless paradigm, designers are increasingly concerned about hardware-based attacks on the semiconductor supply chain. Logic locking is a design-for-trust method that adds extra key-controlled gates in the circuits to prevent hardware intellectual property theft and overproduction. While attackers have traditionally relied on an oracle to attack logic-locked circuits, machine learning attacks have shown the ability to retrieve the secret key even without access to an oracle. In this paper, we first examine the limitations of state-of-the-art machine learning attacks and argue that the use of key hamming distance as the sole model-guiding structural metric is not always useful. Then, we develop, train, and test a corruptibility-aware graph neural network-based oracle-less attack on logic locking that takes into consideration both the structure and the behavior of the circuits. Our model is explainable in the sense that we analyze what the machine learning model has interpreted in the training process and how it can perform a successful attack. Chip designers may find this information beneficial in securing their designs while avoiding incremental fixes.
BetterV: Controlled Verilog Generation with Discriminative Guidance
Paper ↗
Abstract
Due to the growing complexity of modern Integrated Circuits (ICs), there is a need for automated circuit design methods. Recent years have seen rising research in hardware design language generation to facilitate the design process. In this work, we propose a Verilog generation framework, BetterV, which fine-tunes the large language models (LLMs) on processed domain-specific datasets and incorporates generative discriminators for guidance on particular design demands. The Verilog modules are collected, filtered and processed from internet to form a clean and abundant dataset. Instruct-tuning methods are specially designed to fine-tune the LLMs to understand the knowledge about Verilog. Furthermore, data are augmented to enrich the training set and also used to train a generative discriminator on particular downstream task, which leads a guidance for the LLMs to optimize the Verilog implementation. BetterV has the ability to generate syntactically and functionally correct Verilog, which can outperform GPT-4 on the VerilogEval benchmark. With the help of task-specific generative discriminator, BetterV can achieve remarkable improvement on various electronic design automation (EDA) downstream tasks, including the netlist node reduction for synthesis and verification runtime reduction with Boolean Satisfiability (SAT) solving.
SMLP: Symbolic Machine Learning Prover
Paper ↗
Abstract
Symbolic Machine Learning Prover (SMLP) is a tool and a library for system exploration based on data samples obtained by simulating or executing the system on a number of input vectors. SMLP aims at exploring the system based on this data by taking a grey-box approach: SMLP combines statistical methods of data exploration with building and exploring machine learning models in close feedback loop with the system's response, and exploring these models by combining probabilistic and formal methods. SMLP has been applied in industrial setting at Intel for analyzing and optimizing hardware designs at the analog level. SMLP is a general purpose tool and can be applied to systems that can be sampled and modeled by machine learning models.
ChIRAAG: ChatGPT Informed Rapid and Automated Assertion Generation
Paper ↗
Abstract
System Verilog Assertion (SVA) formulation -- a critical yet complex task is a prerequisite in the Assertion Based Verification (ABV) process. Traditionally, SVA formulation involves expert-driven interpretation of specifications, which is time-consuming and prone to human error. Recently, LLM-informed automatic assertion generation is gaining interest. We designed a novel framework called ChIRAAG, based on OpenAI GPT4, to generate SVA from natural language specifications of a design. ChIRAAG constitutes the systematic breakdown of design specifications into a standardized format, further generating assertions from formatted specifications using LLM. Furthermore, we used few test cases to validate the LLM-generated assertions. Automatic feedback of log messages from the simulation tool to the LLM ensures that the framework can generate correct SVAs. In our experiments, only 27% of LLM-generated raw assertions had errors, which was rectified in few iterations based on the simulation log. Our results on OpenTitan designs show that LLMs can streamline and assist engineers in the assertion generation process, reshaping verification workflows.
Fine Time Measurement for the Internet of Things: A Practical Approach Using ESP32
Paper ↗
Abstract
In the world of Internet of Things (IoT), obtaining the physical location of devices has always been a task of great interest for developing increasingly complex location-based services (LBS). That is why in recent years wireless communication standards have been incorporating new additions focused on providing localization mechanisms to technologies widely used in the IoT world, such as Wi-Fi or Bluetooth. In particular, the IEEE 802.11-2016 Wi-Fi standard introduced ranging estimation between two devices through the so-called fine time measurement (FTM) protocol, defined by the IEEE 802.11mc. FTM is not yet widespread in the IoT field, but commercial modules capable of offering this functionality at a reasonable price are starting to appear. In early 2021, the most widespread system on a chip (SOC) family among IoT devices, the ESP32-XX series, added support for this Wi-Fi standard, enabling, for the first time, the use of a standard designed for location-based systems. This article analyzes the performance of this FTM implementation by carrying out and studying several measurement campaigns in different indoor and outdoor scenarios. Additionally, this work proposes an alternative real-time implementation for distance estimation inside the ESP32 using an approach based on machine learning. Such an implementation is successfully validated in a scenario totally different than those considered for the training and test sets. Finally, both the measurement sets and the developed software are available to the scientific community.
LLM4SecHW: Leveraging Domain Specific Large Language Model for Hardware Debugging
Paper ↗
Abstract
This paper presents LLM4SecHW, a novel framework for hardware debugging that leverages domain specific Large Language Model (LLM). Despite the success of LLMs in automating various software development tasks, their application in the hardware security domain has been limited due to the constraints of commercial LLMs and the scarcity of domain specific data. To address these challenges, we propose a unique approach to compile a dataset of open source hardware design defects and their remediation steps, utilizing version control data. This dataset provides a substantial foundation for training machine learning models for hardware. LLM4SecHW employs fine tuning of medium sized LLMs based on this dataset, enabling the identification and rectification of bugs in hardware designs. This pioneering approach offers a reference workflow for the application of fine tuning domain specific LLMs in other research areas. We evaluate the performance of our proposed system on various open source hardware designs, demonstrating its efficacy in accurately identifying and correcting defects. Our work brings a new perspective on automating the quality control process in hardware design.
Hardware Phi-1.5B: A Large Language Model Encodes Hardware Domain Specific Knowledge
Paper ↗
Abstract
In the rapidly evolving semiconductor industry, where research, design, verification, and manufacturing are intricately linked, the potential of Large Language Models to revolutionize hardware design and security verification is immense. The primary challenge, however, lies in the complexity of hardware specific issues that are not adequately addressed by the natural language or software code knowledge typically acquired during the pretraining stage. Additionally, the scarcity of datasets specific to the hardware domain poses a significant hurdle in developing a foundational model. Addressing these challenges, this paper introduces Hardware Phi 1.5B, an innovative large language model specifically tailored for the hardware domain of the semiconductor industry. We have developed a specialized, tiered dataset comprising small, medium, and large subsets and focused our efforts on pretraining using the medium dataset. This approach harnesses the compact yet efficient architecture of the Phi 1.5B model. The creation of this first pretrained, hardware domain specific large language model marks a significant advancement, offering improved performance in hardware design and verification tasks and illustrating a promising path forward for AI applications in the semiconductor sector.
Designing Silicon Brains using LLM: Leveraging ChatGPT for Automated Description of a Spiking Neuron Array
Paper ↗
Abstract
Large language models (LLMs) have made headlines for synthesizing correct-sounding responses to a variety of prompts, including code generation. In this paper, we present the prompts used to guide ChatGPT4 to produce a synthesizable and functional verilog description for the entirety of a programmable Spiking Neuron Array ASIC. This design flow showcases the current state of using ChatGPT4 for natural language driven hardware design. The AI-generated design was verified in simulation using handcrafted testbenches and has been submitted for fabrication in Skywater 130nm through Tiny Tapeout 5 using an open-source EDA flow.
SpecLLM: Exploring Generation and Review of VLSI Design Specification with Large Language Model
Paper ↗
Abstract
The development of architecture specifications is an initial and fundamental stage of the integrated circuit (IC) design process. Traditionally, architecture specifications are crafted by experienced chip architects, a process that is not only time-consuming but also error-prone. Mistakes in these specifications may significantly affect subsequent stages of chip design. Despite the presence of advanced electronic design automation (EDA) tools, effective solutions to these specification-related challenges remain scarce. Since writing architecture specifications is naturally a natural language processing (NLP) task, this paper pioneers the automation of architecture specification development with the advanced capabilities of large language models (LLMs). Leveraging our definition and dataset, we explore the application of LLMs in two key aspects of architecture specification development: (1) Generating architecture specifications, which includes both writing specifications from scratch and converting RTL code into detailed specifications. (2) Reviewing existing architecture specifications. We got promising results indicating that LLMs may revolutionize how these critical specification documents are developed in IC design nowadays. By reducing the effort required, LLMs open up new possibilities for efficiency and accuracy in this crucial aspect of chip design.
Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization
Paper ↗
Abstract
Logic synthesis, a pivotal stage in chip design, entails optimizing chip specifications encoded in hardware description languages like Verilog into highly efficient implementations using Boolean logic gates. The process involves a sequential application of logic minimization heuristics (``synthesis recipe"), with their arrangement significantly impacting crucial metrics such as area and delay. Addressing the challenge posed by the broad spectrum of design complexities - from variations of past designs (e.g., adders and multipliers) to entirely novel configurations (e.g., innovative processor instructions) - requires a nuanced `synthesis recipe` guided by human expertise and intuition. This study conducts a thorough examination of learning and search techniques for logic synthesis, unearthing a surprising revelation: pre-trained agents, when confronted with entirely novel designs, may veer off course, detrimentally affecting the search trajectory. We present ABC-RL, a meticulously tuned $\alpha$ parameter that adeptly adjusts recommendations from pre-trained agents during the search process. Computed based on similarity scores through nearest neighbor retrieval from the training dataset, ABC-RL yields superior synthesis recipes tailored for a wide array of hardware designs. Our findings showcase substantial enhancements in the Quality-of-result (QoR) of synthesized circuits, boasting improvements of up to 24.8% compared to state-of-the-art techniques. Furthermore, ABC-RL achieves an impressive up to 9x reduction in runtime (iso-QoR) when compared to current state-of-the-art methodologies.
BoolGebra: Attributed Graph-learning for Boolean Algebraic Manipulation
Paper ↗
Abstract
Boolean algebraic manipulation is at the core of logic synthesis in Electronic Design Automation (EDA) design flow. Existing methods struggle to fully exploit optimization opportunities, and often suffer from an explosive search space and limited scalability efficiency. This work presents BoolGebra, a novel attributed graph-learning approach for Boolean algebraic manipulation that aims to improve fundamental logic synthesis. BoolGebra incorporates Graph Neural Networks (GNNs) and takes initial feature embeddings from both structural and functional information as inputs. A fully connected neural network is employed as the predictor for direct optimization result predictions, significantly reducing the search space and efficiently locating the optimization space. The experiments involve training the BoolGebra model w.r.t design-specific and cross-design inferences using the trained model, where BoolGebra demonstrates generalizability for cross-design inference and its potential to scale from small, simple training datasets to large, complex inference datasets. Finally, BoolGebra is integrated with existing synthesis tool ABC to perform end-to-end logic minimization evaluation w.r.t SOTA baselines.
Using LLM such as ChatGPT for Designing and Implementing a RISC Processor: Execution,Challenges and Limitations
Paper ↗
Abstract
This paper discusses the feasibility of using Large Language Models LLM for code generation with a particular application in designing an RISC. The paper also reviews the associated steps such as parsing, tokenization, encoding, attention mechanism, sampling the tokens and iterations during code generation. The generated code for the RISC components is verified through testbenches and hardware implementation on a FPGA board. Four metric parameters Correct output on the first iteration, Number of errors embedded in the code, Number of trials required to achieve the code and Failure to generate the code after three iterations, are used to compare the efficiency of using LLM in programming. In all the cases, the generated code had significant errors and human intervention was always required to fix the bugs. LLM can therefore be used to complement a programmer code design.
VeriBug: An Attention-based Framework for Bug-Localization in Hardware Designs
Paper ↗
Abstract
In recent years, there has been an exponential growth in the size and complexity of System-on-Chip designs targeting different specialized applications. The cost of an undetected bug in these systems is much higher than in traditional processor systems as it may imply the loss of property or life. The problem is further exacerbated by the ever-shrinking time-to-market and ever-increasing demand to churn out billions of devices. Despite decades of research in simulation and formal methods for debugging and verification, it is still one of the most time-consuming and resource intensive processes in contemporary hardware design cycle. In this work, we propose VeriBug, which leverages recent advances in deep learning to accelerate debugging at the Register-Transfer Level and generates explanations of likely root causes. First, VeriBug uses control-data flow graph of a hardware design and learns to execute design statements by analyzing the context of operands and their assignments. Then, it assigns an importance score to each operand in a design statement and uses that score for generating explanations for failures. Finally, VeriBug produces a heatmap highlighting potential buggy source code portions. Our experiments show that VeriBug can achieve an average bug localization coverage of 82.5% on open-source designs and different types of injected bugs.
Herding LLaMaS: Using LLMs as an OS Module
Paper ↗
Abstract
Computer systems are becoming increasingly heterogeneous with the emergence of new memory technologies and compute devices. GPUs alongside CPUs have become commonplace and CXL is poised to be a mainstay of cloud systems. The operating system is responsible for managing these hardware resources, requiring modification every time a new device is released. Years of research and development are sunk into tuning the OS for high performance with each new heterogeneous device. With the recent explosion in memory technologies and domain-specific accelerators, it would be beneficial to have an OS that could provide high performance for new devices without significant effort. We propose LLaMaS which can adapt to new devices easily. LLaMaS uses Large Language Models (LLMs) to extract the useful features of new devices from their textual description and uses these features to make operating system decisions at runtime. Adding support to LLaMaS for a new device is as simple as describing the system and new device properties in plaintext. LLaMaS reduces the burden on system administrators to enable easy integration of new devices into production systems. Preliminary evaluation using ChatGPT shows that LLMs are capable of extracting device features from text and make correct OS decisions based on those features.
Uncertainty-Aware Hardware Trojan Detection Using Multimodal Deep Learning
Paper ↗
Abstract
The risk of hardware Trojans being inserted at various stages of chip production has increased in a zero-trust fabless era. To counter this, various machine learning solutions have been developed for the detection of hardware Trojans. While most of the focus has been on either a statistical or deep learning approach, the limited number of Trojan-infected benchmarks affects the detection accuracy and restricts the possibility of detecting zero-day Trojans. To close the gap, we first employ generative adversarial networks to amplify our data in two alternative representation modalities, a graph and a tabular, ensuring that the dataset is distributed in a representative manner. Further, we propose a multimodal deep learning approach to detect hardware Trojans and evaluate the results from both early fusion and late fusion strategies. We also estimate the uncertainty quantification metrics of each prediction for risk-aware decision-making. The outcomes not only confirms the efficacy of our proposed hardware Trojan detection method but also opens a new door for future studies employing multimodality and uncertainty quantification to address other hardware security challenges.
Hierarchical Source-to-Post-Route QoR Prediction in High-Level Synthesis with GNNs
Paper ↗
Abstract
High-level synthesis (HLS) notably speeds up the hardware design process by avoiding RTL programming. However, the turnaround time of HLS increases significantly when post-route quality of results (QoR) are considered during optimization. To tackle this issue, we propose a hierarchical post-route QoR prediction approach for FPGA HLS, which features: (1) a modeling flow that directly estimates latency and post-route resource usage from C/C++ programs; (2) a graph construction method that effectively represents the control and data flow graph of source code and effects of HLS pragmas; and (3) a hierarchical GNN training and prediction method capable of capturing the impact of loop hierarchies. Experimental results show that our method presents a prediction error of less than 10% for different types of QoR metrics, which gains tremendous improvement compared with the state-of-the-art GNN methods. By adopting our proposed methodology, the runtime for design space exploration in HLS is shortened to tens of minutes and the achieved ADRS is reduced to 6.91% on average.
Zero-Shot RTL Code Generation with Attention Sink Augmented Large Language Models
Paper ↗
Abstract
The design and optimization of hardware have traditionally been resource-intensive, demanding considerable expertise and dependence on established design automation tools. This paper discusses the possibility of exploiting large language models to streamline the code generation process in hardware design. In contrast to earlier studies, this paper aims to use large language models that accepts high-level design specifications through a single prompt to generate corresponding Register-Transfer Level (RTL) code. The ability to use large language models on RTL code generation not only expedites design iteration cycles but also facilitates the exploration of design spaces that have computational challenges for conventional techniques. Through our evaluation, we demonstrate the shortcoming of existing attention mechanisms, and present the abilities of language models to produce functional, optimized, and industry-standard compliant RTL code when a novel attention mechanism is used. These findings underscore the expanding role of large language models in shaping the future landscape of architectural exploration and automation in hardware design.
Novel End-to-End Production-Ready Machine Learning Flow for Nanolithography Modeling and Correction
Paper ↗
Abstract
Optical lithography is the main enabler to semiconductor manufacturing. It requires extensive processing to perform the Resolution Enhancement Techniques (RETs) required to transfer the design data to a working Integrated Circuits (ICs). The processing power and computational runtime for RETs tasks is ever increasing due to the continuous reduction of the feature size and the expansion of the chip area. State-of-the-art research sought Machine Learning (ML) technologies to reduce runtime and computational power, however they are still not used in production yet. In this study, we analyze the reasons holding back ML computational lithography from being production ready and present a novel highly scalable end-to-end flow that enables production ready ML-RET correction.
Design Space Exploration of Approximate Computing Techniques with a Reinforcement Learning Approach
Paper ↗
Abstract
Approximate Computing (AxC) techniques have become increasingly popular in trading off accuracy for performance gains in various applications. Selecting the best AxC techniques for a given application is challenging. Among proposed approaches for exploring the design space, Machine Learning approaches such as Reinforcement Learning (RL) show promising results. In this paper, we proposed an RL-based multi-objective Design Space Exploration strategy to find the approximate versions of the application that balance accuracy degradation and power and computation time reduction. Our experimental results show a good trade-off between accuracy degradation and decreased power and computation time for some benchmarks.
LLM4EDA: Emerging Progress in Large Language Models for Electronic Design Automation
Paper ↗
Abstract
Driven by Moore's Law, the complexity and scale of modern chip design are increasing rapidly. Electronic Design Automation (EDA) has been widely applied to address the challenges encountered in the full chip design process. However, the evolution of very large-scale integrated circuits has made chip design time-consuming and resource-intensive, requiring substantial prior expert knowledge. Additionally, intermediate human control activities are crucial for seeking optimal solutions. In system design stage, circuits are usually represented with Hardware Description Language (HDL) as a textual format. Recently, Large Language Models (LLMs) have demonstrated their capability in context understanding, logic reasoning and answer generation. Since circuit can be represented with HDL in a textual format, it is reasonable to question whether LLMs can be leveraged in the EDA field to achieve fully automated chip design and generate circuits with improved power, performance, and area (PPA). In this paper, we present a systematic study on the application of LLMs in the EDA field, categorizing it into the following cases: 1) assistant chatbot, 2) HDL and script generation, and 3) HDL verification and analysis. Additionally, we highlight the future research direction, focusing on applying LLMs in logic synthesis, physical design, multi-modal feature extraction and alignment of circuits. We collect relevant papers up-to-date in this field via the following link: https://github.com/Thinklab-SJTU/Awesome-LLM4EDA.
RTLCoder: Fully Open-Source and Efficient LLM-Assisted RTL Code Generation Technique
Paper ↗
Abstract
The automatic generation of RTL code (e.g., Verilog) using natural language instructions and large language models (LLMs) has attracted significant research interest recently. However, most existing approaches heavily rely on commercial LLMs such as ChatGPT, while open-source LLMs tailored for this specific design generation task exhibit notably inferior performance. The absence of high-quality open-source solutions restricts the flexibility and data privacy of this emerging technique. In this study, we present a new customized LLM solution with a modest parameter count of only 7B, achieving better performance than GPT-3.5 on all representative benchmarks for RTL code generation. Especially, it outperforms GPT-4 in VerilogEval Machine benchmark. This remarkable balance between accuracy and efficiency is made possible by leveraging our new RTL code dataset and a customized LLM algorithm, both of which have been made fully open-source. Furthermore, we have successfully quantized our LLM to 4-bit with a total size of 4GB, enabling it to function on a single laptop with only slight performance degradation. This efficiency allows the RTL generator to serve as a local assistant for engineers, ensuring all design privacy concerns are addressed.
RTLCoder: Outperforming GPT-3.5 in Design RTL Generation with Our Open-Source Dataset and Lightweight Solution
Paper ↗
Abstract
The automatic generation of RTL code (e.g., Verilog) using natural language instructions and large language models (LLMs) has attracted significant research interest recently. However, most existing approaches heavily rely on commercial LLMs such as ChatGPT, while open-source LLMs tailored for this specific design generation task exhibit notably inferior performance. The absence of high-quality open-source solutions restricts the flexibility and data privacy of this emerging technique. In this study, we present a new customized LLM solution with a modest parameter count of only 7B, achieving better performance than GPT-3.5 on all representative benchmarks for RTL code generation. Especially, it outperforms GPT-4 in VerilogEval Machine benchmark. This remarkable balance between accuracy and efficiency is made possible by leveraging our new RTL code dataset and a customized LLM algorithm, both of which have been made fully open-source.
A Machine Learning Approach Towards SKILL Code Autocompletion
Paper ↗
Abstract
As Moore's Law continues to increase the complexity of electronic systems, Electronic Design Automation (EDA) must advance to meet global demand. An important example of an EDA technology is SKILL, a scripting language used to customize and extend EDA software. Recently, code generation models using the transformer architecture have achieved impressive results in academic settings and have even been used in commercial developer tools to improve developer productivity. To the best of our knowledge, this study is the first to apply transformers to SKILL code autocompletion towards improving the productivity of hardware design engineers. In this study, a novel, data-efficient methodology for generating SKILL code is proposed and experimentally validated. More specifically, we propose a novel methodology for (i) creating a high-quality SKILL dataset with both unlabeled and labeled data, (ii) a training strategy where T5 models pre-trained on general programming language code are fine-tuned on our custom SKILL dataset using unsupervised and supervised learning, and (iii) evaluating synthesized SKILL code. We show that models trained using the proposed methodology outperform baselines in terms of human-judgment score and BLEU score. A major challenge faced was the extremely small amount of available SKILL code data that can be used to train a transformer model to generate SKILL code. Despite our validated improvements, the extremely small dataset available to us was still not enough to train a model that can reliably autocomplete SKILL code. We discuss this and other limitations as well as future work that could address these limitations.
EDALearn: A Comprehensive RTL-to-Signoff EDA Benchmark for Democratized and Reproducible ML for EDA Research
Paper ↗
Abstract
The application of Machine Learning (ML) in Electronic Design Automation (EDA) for Very Large-Scale Integration (VLSI) design has garnered significant research attention. Despite the requirement for extensive datasets to build effective ML models, most studies are limited to smaller, internally generated datasets due to the lack of comprehensive public resources. In response, we introduce EDALearn, the first holistic, open-source benchmark suite specifically for ML tasks in EDA. This benchmark suite presents an end-to-end flow from synthesis to physical implementation, enriching data collection across various stages. It fosters reproducibility and promotes research into ML transferability across different technology nodes. Accommodating a wide range of VLSI design instances and sizes, our benchmark aptly represents the complexity of contemporary VLSI designs. Additionally, we provide an in-depth data analysis, enabling users to fully comprehend the attributes and distribution of our data, which is essential for creating efficient ML models. Our contributions aim to encourage further advances in the ML-EDA domain.
On-sensor Printed Machine Learning Classification via Bespoke ADC and Decision Tree Co-Design
Paper ↗
Abstract
Printed electronics (PE) technology provides cost-effective hardware with unmet customization, due to their low non-recurring engineering and fabrication costs. PE exhibit features such as flexibility, stretchability, porosity, and conformality, which make them a prominent candidate for enabling ubiquitous computing. Still, the large feature sizes in PE limit the realization of complex printed circuits, such as machine learning classifiers, especially when processing sensor inputs is necessary, mainly due to the costly analog-to-digital converters (ADCs). To this end, we propose the design of fully customized ADCs and present, for the first time, a co-design framework for generating bespoke Decision Tree classifiers. Our comprehensive evaluation shows that our co-design enables self-powered operation of on-sensor printed classifiers in all benchmark cases.
Advanced Large Language Model (LLM)-Driven Verilog Development: Enhancing Power, Performance, and Area Optimization in Code Synthesis
Paper ↗
Abstract
The increasing use of Advanced Language Models (ALMs) in diverse sectors, particularly due to their impressive capability to generate top-tier content following linguistic instructions, forms the core of this investigation. This study probes into ALMs' deployment in electronic hardware design, with a specific emphasis on the synthesis and enhancement of Verilog programming. We introduce an innovative framework, crafted to assess and amplify ALMs' productivity in this niche. The methodology commences with the initial crafting of Verilog programming via ALMs, succeeded by a distinct dual-stage refinement protocol. The premier stage prioritizes augmenting the code's operational and linguistic precision, while the latter stage is dedicated to aligning the code with Power-Performance-Area (PPA) benchmarks, a pivotal component in proficient hardware design. This bifurcated strategy, merging error remediation with PPA enhancement, has yielded substantial upgrades in the caliber of ALM-created Verilog programming. Our framework achieves an 81.37% rate in linguistic accuracy and 62.0% in operational efficacy in programming synthesis, surpassing current leading-edge techniques, such as 73% in linguistic accuracy and 46% in operational efficacy. These findings illuminate ALMs' aptitude in tackling complex technical domains and signal a positive shift in the mechanization of hardware design operations.
RTLFixer: Automatically Fixing RTL Syntax Errors with Large Language Models
Paper ↗
Abstract
This paper presents RTLFixer, a novel framework enabling automatic syntax errors fixing for Verilog code with Large Language Models (LLMs). Despite LLM's promising capabilities, our analysis indicates that approximately 55% of errors in LLM-generated Verilog are syntax-related, leading to compilation failures. To tackle this issue, we introduce a novel debugging framework that employs Retrieval-Augmented Generation (RAG) and ReAct prompting, enabling LLMs to act as autonomous agents in interactively debugging the code with feedback. This framework demonstrates exceptional proficiency in resolving syntax errors, successfully correcting about 98.5% of compilation errors in our debugging dataset, comprising 212 erroneous implementations derived from the VerilogEval benchmark. Our method leads to 32.3% and 10.1% increase in pass@1 success rates in the VerilogEval-Machine and VerilogEval-Human benchmarks, respectively.
Practical Layout-Aware Analog/Mixed-Signal Design Automation with Bayesian Neural Networks
Paper ↗
Abstract
The high simulation cost has been a bottleneck of practical analog/mixed-signal design automation. Many learning-based algorithms require thousands of simulated data points, which is impractical for expensive to simulate circuits. We propose a learning-based algorithm that can be trained using a small amount of data and, therefore, scalable to tasks with expensive simulations. Our efficient algorithm solves the post-layout performance optimization problem where simulations are known to be expensive. Our comprehensive study also solves the schematic-level sizing problem. For efficient optimization, we utilize Bayesian Neural Networks as a regression model to approximate circuit performance. For layout-aware optimization, we handle the problem as a multi-fidelity optimization problem and improve efficiency by exploiting the correlations from cheaper evaluations. We present three test cases to demonstrate the efficiency of our algorithms. Our tests prove that the proposed approach is more efficient than conventional baselines and state-of-the-art algorithms.
Verilog-to-PyG -- A Framework for Graph Learning and Augmentation on RTL Designs
Paper ↗
Abstract
The complexity of modern hardware designs necessitates advanced methodologies for optimizing and analyzing modern digital systems. In recent times, machine learning (ML) methodologies have emerged as potent instruments for assessing design quality-of-results at the Register-Transfer Level (RTL) or Boolean level, aiming to expedite design exploration of advanced RTL configurations. In this presentation, we introduce an innovative open-source framework that translates RTL designs into graph representation foundations, which can be seamlessly integrated with the PyTorch Geometric graph learning platform. Furthermore, the Verilog-to-PyG (V2PYG) framework is compatible with the open-source Electronic Design Automation (EDA) toolchain OpenROAD, facilitating the collection of labeled datasets in an utterly open-source manner. Additionally, we will present novel RTL data augmentation methods (incorporated in our framework) that enable functional equivalent design augmentation for the construction of an extensive graph-based RTL design database. Lastly, we will showcase several using cases of V2PYG with detailed scripting examples. V2PYG can be found at \url{https://yu-maryland.github.io/Verilog-to-PyG/}.
AutoChip: Automating HDL Generation Using LLM Feedback
Paper ↗
Abstract
Traditionally, designs are written in Verilog hardware description language (HDL) and debugged by hardware engineers. While this approach is effective, it is time-consuming and error-prone for complex designs. Large language models (LLMs) are promising in automating HDL code generation. LLMs are trained on massive datasets of text and code, and they can learn to generate code that compiles and is functionally accurate. We aim to evaluate the ability of LLMs to generate functionally correct HDL models. We build AutoChip by combining the interactive capabilities of LLMs and the output from Verilog simulations to generate Verilog modules. We start with a design prompt for a module and the context from compilation errors and debugging messages, which highlight differences between the expected and actual outputs. This ensures that accurate Verilog code can be generated without human intervention. We evaluate AutoChip using problem sets from HDLBits. We conduct a comprehensive analysis of the AutoChip using several LLMs and problem categories. The results show that incorporating context from compiler tools, such as Icarus Verilog, improves the effectiveness, yielding 24.20% more accurate Verilog. We release our evaluation scripts and datasets as open-source contributions at the following link https://github.com/shailja-thakur/AutoChip.
Leveraging High-Level Synthesis and Large Language Models to Generate, Simulate, and Deploy a Uniform Random Number Generator Hardware Design
Paper ↗
Abstract
We present a new high-level synthesis methodology for using large language model tools to generate hardware designs. The methodology uses exclusively open-source tools excluding the large language model. As a case study, we use our methodology to generate a permuted congruential random number generator design with a wishbone interface. We verify the functionality and quality of the random number generator design using large language model-generated simulations and the Dieharder randomness test suite. We document all the large language model chat logs, Python scripts, Verilog scripts, and simulation results used in the case study. We believe that our method of hardware design generation coupled with the open source silicon 130 nm design tools will revolutionize application-specific integrated circuit design. Our methodology significantly lowers the bar to entry when building domain-specific computing accelerators for the Internet of Things and proof of concept prototypes for later fabrication in more modern process nodes.
Toward Reinforcement Learning-based Rectilinear Macro Placement Under Human Constraints
Paper ↗
Abstract
Macro placement is a critical phase in chip design, which becomes more intricate when involving general rectilinear macros and layout areas. Furthermore, macro placement that incorporates human-like constraints, such as design hierarchy and peripheral bias, has the potential to significantly reduce the amount of additional manual labor required from designers. This study proposes a methodology that leverages an approach suggested by Google's Circuit Training (G-CT) to provide a learning-based macro placer that not only supports placing rectilinear cases, but also adheres to crucial human-like design principles. Our experimental results demonstrate the effectiveness of our framework in achieving power-performance-area (PPA) metrics and in obtaining placements of high quality, comparable to those produced with human intervention. Additionally, our methodology shows potential as a generalized model to address diverse macro shapes and layout areas.
Relax: Composable Abstractions for End-to-End Dynamic Machine Learning
Paper ↗
Abstract
Dynamic shape computations have become critical in modern machine learning workloads, especially in emerging large language models. The success of these models has driven the demand for their universal deployment across a diverse set of backend environments. In this paper, we present Relax, a compiler abstraction for optimizing end-to-end dynamic machine learning workloads. Relax introduces a cross-level abstraction that encapsulates computational graphs, loop-level tensor programs, and external library calls in a single representation. Relax also introduces first-class symbolic shape annotations to track dynamic shape computations globally across the program, enabling dynamic shape-aware cross-level optimizations. We build an end-to-end compilation framework using the proposed approach to optimize dynamic shape models. Experimental results on LLMs show that Relax delivers performance competitive with state-of-the-art systems across various GPUs and enables deployment of emerging models to a broader set of emerging environments, including mobile phones, embedded devices, and web browsers.
ChipNeMo: Domain-Adapted LLMs for Chip Design
Paper ↗
Abstract
ChipNeMo aims to explore the applications of large language models (LLMs) for industrial chip design. Instead of directly deploying off-the-shelf commercial or open-source LLMs, we instead adopt the following domain adaptation techniques: domain-adaptive tokenization, domain-adaptive continued pretraining, model alignment with domain-specific instructions, and domain-adapted retrieval models. We evaluate these methods on three selected LLM applications for chip design: an engineering assistant chatbot, EDA script generation, and bug summarization and analysis. Our evaluations demonstrate that domain-adaptive pretraining of language models, can lead to superior performance in domain related downstream tasks compared to their base LLaMA2 counterparts, without degradations in generic capabilities. In particular, our largest model, ChipNeMo-70B, outperforms the highly capable GPT-4 on two of our use cases, namely engineering assistant chatbot and EDA scripts generation, while exhibiting competitive performance on bug summarization and analysis. These results underscore the potential of domain-specific customization for enhancing the effectiveness of large language models in specialized applications.
Learning Generalizable Program and Architecture Representations for Performance Modeling
Paper ↗
Abstract
Performance modeling is an essential tool in many areas, including performance characterization/optimization, design space exploration, and resource allocation problems, to name a few. However, existing performance modeling approaches have limitations, such as high computational cost for discrete-event simulators, narrow flexibility of hardware emulators, or restricted accuracy/generality of analytical/data-driven models. To address these limitations, this paper proposes PerfVec, a novel deep learning-based performance modeling framework that learns high-dimensional and independent/orthogonal program and microarchitecture representations. Once learned, a program representation can be used to predict its performance on any microarchitecture, and likewise, a microarchitecture representation can be applied in the performance prediction of any program. Additionally, PerfVec yields a foundation model that captures the performance essence of instructions, which can be directly used by developers in numerous performance modeling related tasks without incurring its training cost. The evaluation demonstrates that PerfVec is more general and efficient than previous approaches.
AMG: Automated Efficient Approximate Multiplier Generator for FPGAs via Bayesian Optimization
Paper ↗
Abstract
Approximate computing is a promising approach to reduce the power, delay, and area in hardware design for many error-resilient applications such as machine learning (ML) and digital signal processing (DSP) systems, in which multipliers usually are key arithmetic units. Due to the underlying architectural differences between ASICs and FPGAs, existing ASIC-based approximate multipliers do not offer symmetrical gains when they are implemented by FPGA resources. In this paper, we propose AMG, an open-source automated approximate multiplier generator for FPGAs driven by Bayesian optimization (BO) with parallel evaluation. The proposed method simplifies the exact half adders (HAs) for the initial partial product (PP) compression in a multiplier while preserving coarse-grained additions for the following accumulation. The generated multipliers can be effectively mapped to lookup tables (LUTs) and carry chains provided by modern FPGAs, reducing hardware costs with acceptable errors. Compared with 1167 multipliers from previous works, our generated multipliers can form a Pareto front with 28.70%-38.47% improvements in terms of the product of hardware cost and error on average. All source codes, reproduced multipliers, and our generated multipliers are available at https://github.com/phyzhenli/AMG.
AMG: Automated Efficient Approximate Multiplier Generator for FPGAs via Bayesian Optimization
Paper ↗
Abstract
Approximate computing is a promising approach to reduce the power, delay, and area in hardware design for many error-resilient applications such as machine learning (ML) and digital signal processing (DSP) systems, in which multipliers usually are key arithmetic units. Due to the underlying architectural differences between ASICs and FPGAs, existing ASIC-based approximate multipliers do not offer symmetrical gains when they are implemented by FPGA resources. In this paper, we propose AMG, an open-source automated approximate multiplier generator for FPGAs driven by Bayesian optimization (BO) with parallel evaluation. The proposed method simplifies the exact half adders (HAs) for the initial partial product (PP) compression in a multiplier while preserving coarse-grained additions for the following accumulation. The generated multipliers can be effectively mapped to lookup tables (LUTs) and carry chains provided by modern FPGAs, reducing hardware costs with acceptable errors. Compared with 1167 multipliers from previous works, our generated multipliers can form a Pareto front with 28.70%-38.47% improvements in terms of the product of hardware cost and error on average. All source codes, reproduced multipliers, and our generated multipliers are available at https://github.com/phyzhenli/AMG.
Scalable machine learning-assisted clear-box characterization for optimally controlled photonic circuits
Paper ↗
Abstract
Photonic integrated circuits offer a compact and stable platform for generating, manipulating, and detecting light. They are instrumental for classical and quantum applications. Imperfections stemming from fabrication constraints, tolerances and operation wavelength impose limitations on the accuracy and thus utility of current photonic integrated devices. Mitigating these imperfections typically necessitates a model of the underlying physical structure and the estimation of parameters that are challenging to access. Direct solutions are currently lacking for mesh configurations extending beyond trivial cases. We introduce a scalable and innovative method to characterize photonic chips through an iterative machine learning-assisted procedure. Our method is based on a clear-box approach that harnesses a fully modeled virtual replica of the photonic chip to characterize. The process is sample-efficient and can be carried out with a continuous-wave laser and powermeters. The model estimates individual passive phases, crosstalk, beamsplitter reflectivity values and relative input/output losses. Building upon the accurate characterization results, we mitigate imperfections to enable enhanced control over the device. We validate our characterization and imperfection mitigation methods on a 12-mode Clements-interferometer equipped with 126 phase shifters, achieving beyond state-of-the-art chip control with an average 99.77 % amplitude fidelity on 100 implemented Haar-random unitary matrices.
Towards the Imagenets of ML4EDA
Paper ↗
Abstract
Despite the growing interest in ML-guided EDA tools from RTL to GDSII, there are no standard datasets or prototypical learning tasks defined for the EDA problem domain. Experience from the computer vision community suggests that such datasets are crucial to spur further progress in ML for EDA. Here we describe our experience curating two large-scale, high-quality datasets for Verilog code generation and logic synthesis. The first, VeriGen, is a dataset of Verilog code collected from GitHub and Verilog textbooks. The second, OpenABC-D, is a large-scale, labeled dataset designed to aid ML for logic synthesis tasks. The dataset consists of 870,000 And-Inverter-Graphs (AIGs) produced from 1500 synthesis runs on a large number of open-source hardware projects. In this paper we will discuss challenges in curating, maintaining and growing the size and scale of these datasets. We will also touch upon questions of dataset quality and security, and the use of novel data augmentation tools that are tailored for the hardware domain.
Risk-Aware and Explainable Framework for Ensuring Guaranteed Coverage in Evolving Hardware Trojan Detection
Paper ↗
Abstract
As the semiconductor industry has shifted to a fabless paradigm, the risk of hardware Trojans being inserted at various stages of production has also increased. Recently, there has been a growing trend toward the use of machine learning solutions to detect hardware Trojans more effectively, with a focus on the accuracy of the model as an evaluation metric. However, in a high-risk and sensitive domain, we cannot accept even a small misclassification. Additionally, it is unrealistic to expect an ideal model, especially when Trojans evolve over time. Therefore, we need metrics to assess the trustworthiness of detected Trojans and a mechanism to simulate unseen ones. In this paper, we generate evolving hardware Trojans using our proposed novel conformalized generative adversarial networks and offer an efficient approach to detecting them based on a non-invasive algorithm-agnostic statistical inference framework that leverages the Mondrian conformal predictor. The method acts like a wrapper over any of the machine learning models and produces set predictions along with uncertainty quantification for each new detected Trojan for more robust decision-making. In the case of a NULL set, a novel method to reject the decision by providing a calibrated explainability is discussed. The proposed approach has been validated on both synthetic and real chip-level benchmarks and proven to pave the way for researchers looking to find informed machine learning solutions to hardware security problems.
DeePref: Deep Reinforcement Learning For Video Prefetching In Content Delivery Networks
Paper ↗
Abstract
Content Delivery Networks carry the majority of Internet traffic, and the increasing demand for video content as a major IP traffic across the Internet highlights the importance of caching and prefetching optimization algorithms. Prefetching aims to make data available in the cache before the requester places its request to reduce access time and improve the Quality of Experience on the user side. Prefetching is well investigated in operating systems, compiler instructions, in-memory cache, local storage systems, high-speed networks, and cloud systems. Traditional prefetching techniques are well adapted to a particular access pattern, but fail to adapt to sudden variations or randomization in workloads. This paper explores the use of reinforcement learning to tackle the changes in user access patterns and automatically adapt over time. To this end, we propose, DeePref, a Deep Reinforcement Learning agent for online video content prefetching in Content Delivery Networks. DeePref is a prefetcher implemented on edge networks and is agnostic to hardware design, operating systems, and applications. Our results show that DeePref DRQN, using a real-world dataset, achieves a 17% increase in prefetching accuracy and a 28% increase in prefetching coverage on average compared to baseline approaches that use video content popularity as a building block to statically or dynamically make prefetching decisions. We also study the possibility of transfer learning of statistical models from one edge network into another, where unseen user requests from unknown distribution are observed. In terms of transfer learning, the increase in prefetching accuracy and prefetching coverage are [$30%$, $10%$], respectively. Our source code will be available on Github.
SCAR: Power Side-Channel Analysis at RTL-Level
Paper ↗
Abstract
Power side-channel attacks exploit the dynamic power consumption of cryptographic operations to leak sensitive information of encryption hardware. Therefore, it is necessary to conduct power side-channel analysis for assessing the susceptibility of cryptographic systems and mitigating potential risks. Existing power side-channel analysis primarily focuses on post-silicon implementations, which are inflexible in addressing design flaws, leading to costly and time-consuming post-fabrication design re-spins. Hence, pre-silicon power side-channel analysis is required for early detection of vulnerabilities to improve design robustness. In this paper, we introduce SCAR, a novel pre-silicon power side-channel analysis framework based on Graph Neural Networks (GNN). SCAR converts register-transfer level (RTL) designs of encryption hardware into control-data flow graphs and use that to detect the design modules susceptible to side-channel leakage. Furthermore, we incorporate a deep learning-based explainer in SCAR to generate quantifiable and human-accessible explanation of our detection and localization decisions. We have also developed a fortification component as a part of SCAR that uses large-language models (LLM) to automatically generate and insert additional design code at the localized zone to shore up the side-channel leakage. When evaluated on popular encryption algorithms like AES, RSA, and PRESENT, and postquantum cryptography algorithms like Saber and CRYSTALS-Kyber, SCAR, achieves up to 94.49% localization accuracy, 100% precision, and 90.48% recall. Additionally, through explainability analysis, SCAR reduces features for GNN model training by 57% while maintaining comparable accuracy. We believe that SCAR will transform the security-critical hardware design cycle, resulting in faster design closure at a reduced design cost.
LLM for SoC Security: A Paradigm Shift
Paper ↗
Abstract
As the ubiquity and complexity of system-on-chip (SoC) designs increase across electronic devices, the task of incorporating security into an SoC design flow poses significant challenges. Existing security solutions are inadequate to provide effective verification of modern SoC designs due to their limitations in scalability, comprehensiveness, and adaptability. On the other hand, Large Language Models (LLMs) are celebrated for their remarkable success in natural language understanding, advanced reasoning, and program synthesis tasks. Recognizing an opportunity, our research delves into leveraging the emergent capabilities of Generative Pre-trained Transformers (GPTs) to address the existing gaps in SoC security, aiming for a more efficient, scalable, and adaptable methodology. By integrating LLMs into the SoC security verification paradigm, we open a new frontier of possibilities and challenges to ensure the security of increasingly complex SoCs. This paper offers an in-depth analysis of existing works, showcases practical case studies, demonstrates comprehensive experiments, and provides useful promoting guidelines. We also present the achievements, prospects, and challenges of employing LLM in different SoC security verification tasks.
LLM4DV: Using Large Language Models for Hardware Test Stimuli Generation
Paper ↗
Abstract
Hardware design verification (DV) is a process that checks the functional equivalence of a hardware design against its specifications, improving hardware reliability and robustness. A key task in the DV process is the test stimuli generation, which creates a set of conditions or inputs for testing. These test conditions are often complex and specific to the given hardware design, requiring substantial human engineering effort to optimize. We seek a solution of automated and efficient testing for arbitrary hardware designs that takes advantage of large language models (LLMs). LLMs have already shown promising results for improving hardware design automation, but remain under-explored for hardware DV. In this paper, we propose an open-source benchmarking framework named LLM4DV that efficiently orchestrates LLMs for automated hardware test stimuli generation. Our analysis evaluates six different LLMs involving six prompting improvements over eight hardware designs and provides insight for future work on LLMs development for efficient automated DV.
Regulating CPU Temperature With Thermal-Aware Scheduling Using a Reduced Order Learning Thermal Model
Paper ↗
Abstract
Modern real-time systems utilize considerable amounts of power while executing computation-intensive tasks. The execution of these tasks leads to significant power dissipation and heating of the device. It therefore results in severe thermal issues like temperature escalation, high thermal gradients, and excessive hot spot formation, which may result in degrading chip performance, accelerating device aging, and premature failure. Thermal-Aware Scheduling (TAS) enables optimization of thermal dissipation to maintain a safe thermal state. In this work, we implement a new TAS algorithm, POD-TAS, which manages the thermal behavior of a multi-core CPU based on a defined set of states and their transitions. We compare the performances of a dynamic RC thermal circuit simulator (HotSpot) and a reduced order Proper Orthogonal Decomposition (POD)-based thermal model and we select the latter for use in our POD-TAS algorithm. We implement a novel simulation-based evaluation methodology to compare TAS algorithms. This methodology is used to evaluate the performance of the proposed POD-TAS algorithm. Additionally, we compare the performance of a state of the art TAS algorithm, RT-TAS, to our proposed POD-TAS algorithm. Furthermore, we utilize the COMBS benchmark suite to provide CPU workloads for task scheduling. Our experimental results on a multi-core processor using a set of 4 benchmarks demonstrate that the proposed POD-TAS method can improve thermal performance by decreasing the peak thermal variance by 53.0% and the peak chip temperature of 29.01%. Using a set of 8 benchmarks, the comparison of the two algorithms shows a decrease of 29.57% in the peak spatial variance of the chip temperature and 26.26% in the peak chip temperature. We also identify several potential future research directions.
MORPH: Design Co-optimization with Reinforcement Learning via a Differentiable Hardware Model Proxy
Paper ↗
Abstract
We introduce MORPH, a method for co-optimization of hardware design parameters and control policies in simulation using reinforcement learning. Like most co-optimization methods, MORPH relies on a model of the hardware being optimized, usually simulated based on the laws of physics. However, such a model is often difficult to integrate into an effective optimization routine. To address this, we introduce a proxy hardware model, which is always differentiable and enables efficient co-optimization alongside a long-horizon control policy using RL. MORPH is designed to ensure that the optimized hardware proxy remains as close as possible to its realistic counterpart, while still enabling task completion. We demonstrate our approach on simulated 2D reaching and 3D multi-fingered manipulation tasks.
AxOCS: Scaling FPGA-based Approximate Operators using Configuration Supersampling
Paper ↗
Abstract
The rising usage of AI and ML-based processing across application domains has exacerbated the need for low-cost ML implementation, specifically for resource-constrained embedded systems. To this end, approximate computing, an approach that explores the power, performance, area (PPA), and behavioral accuracy (BEHAV) trade-offs, has emerged as a possible solution for implementing embedded machine learning. Due to the predominance of MAC operations in ML, designing platform-specific approximate arithmetic operators forms one of the major research problems in approximate computing. Recently there has been a rising usage of AI/ML-based design space exploration techniques for implementing approximate operators. However, most of these approaches are limited to using ML-based surrogate functions for predicting the PPA and BEHAV impact of a set of related design decisions. While this approach leverages the regression capabilities of ML methods, it does not exploit the more advanced approaches in ML. To this end, we propose AxOCS, a methodology for designing approximate arithmetic operators through ML-based supersampling. Specifically, we present a method to leverage the correlation of PPA and BEHAV metrics across operators of varying bit-widths for generating larger bit-width operators. The proposed approach involves traversing the relatively smaller design space of smaller bit-width operators and employing its associated Design-PPA-BEHAV relationship to generate initial solutions for metaheuristics-based optimization for larger operators. The experimental evaluation of AxOCS for FPGA-optimized approximate operators shows that the proposed approach significantly improves the quality-resulting hypervolume for multi-objective optimization-of 8x8 signed approximate multipliers.
Using LLMs to Facilitate Formal Verification of RTL
Paper ↗
Abstract
Formal property verification (FPV) has existed for decades and has been shown to be effective at finding intricate RTL bugs. However, formal properties, such as those written as SystemVerilog Assertions (SVA), are time-consuming and error-prone to write, even for experienced users. Prior work has attempted to lighten this burden by raising the abstraction level so that SVA is generated from high-level specifications. However, this does not eliminate the manual effort of reasoning and writing about the detailed hardware behavior. Motivated by the increased need for FPV in the era of heterogeneous hardware and the advances in large language models (LLMs), we set out to explore whether LLMs can capture RTL behavior and generate correct SVA properties. First, we design an FPV-based evaluation framework that measures the correctness and completeness of SVA. Then, we evaluate GPT4 iteratively to craft the set of syntax and semantic rules needed to prompt it toward creating better SVA. We extend the open-source AutoSVA framework by integrating our improved GPT4-based flow to generate safety properties, in addition to facilitating their existing flow for liveness properties. Lastly, our use cases evaluate (1) the FPV coverage of GPT4-generated SVA on complex open-source RTL and (2) using generated SVA to prompt GPT4 to create RTL from scratch. Through these experiments, we find that GPT4 can generate correct SVA even for flawed RTL, without mirroring design errors. Particularly, it generated SVA that exposed a bug in the RISC-V CVA6 core that eluded the prior work's evaluation.
VerilogEval: Evaluating Large Language Models for Verilog Code Generation
Paper ↗
Abstract
The increasing popularity of large language models (LLMs) has paved the way for their application in diverse domains. This paper proposes a benchmarking framework tailored specifically for evaluating LLM performance in the context of Verilog code generation for hardware design and verification. We present a comprehensive evaluation dataset consisting of 156 problems from the Verilog instructional website HDLBits. The evaluation set consists of a diverse set of Verilog code generation tasks, ranging from simple combinational circuits to complex finite state machines. The Verilog code completions can be automatically tested for functional correctness by comparing the transient simulation outputs of the generated design with a golden solution. We also demonstrate that the Verilog code generation capability of pretrained language models could be improved with supervised fine-tuning by bootstrapping with LLM generated synthetic problem-code pairs.
Comparing Llama-2 and GPT-3 LLMs for HPC kernels generation
Paper ↗
Abstract
We evaluate the use of the open-source Llama-2 model for generating well-known, high-performance computing kernels (e.g., AXPY, GEMV, GEMM) on different parallel programming models and languages (e.g., C++: OpenMP, OpenMP Offload, OpenACC, CUDA, HIP; Fortran: OpenMP, OpenMP Offload, OpenACC; Python: numpy, Numba, pyCUDA, cuPy; and Julia: Threads, CUDA.jl, AMDGPU.jl). We built upon our previous work that is based on the OpenAI Codex, which is a descendant of GPT-3, to generate similar kernels with simple prompts via GitHub Copilot. Our goal is to compare the accuracy of Llama-2 and our original GPT-3 baseline by using a similar metric. Llama-2 has a simplified model that shows competitive or even superior accuracy. We also report on the differences between these foundational large language models as generative AI continues to redefine human-computer interactions. Overall, Copilot generates codes that are more reliable but less optimized, whereas codes generated by Llama-2 are less reliable but more optimized when correct.
CktGNN: Circuit Graph Neural Network for Electronic Design Automation
Paper ↗
Abstract
The electronic design automation of analog circuits has been a longstanding challenge in the integrated circuit field due to the huge design space and complex design trade-offs among circuit specifications. In the past decades, intensive research efforts have mostly been paid to automate the transistor sizing with a given circuit topology. By recognizing the graph nature of circuits, this paper presents a Circuit Graph Neural Network (CktGNN) that simultaneously automates the circuit topology generation and device sizing based on the encoder-dependent optimization subroutines. Particularly, CktGNN encodes circuit graphs using a two-level GNN framework (of nested GNN) where circuits are represented as combinations of subgraphs in a known subgraph basis. In this way, it significantly improves design efficiency by reducing the number of subgraphs to perform message passing. Nonetheless, another critical roadblock to advancing learning-assisted circuit design automation is a lack of public benchmarks to perform canonical assessment and reproducible research. To tackle the challenge, we introduce Open Circuit Benchmark (OCB), an open-sourced dataset that contains $10$K distinct operational amplifiers with carefully-extracted circuit specifications. OCB is also equipped with communicative circuit generation and evaluation capabilities such that it can help to generalize CktGNN to design various analog circuits by producing corresponding datasets. Experiments on OCB show the extraordinary advantages of CktGNN through representation-based optimization frameworks over other recent powerful GNN baselines and human experts' manual designs. Our work paves the way toward a learning-based open-sourced design automation for analog circuits. Our source code is available at \url{https://github.com/zehao-dong/CktGNN}.
Best Memory Architecture Exploration under Parameters Variations accelerated with Machine Learning
Paper ↗
Abstract
The design of effective memory architecture is of utmost importance in modern computing systems. However, the design of memory subsystems is even more difficult today because process variation and modern design techniques like dynamic voltage scaling make performance metrics for memory assessment be treated as random variables instead of scalars at design time. Most of the previous works have studied the design of memory design from the yield analysis perspective leaving the question of the best memory organization on average open. Because examining all possible combinations of design parameter values of a memory chip would require prohibitively much time, in this work, we propose Best Arm Identification (BAI) algorithms to accelerate the exploration for the best memory architecture on average under parameter variations. Our experimental results demonstrate that we can arrive at the best memory organization 99% of the time in x5 faster than an exhaustive search of all possible conditions.
Packet Header Recognition Utilizing an All-Optical Reservoir Based on Reinforcement-Learning-Optimized Double-Ring Resonator
Paper ↗
Abstract
Optical packet header recognition is an important signal processing task of optical communication networks. In this work, we propose an all-optical reservoir, consisting of integrated double-ring resonators (DRRs) as nodes, for fast and accurate optical packet header recognition. As the delay-bandwidth product (DBP) of the node is a key figure-of-merit in the reservoir, we adopt a deep reinforcement learning algorithm to maximize the DBPs for various types of DRRs, which has the advantage of full parameter space optimization and fast convergence speed. Intriguingly, the optimized DBPs of the DRRs in cascaded, parallel, and embedded configurations reach the same maximum value, which is believed to be the global maximum. Finally, 3-bit and 6-bit packet header recognition tasks are performed with the all-optical reservoir consisting of the optimized cascaded rings, which have greatly reduced chip size and the desired "flat-top" delay spectra. Using this optical computing scheme, word-error rates as low as 5*10-4 and 9*10-4 are achieved for 3-bit and 6-bit packet header recognition tasks, respectively, which are one order of magnitude better than the previously reported values.
A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Design
Paper ↗
Abstract
Logic Synthesis (LS) plays a vital role in chip design -- a cornerstone of the semiconductor industry. A key task in LS is to transform circuits -- modeled by directed acyclic graphs (DAGs) -- into simplified circuits with equivalent functionalities. To tackle this task, many LS operators apply transformations to subgraphs -- rooted at each node on an input DAG -- sequentially. However, we found that a large number of transformations are ineffective, which makes applying these operators highly time-consuming. In particular, we notice that the runtime of the Resub and Mfs2 operators often dominates the overall runtime of LS optimization processes. To address this challenge, we propose a novel data-driven LS operator paradigm, namely PruneX, to reduce ineffective transformations. The major challenge of developing PruneX is to learn models that well generalize to unseen circuits, i.e., the out-of-distribution (OOD) generalization problem. Thus, the major technical contribution of PruneX is the novel circuit domain generalization framework, which learns domain-invariant representations based on the transformation-invariant domain-knowledge. To the best of our knowledge, PruneX is the first approach to tackle the OOD problem in LS operators. We integrate PruneX with the aforementioned Resub and Mfs2 operators. Experiments demonstrate that PruneX significantly improves their efficiency while keeping comparable optimization performance on industrial and very large-scale circuits, achieving up to $3.1\times$ faster runtime.
Unlocking Hardware Security Assurance: The Potential of LLMs
Paper ↗
Abstract
System-on-Chips (SoCs) form the crux of modern computing systems. SoCs enable high-level integration through the utilization of multiple Intellectual Property (IP) cores. However, the integration of multiple IP cores also presents unique challenges owing to their inherent vulnerabilities, thereby compromising the security of the entire system. Hence, it is imperative to perform hardware security validation to address these concerns. The efficiency of this validation procedure is contingent on the quality of the SoC security properties provided. However, generating security properties with traditional approaches often requires expert intervention and is limited to a few IPs, thereby resulting in a time-consuming and non-robust process. To address this issue, we, for the first time, propose a novel and automated Natural Language Processing (NLP)-based Security Property Generator (NSPG). Specifically, our approach utilizes hardware documentation in order to propose the first hardware security-specific language model, HS-BERT, for extracting security properties dedicated to hardware design. To evaluate our proposed technique, we trained the HS-BERT model using sentences from RISC-V, OpenRISC, MIPS, OpenSPARC, and OpenTitan SoC documentation. When assessedb on five untrained OpenTitan hardware IP documents, NSPG was able to extract 326 security properties from 1723 sentences. This, in turn, aided in identifying eight security bugs in the OpenTitan SoC design presented in the hardware hacking competition, Hack@DAC 2022.
ChatEDA: A Large Language Model Powered Autonomous Agent for EDA
Paper ↗
Abstract
The integration of a complex set of Electronic Design Automation (EDA) tools to enhance interoperability is a critical concern for circuit designers. Recent advancements in large language models (LLMs) have showcased their exceptional capabilities in natural language processing and comprehension, offering a novel approach to interfacing with EDA tools. This research paper introduces ChatEDA, an autonomous agent for EDA empowered by an LLM, AutoMage, complemented by EDA tools serving as executors. ChatEDA streamlines the design flow from the Register-Transfer Level (RTL) to the Graphic Data System Version II (GDSII) by effectively managing task decomposition, script generation, and task execution. Through comprehensive experimental evaluations, ChatEDA has demonstrated its proficiency in handling diverse requirements, and our fine-tuned AutoMage model has exhibited superior performance compared to GPT-4 and other similar LLMs.
Accelerating Exact Combinatorial Optimization via RL-based Initialization -- A Case Study in Scheduling
Paper ↗
Abstract
Scheduling on dataflow graphs (also known as computation graphs) is an NP-hard problem. The traditional exact methods are limited by runtime complexity, while reinforcement learning (RL) and heuristic-based approaches struggle with determinism and solution quality. This research aims to develop an innovative approach that employs machine learning (ML) for addressing combinatorial optimization problems, using scheduling as a case study. The goal is to provide guarantees in optimality and determinism while maintaining the runtime cost of heuristic methods. Specifically, we introduce a novel two-phase RL-to-ILP scheduling framework, which includes three steps: 1) RL solver acts as coarse-grain scheduler, 2) solution relaxation and 3) exact solving via ILP. Our framework demonstrates the same scheduling performance compared with using exact scheduling methods while achieving up to 128 $\times$ speed improvements. This was conducted on actual EdgeTPU platforms, utilizing ImageNet DNN computation graphs as input. Additionally, the framework offers improved on-chip inference runtime and acceleration compared to the commercially available EdgeTPU compiler.
DIVAS: An LLM-based End-to-End Framework for SoC Security Analysis and Policy-based Protection
Paper ↗
Abstract
Securing critical assets in a bus-based System-On-Chip (SoC) is imperative to mitigate potential vulnerabilities and prevent unauthorized access, ensuring the integrity, availability, and confidentiality of the system. Ensuring security throughout the SoC design process is a formidable task owing to the inherent intricacies in SoC designs and the dispersion of assets across diverse IPs. Large Language Models (LLMs), exemplified by ChatGPT (OpenAI) and BARD (Google), have showcased remarkable proficiency across various domains, including security vulnerability detection and prevention in SoC designs. In this work, we propose DIVAS, a novel framework that leverages the knowledge base of LLMs to identify security vulnerabilities from user-defined SoC specifications, map them to the relevant Common Weakness Enumerations (CWEs), followed by the generation of equivalent assertions, and employ security measures through enforcement of security policies. The proposed framework is implemented using multiple ChatGPT and BARD models, and their performance was analyzed while generating relevant CWEs from the SoC specifications provided. The experimental results obtained from open-source SoC benchmarks demonstrate the efficacy of our proposed framework.
RTLLM: An Open-Source Benchmark for Design RTL Generation with Large Language Model
Paper ↗
Abstract
Inspired by the recent success of large language models (LLMs) like ChatGPT, researchers start to explore the adoption of LLMs for agile hardware design, such as generating design RTL based on natural-language instructions. However, in existing works, their target designs are all relatively simple and in a small scale, and proposed by the authors themselves, making a fair comparison among different LLM solutions challenging. In addition, many prior works only focus on the design correctness, without evaluating the design qualities of generated design RTL. In this work, we propose an open-source benchmark named RTLLM, for generating design RTL with natural language instructions. To systematically evaluate the auto-generated design RTL, we summarized three progressive goals, named syntax goal, functionality goal, and design quality goal. This benchmark can automatically provide a quantitative evaluation of any given LLM-based solution. Furthermore, we propose an easy-to-use yet surprisingly effective prompt engineering technique named self-planning, which proves to significantly boost the performance of GPT-3.5 in our proposed benchmark.
GraPhSyM: Graph Physical Synthesis Model
Paper ↗
Abstract
In this work, we introduce GraPhSyM, a Graph Attention Network (GATv2) model for fast and accurate estimation of post-physical synthesis circuit delay and area metrics from pre-physical synthesis circuit netlists. Once trained, GraPhSyM provides accurate visibility of final design metrics to early EDA stages, such as logic synthesis, without running the slow physical synthesis flow, enabling global co-optimization across stages. Additionally, the swift and precise feedback provided by GraPhSyM is instrumental for machine-learning-based EDA optimization frameworks. Given a gate-level netlist of a circuit represented as a graph, GraPhSyM utilizes graph structure, connectivity, and electrical property features to predict the impact of physical synthesis transformations such as buffer insertion and gate sizing. When trained on a dataset of 6000 prefix adder designs synthesized at an aggressive delay target, GraPhSyM can accurately predict the post-synthesis delay (98.3%) and area (96.1%) metrics of unseen adders with a fast 0.22s inference time. Furthermore, we illustrate the compositionality of GraPhSyM by employing the model trained on a fixed delay target to accurately anticipate post-synthesis metrics at a variety of unseen delay targets. Lastly, we report promising generalization capabilities of the GraPhSyM model when it is evaluated on circuits different from the adders it was exclusively trained on. The results show the potential for GraPhSyM to serve as a powerful tool for advanced optimization techniques and as an oracle for EDA machine learning frameworks.
Imbalanced Large Graph Learning Framework for FPGA Logic Elements Packing Prediction
Paper ↗
Abstract
Packing is a required step in a typical FPGA CAD flow. It has high impacts to the performance of FPGA placement and routing. Early prediction of packing results can guide design optimization and expedite design closure. In this work, we propose an imbalanced large graph learning framework, ImLG, for prediction of whether logic elements will be packed after placement. Specifically, we propose dedicated feature extraction and feature aggregation methods to enhance the node representation learning of circuit graphs. With imbalanced distribution of packed and unpacked logic elements, we further propose techniques such as graph oversampling and mini-batch training for this imbalanced learning task in large circuit graphs. Experimental results demonstrate that our framework can improve the F1 score by 42.82% compared to the most recent Gaussian-based prediction method. Physical design results show that the proposed method can assist the placer in improving routed wirelength by 0.93% and SLICE occupation by 0.89%.
Variational Label-Correlation Enhancement for Congestion Prediction
Paper ↗
Abstract
The physical design process of large-scale designs is a time-consuming task, often requiring hours to days to complete, with routing being the most critical and complex step. As the the complexity of Integrated Circuits (ICs) increases, there is an increased demand for accurate routing quality prediction. Accurate congestion prediction aids in identifying design flaws early on, thereby accelerating circuit design and conserving resources. Despite the advancements in current congestion prediction methodologies, an essential aspect that has been largely overlooked is the spatial label-correlation between different grids in congestion prediction. The spatial label-correlation is a fundamental characteristic of circuit design, where the congestion status of a grid is not isolated but inherently influenced by the conditions of its neighboring grids. In order to fully exploit the inherent spatial label-correlation between neighboring grids, we propose a novel approach, {\ours}, i.e., VAriational Label-Correlation Enhancement for Congestion Prediction, which considers the local label-correlation in the congestion map, associating the estimated congestion value of each grid with a local label-correlation weight influenced by its surrounding grids. {\ours} leverages variational inference techniques to estimate this weight, thereby enhancing the regression model's performance by incorporating spatial dependencies. Experiment results validate the superior effectiveness of {\ours} on the public available \texttt{ISPD2011} and \texttt{DAC2012} benchmarks using the superblue circuit line.
Revolutionizing TCAD Simulations with Universal Device Encoding and Graph Attention Networks
Paper ↗
Abstract
An innovative methodology that leverages artificial intelligence (AI) and graph representation for semiconductor device encoding in TCAD device simulation is proposed. A graph-based universal encoding scheme is presented that not only considers material-level and device-level embeddings, but also introduces a novel spatial relationship embedding inspired by interpolation operations typically used in finite element meshing. Universal physical laws from device simulations are leveraged for comprehensive data-driven modeling, which encompasses surrogate Poisson emulation and current-voltage (IV) prediction based on drift-diffusion model. Both are achieved using a novel graph attention network, referred to as RelGAT. Comprehensive technical details based on the device simulator Sentaurus TCAD are presented, empowering researchers to adopt the proposed AI-driven Electronic Design Automation (EDA) solution at the device level.
Seeking the Yield Barrier: High-Dimensional SRAM Evaluation Through Optimal Manifold
Paper ↗
Abstract
Being able to efficiently obtain an accurate estimate of the failure probability of SRAM components has become a central issue as model circuits shrink their scale to submicrometer with advanced technology nodes. In this work, we revisit the classic norm minimization method. We then generalize it with infinite components and derive the novel optimal manifold concept, which bridges the surrogate-based and importance sampling (IS) yield estimation methods. We then derive a sub-optimal manifold, optimal hypersphere, which leads to an efficient sampling method being aware of the failure boundary called onion sampling. Finally, we use a neural coupling flow (which learns from samples like a surrogate model) as the IS proposal distribution. These combinations give rise to a novel yield estimation method, named Optimal Manifold Important Sampling (OPTIMIS), which keeps the advantages of the surrogate and IS methods to deliver state-of-the-art performance with robustness and consistency, with up to 3.5x in efficiency and 3x in accuracy over the best of SOTA methods in High-dimensional SRAM evaluation.
VeriGen: A Large Language Model for Verilog Code Generation
Paper ↗
Abstract
In this study, we explore the capability of Large Language Models (LLMs) to automate hardware design by generating high-quality Verilog code, a common language for designing and modeling digital systems. We fine-tune pre-existing LLMs on Verilog datasets compiled from GitHub and Verilog textbooks. We evaluate the functional correctness of the generated Verilog code using a specially designed test suite, featuring a custom problem set and testing benches. Here, our fine-tuned open-source CodeGen-16B model outperforms the commercial state-of-the-art GPT-3.5-turbo model with a 1.1% overall increase. Upon testing with a more diverse and complex problem set, we find that the fine-tuned model shows competitive performance against state-of-the-art gpt-3.5-turbo, excelling in certain scenarios. Notably, it demonstrates a 41% improvement in generating syntactically correct Verilog code across various problem categories compared to its pre-trained counterpart, highlighting the potential of smaller, in-house LLMs in hardware design automation.
New Interaction Paradigm for Complex EDA Software Leveraging GPT
Paper ↗
Abstract
In the rapidly growing field of electronic design automation (EDA), professional software such as KiCad, Cadence , and Altium Designer provide increasingly extensive design functionalities. However, the intricate command structure and high learning curve create a barrier, particularly for novice printed circuit board (PCB) designers. This results in difficulties in selecting appropriate functions or plugins for varying design purposes, compounded by the lack of intuitive learning methods beyond traditional documentation, videos, and online forums. To address this challenge, an artificial intelligence (AI) interaction assist plugin for EDA software named SmartonAl is developed here, also KiCad is taken as the first example. SmartonAI is inspired by the HuggingGPT framework and employs large language models, such as GPT and BERT, to facilitate task planning and execution. On receiving a designer request, SmartonAI conducts a task breakdown and efficiently executes relevant subtasks, such as analysis of help documentation paragraphs and execution of different plugins, along with leveraging the built-in schematic and PCB manipulation functions in both SmartonAl itself and software. Our preliminary results demonstrate that SmartonAI can significantly streamline the PCB design process by simplifying complex commands into intuitive language-based interactions. By harnessing the powerful language capabilities of ChatGPT and the rich design functions of KiCad, the plugin effectively bridges the gap between complex EDA software and user-friendly interaction. Meanwhile, the new paradigm behind SmartonAI can also extend to other complex software systems, illustrating the immense potential of AI-assisted user interfaces in advancing digital interactions across various domains.
New Interaction Paradigm for Complex EDA Software Leveraging GPT
Paper ↗
Abstract
Electronic Design Automation (EDA) tools such as KiCad offer powerful functionalities but remain difficult to use, particularly for beginners, due to their steep learning curves and fragmented documentation. To address this challenge, we present SmartonAI, an AI-assisted interaction system that integrates large language models into the EDA workflow, enabling natural language communication, intelligent task decomposition, and contextual plugin execution. SmartonAI consists of two main components: a Chat Plugin that breaks down user instructions into subtasks and retrieves tailored documentation, and a OneCommandLine Plugin that recommends and executes relevant plugins based on user intent. The system supports multilingual interaction and adapts to user feedback through incremental learning. Preliminary results suggest that SmartonAI significantly reduces onboarding time and enhances productivity, representing a promising step toward generalizable AI-assisted interaction paradigms for complex software systems.
A Reinforcement Learning Framework with Region-Awareness and Shared Path Experience for Efficient Routing in Networks-on-Chip
Paper ↗
Abstract
Network-on-chip (NoC) architectures provide a scalable, high-performance, and reliable interconnect for emerging manycore systems. The routing policies used in NoCs have a significant impact on overall performance. Prior efforts have proposed reinforcement learning (RL)-based adaptive routing policies to avoid congestion and minimize latency in NoCs. The output quality of RL policies depends on selecting a representative cost function and an effective update mechanism. Unfortunately, existing RL policies for NoC routing fail to represent path contention and regional congestion in the cost function. Moreover, the experience of packet flows sharing the same route is not fully incorporated into the RL update mechanism. In this paper, we present a novel regional congestion-aware RL-based NoC routing policy called Q-RASP that is capable of sharing experience from packets using the same routes. Q-RASP improves average packet latency by up to 18.3% and reduces NoC energy consumption by up to 6.7% with minimal area overheads compared to state-of-the-art RL-based NoC routing implementations.
The Power of Large Language Models for Wireless Communication System Development: A Case Study on FPGA Platforms
Paper ↗
Abstract
Large language models (LLMs) have garnered significant attention across various research disciplines, including the wireless communication community. There have been several heated discussions on the intersection of LLMs and wireless technologies. While recent studies have demonstrated the ability of LLMs to generate hardware description language (HDL) code for simple computation tasks, developing wireless prototypes and products via HDL poses far greater challenges because of the more complex computation tasks involved. In this paper, we aim to address this challenge by investigating the role of LLMs in FPGA-based hardware development for advanced wireless signal processing. We begin by exploring LLM-assisted code refactoring, reuse, and validation, using an open-source software-defined radio (SDR) project as a case study. Through the case study, we find that an LLM assistant can potentially yield substantial productivity gains for researchers and developers. We then examine the feasibility of using LLMs to generate HDL code for advanced wireless signal processing, using the Fast Fourier Transform (FFT) algorithm as an example. This task presents two unique challenges: the scheduling of subtasks within the overall task and the multi-step thinking required to solve certain arithmetic problem within the task. To address these challenges, we employ in-context learning (ICL) and Chain-of-Thought (CoT) prompting techniques, culminating in the successful generation of a 64-point Verilog FFT module. Our results demonstrate the potential of LLMs for generalization and imitation, affirming their usefulness in writing HDL code for wireless communication systems. Overall, this work contributes to understanding the role of LLMs in wireless communication and motivates further exploration of their capabilities.
AI4OPT: AI Institute for Advances in Optimization
Paper ↗
Abstract
This article is a short introduction to AI4OPT, the NSF AI Institute for Advances in Optimization. AI4OPT fuses AI and Optimization, inspired by end-use cases in supply chains, energy systems, chip design and manufacturing, and sustainable food systems. AI4OPT also applies its "teaching the teachers" philosophy to provide longitudinal educational pathways in AI for engineering.
Macro Placement by Wire-Mask-Guided Black-Box Optimization
Paper ↗
Abstract
The development of very large-scale integration (VLSI) technology has posed new challenges for electronic design automation (EDA) techniques in chip floorplanning. During this process, macro placement is an important subproblem, which tries to determine the positions of all macros with the aim of minimizing half-perimeter wirelength (HPWL) and avoiding overlapping. Previous methods include packing-based, analytical and reinforcement learning methods. In this paper, we propose a new black-box optimization (BBO) framework (called WireMask-BBO) for macro placement, by using a wire-mask-guided greedy procedure for objective evaluation. Equipped with different BBO algorithms, WireMask-BBO empirically achieves significant improvements over previous methods, i.e., achieves significantly shorter HPWL by using much less time. Furthermore, it can fine-tune existing placements by treating them as initial solutions, which can bring up to 50% improvement in HPWL. WireMask-BBO has the potential to significantly improve the quality and efficiency of chip floorplanning, which makes it appealing to researchers and practitioners in EDA and will also promote the application of BBO. Our code is available at https://github.com/lamda-bbo/WireMask-BBO.
OpenPARF: An Open-Source Placement and Routing Framework for Large-Scale Heterogeneous FPGAs with Deep Learning Toolkit
Paper ↗
Abstract
This paper proposes OpenPARF, an open-source placement and routing framework for large-scale FPGA designs. OpenPARF is implemented with the deep learning toolkit PyTorch and supports massive parallelization on GPU. The framework proposes a novel asymmetric multi-electrostatic field system to solve FPGA placement. It considers fine-grained routing resources inside configurable logic blocks (CLBs) for FPGA routing and supports large-scale irregular routing resource graphs. Experimental results on ISPD 2016 and ISPD 2017 FPGA contest benchmarks and industrial benchmarks demonstrate that OpenPARF can achieve 0.4-12.7% improvement in routed wirelength and more than $2\times$ speedup in placement. We believe that OpenPARF can pave the road for developing FPGA physical design engines and stimulate further research on related topics.
ChiPFormer: Transferable Chip Placement via Offline Decision Transformer
Paper ↗
Abstract
Placement is a critical step in modern chip design, aiming to determine the positions of circuit modules on the chip canvas. Recent works have shown that reinforcement learning (RL) can improve human performance in chip placement. However, such an RL-based approach suffers from long training time and low transfer ability in unseen chip circuits. To resolve these challenges, we cast the chip placement as an offline RL formulation and present ChiPFormer that enables learning a transferable placement policy from fixed offline data. ChiPFormer has several advantages that prior arts do not have. First, ChiPFormer can exploit offline placement designs to learn transferable policies more efficiently in a multi-task setting. Second, ChiPFormer can promote effective finetuning for unseen chip circuits, reducing the placement runtime from hours to minutes. Third, extensive experiments on 32 chip circuits demonstrate that ChiPFormer achieves significantly better placement quality while reducing the runtime by 10x compared to recent state-of-the-art approaches in both public benchmarks and realistic industrial tasks. The deliverables are released at https://sites.google.com/view/chipformer/home.
(Security) Assertions by Large Language Models
Paper ↗
Abstract
The security of computer systems typically relies on a hardware root of trust. As vulnerabilities in hardware can have severe implications on a system, there is a need for techniques to support security verification activities. Assertion-based verification is a popular verification technique that involves capturing design intent in a set of assertions that can be used in formal verification or testing-based checking. However, writing security-centric assertions is a challenging task. In this work, we investigate the use of emerging large language models (LLMs) for code generation in hardware assertion generation for security, where primarily natural language prompts, such as those one would see as code comments in assertion files, are used to produce SystemVerilog assertions. We focus our attention on a popular LLM and characterize its ability to write assertions out of the box, given varying levels of detail in the prompt. We design an evaluation framework that generates a variety of prompts, and we create a benchmark suite comprising real-world hardware designs and corresponding golden reference assertions that we want to generate with the LLM.
Pushing the Limits of Machine Design: Automated CPU Design with AI
Paper ↗
Abstract
Design activity -- constructing an artifact description satisfying given goals and constraints -- distinguishes humanity from other animals and traditional machines, and endowing machines with design abilities at the human level or beyond has been a long-term pursuit. Though machines have already demonstrated their abilities in designing new materials, proteins, and computer programs with advanced artificial intelligence (AI) techniques, the search space for designing such objects is relatively small, and thus, "Can machines design like humans?" remains an open question. To explore the boundary of machine design, here we present a new AI approach to automatically design a central processing unit (CPU), the brain of a computer, and one of the world's most intricate devices humanity have ever designed. This approach generates the circuit logic, which is represented by a graph structure called Binary Speculation Diagram (BSD), of the CPU design from only external input-output observations instead of formal program code. During the generation of BSD, Monte Carlo-based expansion and the distance of Boolean functions are used to guarantee accuracy and efficiency, respectively. By efficiently exploring a search space of unprecedented size 10^{10^{540}}, which is the largest one of all machine-designed objects to our best knowledge, and thus pushing the limits of machine design, our approach generates an industrial-scale RISC-V CPU within only 5 hours. The taped-out CPU successfully runs the Linux operating system and performs comparably against the human-designed Intel 80486SX CPU. In addition to learning the world's first CPU only from input-output observations, which may reform the semiconductor industry by significantly reducing the design cycle, our approach even autonomously discovers human knowledge of the von Neumann architecture.
The False Dawn: Reevaluating Google's Reinforcement Learning for Chip Macro Placement
Paper ↗
Abstract
Reinforcement learning (RL) for physical design of silicon chips in a Google 2021 Nature paper stirred controversy due to poorly documented claims that raised eyebrows and drew critical media coverage. The paper withheld critical methodology steps and most inputs needed to reproduce results. Our meta-analysis shows how two separate evaluations filled in the gaps and demonstrated that Google RL lags behind (i) human designers, (ii) a well-known algorithm (Simulated Annealing), and (iii) generally-available commercial software, while being slower; and in a 2023 open research contest, RL methods weren't in top 5. Crosschecked data indicate that the integrity of the Nature paper is substantially undermined owing to errors in conduct, analysis and reporting. Before publishing, Google rebuffed internal allegations of fraud, which still stand. We note policy implications and conclusions for chip design.
ArchGym: An Open-Source Gymnasium for Machine Learning Assisted Architecture Design
Paper ↗
Abstract
Machine learning is a prevalent approach to tame the complexity of design space exploration for domain-specific architectures. Using ML for design space exploration poses challenges. First, it's not straightforward to identify the suitable algorithm from an increasing pool of ML methods. Second, assessing the trade-offs between performance and sample efficiency across these methods is inconclusive. Finally, lack of a holistic framework for fair, reproducible, and objective comparison across these methods hinders progress of adopting ML-aided architecture design space exploration and impedes creating repeatable artifacts. To mitigate these challenges, we introduce ArchGym, an open-source gym and easy-to-extend framework that connects diverse search algorithms to architecture simulators. To demonstrate utility, we evaluate ArchGym across multiple vanilla and domain-specific search algorithms in designing custom memory controller, deep neural network accelerators, and custom SoC for AR/VR workloads, encompassing over 21K experiments. Results suggest that with unlimited samples, ML algorithms are equally favorable to meet user-defined target specification if hyperparameters are tuned; no solution is necessarily better than another (e.g., reinforcement learning vs. Bayesian methods). We coin the term hyperparameter lottery to describe the chance for a search algorithm to find an optimal design provided meticulously selected hyperparameters. The ease of data collection and aggregation in ArchGym facilitates research in ML-aided architecture design space exploration. As a case study, we show this advantage by developing a proxy cost model with an RMSE of 0.61% that offers a 2,000-fold reduction in simulation time. Code and data for ArchGym is available at https://bit.ly/ArchGym.
Design and implementation of intelligent packet filtering in IoT microcontroller-based devices
Paper ↗
Abstract
Internet of Things (IoT) devices are increasingly pervasive and essential components in enabling new applications and services. However, their widespread use also exposes them to exploitable vulnerabilities and flaws that can lead to significant losses. In this context, ensuring robust cybersecurity measures is essential to protect IoT devices from malicious attacks. However, the current solutions that provide flexible policy specifications and higher security levels for IoT devices are scarce. To address this gap, we introduce T800, a low-resource packet filter that utilizes machine learning (ML) algorithms to classify packets in IoT devices. We present a detailed performance benchmarking framework and demonstrate T800's effectiveness on the ESP32 system-on-chip microcontroller and ESP-IDF framework. Our evaluation shows that T800 is an efficient solution that increases device computational capacity by excluding unsolicited malicious traffic from the processing pipeline. Additionally, T800 is adaptable to different systems and provides a well-documented performance evaluation strategy for security ML-based mechanisms on ESP32-based IoT systems. Our research contributes to improving the cybersecurity of resource-constrained IoT devices and provides a scalable, efficient solution that can be used to enhance the security of IoT systems.
DeepGate2: Functionality-Aware Circuit Representation Learning
Paper ↗
Abstract
Circuit representation learning aims to obtain neural representations of circuit elements and has emerged as a promising research direction that can be applied to various EDA and logic reasoning tasks. Existing solutions, such as DeepGate, have the potential to embed both circuit structural information and functional behavior. However, their capabilities are limited due to weak supervision or flawed model design, resulting in unsatisfactory performance in downstream tasks. In this paper, we introduce DeepGate2, a novel functionality-aware learning framework that significantly improves upon the original DeepGate solution in terms of both learning effectiveness and efficiency. Our approach involves using pairwise truth table differences between sampled logic gates as training supervision, along with a well-designed and scalable loss function that explicitly considers circuit functionality. Additionally, we consider inherent circuit characteristics and design an efficient one-round graph neural network (GNN), resulting in an order of magnitude faster learning speed than the original DeepGate solution. Experimental results demonstrate significant improvements in two practical downstream tasks: logic synthesis and Boolean satisfiability solving. The code is available at https://github.com/cure-lab/DeepGate2
End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes
Paper ↗
Abstract
Meta-Bayesian optimisation (meta-BO) aims to improve the sample efficiency of Bayesian optimisation by leveraging data from related tasks. While previous methods successfully meta-learn either a surrogate model or an acquisition function independently, joint training of both components remains an open challenge. This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data. Early on, we notice that training transformer-based neural processes from scratch with RL is challenging due to insufficient supervision, especially when rewards are sparse. We formalise this claim with a combinatorial analysis showing that the widely used notion of regret as a reward signal exhibits a logarithmic sparsity pattern in trajectory lengths. To tackle this problem, we augment the RL objective with an auxiliary task that guides part of the architecture to learn a valid probabilistic model as an inductive bias. We demonstrate that our method achieves state-of-the-art regret results against various baselines in experiments on standard hyperparameter optimisation tasks and also outperforms others in the real-world problems of mixed-integer programming tuning, antibody design, and logic synthesis for electronic design automation.
ChipGPT: How far are we from natural language hardware design
Paper ↗
Abstract
As large language models (LLMs) like ChatGPT exhibited unprecedented machine intelligence, it also shows great performance in assisting hardware engineers to realize higher-efficiency logic design via natural language interaction. To estimate the potential of the hardware design process assisted by LLMs, this work attempts to demonstrate an automated design environment that explores LLMs to generate hardware logic designs from natural language specifications. To realize a more accessible and efficient chip development flow, we present a scalable four-stage zero-code logic design framework based on LLMs without retraining or finetuning. At first, the demo, ChipGPT, begins by generating prompts for the LLM, which then produces initial Verilog programs. Second, an output manager corrects and optimizes these programs before collecting them into the final design space. Eventually, ChipGPT will search through this space to select the optimal design under the target metrics. The evaluation sheds some light on whether LLMs can generate correct and complete hardware logic designs described by natural language for some specifications. It is shown that ChipGPT improves programmability, and controllability, and shows broader design optimization space compared to prior work and native LLMs alone.
XRoute Environment: A Novel Reinforcement Learning Environment for Routing
Paper ↗
Abstract
Routing is a crucial and time-consuming stage in modern design automation flow for advanced technology nodes. Great progress in the field of reinforcement learning makes it possible to use those approaches to improve the routing quality and efficiency. However, the scale of the routing problems solved by reinforcement learning-based methods in recent studies is too small for these methods to be used in commercial EDA tools. We introduce the XRoute Environment, a new reinforcement learning environment where agents are trained to select and route nets in an advanced, end-to-end routing framework. Novel algorithms and ideas can be quickly tested in a safe and reproducible manner in it. The resulting environment is challenging, easy to use, customize and add additional scenarios, and it is available under a permissive open-source license. In addition, it provides support for distributed deployment and multi-instance experiments. We propose two tasks for learning and build a full-chip test bed with routing benchmarks of various region sizes. We also pre-define several static routing regions with different pin density and number of nets for easier learning and testing. For net ordering task, we report baseline results for two widely used reinforcement learning algorithms (PPO and DQN) and one searching-based algorithm (TritonRoute). The XRoute Environment will be available at https://github.com/xplanlab/xroute_env.
Chip-Chat: Challenges and Opportunities in Conversational Hardware Design
Paper ↗
Abstract
Modern hardware design starts with specifications provided in natural language. These are then translated by hardware engineers into appropriate Hardware Description Languages (HDLs) such as Verilog before synthesizing circuit elements. Automating this translation could reduce sources of human error from the engineering process. But, it is only recently that artificial intelligence (AI) has demonstrated capabilities for machine-based end-to-end design translations. Commercially-available instruction-tuned Large Language Models (LLMs) such as OpenAI's ChatGPT and Google's Bard claim to be able to produce code in a variety of programming languages; but studies examining them for hardware are still lacking. In this work, we thus explore the challenges faced and opportunities presented when leveraging these recent advances in LLMs for hardware design. Given that these `conversational' LLMs perform best when used interactively, we perform a case study where a hardware engineer co-architects a novel 8-bit accumulator-based microprocessor architecture with the LLM according to real-world hardware constraints. We then sent the processor to tapeout in a Skywater 130nm shuttle, meaning that this `Chip-Chat' resulted in what we believe to be the world's first wholly-AI-written HDL for tapeout.
INVICTUS: Optimizing Boolean Logic Circuit Synthesis via Synergistic Learning and Search
Paper ↗
Abstract
Logic synthesis is the first and most vital step in chip design. This steps converts a chip specification written in a hardware description language (such as Verilog) into an optimized implementation using Boolean logic gates. State-of-the-art logic synthesis algorithms have a large number of logic minimization heuristics, typically applied sequentially based on human experience and intuition. The choice of the order greatly impacts the quality (e.g., area and delay) of the synthesized circuit. In this paper, we propose INVICTUS, a model-based offline reinforcement learning (RL) solution that automatically generates a sequence of logic minimization heuristics ("synthesis recipe") based on a training dataset of previously seen designs. A key challenge is that new designs can range from being very similar to past designs (e.g., adders and multipliers) to being completely novel (e.g., new processor instructions). %Compared to prior work, INVICTUS is the first solution that uses a mix of RL and search methods joint with an online out-of-distribution detector to generate synthesis recipes over a wide range of benchmarks. Our results demonstrate significant improvement in area-delay product (ADP) of synthesized circuits with up to 30\% improvement over state-of-the-art techniques. Moreover, INVICTUS achieves up to $6.3\times$ runtime reduction (iso-ADP) compared to the state-of-the-art.
ProgSG: Cross-Modality Representation Learning for Programs in Electronic Design Automation
Paper ↗
Abstract
Recent years have witnessed the growing popularity of domain-specific accelerators (DSAs), such as Google's TPUs, for accelerating various applications such as deep learning, search, autonomous driving, etc. To facilitate DSA designs, high-level synthesis (HLS) is used, which allows a developer to compile a high-level description in the form of software code in C and C++ into a design in low-level hardware description languages (such as VHDL or Verilog) and eventually synthesized into a DSA on an ASIC (application-specific integrated circuit) or FPGA (field-programmable gate arrays). However, existing HLS tools still require microarchitecture decisions, expressed in terms of pragmas (such as directives for parallelization and pipelining). To enable more people to design DSAs, it is desirable to automate such decisions with the help of deep learning for predicting the quality of HLS designs. This requires us a deeper understanding of the program, which is a combination of original code and pragmas. Naturally, these programs can be considered as sequence data, for which large language models (LLM) can help. In addition, these programs can be compiled and converted into a control data flow graph (CDFG), and the compiler also provides fine-grained alignment between the code tokens and the CDFG nodes. However, existing works either fail to leverage both modalities or combine the two in shallow or coarse ways. We propose ProgSG allowing the source code sequence modality and the graph modalities to interact with each other in a deep and fine-grained way. To alleviate the scarcity of labeled designs, a pre-training method is proposed based on a suite of compiler's data flow analysis tasks. Experimental results on two benchmark datasets show the superiority of ProgSG over baseline methods that either only consider one modality or combine the two without utilizing the alignment information.
HybridNet: Dual-Branch Fusion of Geometrical and Topological Views for VLSI Congestion Prediction
Paper ↗
Abstract
Accurate early congestion prediction can prevent unpleasant surprises at the routing stage, playing a crucial character in assisting designers to iterate faster in VLSI design cycles. In this paper, we introduce a novel strategy to fully incorporate topological and geometrical features of circuits by making several key designs in our network architecture. To be more specific, we construct two individual graphs (geometry-graph, topology-graph) with distinct edge construction schemes according to their unique properties. We then propose a dual-branch network with different encoder layers in each pathway and aggregate representations with a sophisticated fusion strategy. Our network, named HybridNet, not only provides a simple yet effective way to capture the geometric interactions of cells, but also preserves the original topological relationships in the netlist. Experimental results on the ISPD2015 benchmarks show that we achieve an improvement of 10.9% compared to previous methods.
PODTherm-GP: A Physics-based Data-Driven Approach for Effective Architecture-Level Thermal Simulation of Multi-Core CPUs
Paper ↗
Abstract
A thermal simulation methodology derived from the proper orthogonal decomposition (POD) and the Galerkin projection (GP), hereafter referred to as PODTherm-GP, is evaluated in terms of its efficiency and accuracy in a multi-core CPU. The GP projects the heat transfer equation onto a mathematical space whose basis functions are generated from thermal data enabled by the POD learning algorithm. The thermal solution data are collected from FEniCS using the finite element method (FEM) accounting for appropriate parametric variations. The GP incorporates physical principles of heat transfer in the methodology to reach high accuracy and efficiency. The dynamic power map for the CPU in FEM thermal simulation is generated from gem5 and McPACT, together with the SPLASH-2 benchmarks as the simulation workload. It is shown that PODTherm-GP offers an accurate thermal prediction of the CPU with a resolution as fine as the FEM. It is also demonstrated that PODTherm-GP is capable of predicting the dynamic thermal profile of the chip with a good accuracy beyond the training conditions. Additionally, the approach offers a reduction in degrees of freedom by more than 5 orders of magnitude and a speedup of 4 orders, compared to the FEM.
AutoLock: Automatic Design of Logic Locking with Evolutionary Computation
Paper ↗
Abstract
Logic locking protects the integrity of hardware designs throughout the integrated circuit supply chain. However, recent machine learning (ML)-based attacks have challenged its fundamental security, initiating the requirement for the design of learning-resilient locking policies. A promising ML-resilient locking mechanism hides within multiplexer-based locking. Nevertheless, recent attacks have successfully breached these state-of-the-art locking schemes, making it ever more complex to manually design policies that are resilient to all existing attacks. In this project, for the first time, we propose the automatic design exploration of logic locking with evolutionary computation (EC) -- a set of versatile black-box optimization heuristics inspired by evolutionary mechanisms. The project will evaluate the performance of EC-designed logic locking against various types of attacks, starting with the latest ML-based link prediction. Additionally, the project will provide guidelines and best practices for using EC-based logic locking in practical applications.
A Deep Learning Framework for Verilog Autocompletion Towards Design and Verification Automation
Paper ↗
Abstract
Innovative Electronic Design Automation (EDA) solutions are important to meet the design requirements for increasingly complex electronic devices. Verilog, a hardware description language, is widely used for the design and verification of digital circuits and is synthesized using specific EDA tools. However, writing code is a repetitive and time-intensive task. This paper proposes, primarily, a novel deep learning framework for training a Verilog autocompletion model and, secondarily, a Verilog dataset of files and snippets obtained from open-source repositories. The framework involves integrating models pretrained on general programming language data and finetuning them on a dataset curated to be similar to a target downstream task. This is validated by comparing different pretrained models trained on different subsets of the proposed Verilog dataset using multiple evaluation metrics. These experiments demonstrate that the proposed framework achieves better BLEU, ROUGE-L, and chrF scores by 9.5%, 6.7%, and 6.9%, respectively, compared to a model trained from scratch. Code and data are made available at: https://github.com/99EnriqueD/verilog_autocompletion .
Hier-RTLMP: A Hierarchical Automatic Macro Placer for Large-scale Complex IP Blocks
Paper ↗
Abstract
In a typical RTL to GDSII flow, floorplanning or macro placement is a critical step in achieving decent quality of results (QoR). Moreover, in today's physical synthesis flows (e.g., Synopsys Fusion Compiler or Cadence Genus iSpatial), a floorplan .def with macro and IO pin placements is typically needed as an input to the front-end physical synthesis. Recently, with the increasing complexity of IP blocks, and in particular with auto-generated RTL for machine learning (ML) accelerators, the number of hard macros in a single RTL block can easily run into the several hundreds. This makes the task of generating an automatic floorplan (.def) with IO pin and macro placements for front-end physical synthesis even more critical and challenging. The so-called peripheral approach of forcing macros to the periphery of the layout is no longer viable when the ratio of the sum of the macro perimeters to the floorplan perimeter is large, since this increases the required stacking depth of macros. In this paper, we develop a novel multilevel physical planning approach that exploits the hierarchy and dataflow inherent in the design RTL, and describe its realization in a new hierarchical macro placer, Hier-RTLMP. Hier-RTLMP borrows from traditional approaches used in manual system-on-chip (SoC) floorplanning to create an automatic macro placement for use with large IP blocks containing very large numbers of hard macros. Empirical studies demonstrate substantial improvements over the previous RTL-MP macro placement approach, and promising post-route improvements relative to a leading commercial place-and-route tool.
RESPECT: Reinforcement Learning based Edge Scheduling on Pipelined Coral Edge TPUs
Paper ↗
Abstract
Deep neural networks (DNNs) have substantial computational and memory requirements, and the compilation of its computational graphs has a great impact on the performance of resource-constrained (e.g., computation, I/O, and memory-bound) edge computing systems. While efficient execution of their computational graph requires an effective scheduling algorithm, generating the optimal scheduling solution is a challenging NP-hard problem. Furthermore, the complexity of scheduling DNN computational graphs will further increase on pipelined multi-core systems considering memory communication cost, as well as the increasing size of DNNs. Using the synthetic graph for the training dataset, this work presents a reinforcement learning (RL) based scheduling framework RESPECT, which learns the behaviors of optimal optimization algorithms and generates near-optimal scheduling results with short solving runtime overhead. Our framework has demonstrated up to $\sim2.5\times$ real-world on-chip inference runtime speedups over the commercial compiler with ten popular ImageNet models deployed on the physical Coral Edge TPUs system. Moreover, compared to the exact optimization methods, the proposed RL scheduling improves the scheduling optimization runtime by up to 683$\times$ speedups compared to the commercial compiler and matches the exact optimal solutions with up to 930$\times$ speedups. Finally, we perform a comprehensive generalizability test, which demonstrates RESPECT successfully imitates optimal solving behaviors from small synthetic graphs to large real-world DNNs computational graphs.
Deep Photonic Networks with Arbitrary and Broadband Functionality
Paper ↗
Abstract
Growing application space in optical communications, computing, and sensing continues to drive the need for high-performance integrated photonic components. Designing these on-chip systems with complex and application-specific functionality requires beyond what is possible with physical intuition, for which machine learning-based design methods have recently become popular. However, as the expensive computational requirements for physically accurate device simulations last a critical challenge, these methods typically remain limited in scalability and the optical design degrees of freedom they can provide for application-specific and arbitrary photonic integrated circuits. Here, we introduce a highly-scalable, physics-informed framework for the design of on-chip optical systems with arbitrary functionality based on a deep photonic network of custom-designed Mach-Zehnder interferometers. Using this framework, we design ultra-broadband power splitters and a spectral duplexer, each in less than two minutes, and demonstrate state-of-the-art experimental performance with less than 0.66 dB insertion loss and over 120 nm of 1-dB bandwidth for all devices. Our presented framework provides an essential tool with a tractable path towards the systematic design of large-scale photonic systems with custom and broadband power, phase, and dispersion profiles for use in multi-band optical applications including high-throughput communications, quantum information processing, and medical/biological sensing.
Gamora: Graph Learning based Symbolic Reasoning for Large-Scale Boolean Networks
Paper ↗
Abstract
Reasoning high-level abstractions from bit-blasted Boolean networks (BNs) such as gate-level netlists can significantly benefit functional verification, logic minimization, datapath synthesis, malicious logic identification, etc. Mostly, conventional reasoning approaches leverage structural hashing and functional propagation, suffering from limited scalability and inefficient usage of modern computing power. In response, we propose a novel symbolic reasoning framework exploiting graph neural networks (GNNs) and GPU acceleration to reason high-level functional blocks from gate-level netlists, namely Gamora, which offers high reasoning performance w.r.t exact reasoning algorithms, strong scalability to BNs with over 33 million nodes, and generalization capability from simple to complex designs. To further demonstrate the capability of Gamora, we also evaluate its reasoning performance after various technology mapping options, since technology-dependent optimizations are known to make functional reasoning much more challenging. Experimental results show that (1) Gamora reaches almost 100% and over 97% reasoning accuracy for carry-save-array (CSA) and Booth-encoded multipliers, respectively, with up to six orders of magnitude speedups compared to the state-of-the-art implementation in the ABC framework; (2) Gamora maintains high reasoning accuracy (>92%) in finding functional modules after complex technology mapping, upon which we comprehensively analyze the impacts on Gamora reasoning from technology mapping.
Statistical Hardware Design With Multi-model Active Learning
Paper ↗
Abstract
With the rising complexity of numerous novel applications that serve our modern society comes the strong need to design efficient computing platforms. Designing efficient hardware is, however, a complex multi-objective problem that deals with multiple parameters and their interactions. Given that there are a large number of parameters and objectives involved in hardware design, synthesizing all possible combinations is not a feasible method to find the optimal solution. One promising approach to tackle this problem is statistical modeling of a desired hardware performance. Here, we propose a model-based active learning approach to solve this problem. Our proposed method uses Bayesian models to characterize various aspects of hardware performance. We also use transfer learning and Gaussian regression bootstrapping techniques in conjunction with active learning to create more accurate models. Our proposed statistical modeling method provides hardware models that are sufficiently accurate to perform design space exploration as well as performance prediction simultaneously. We use our proposed method to perform design space exploration and performance prediction for various hardware setups, such as micro-architecture design and OpenCL kernels for FPGA targets. Our experiments show that the number of samples required to create performance models significantly reduces while maintaining the predictive power of our proposed statistical models. For instance, in our performance prediction setting, the proposed method needs 65% fewer samples to create the model, and in the design space exploration setting, our proposed method can find the best parameter settings by exploring less than 50 samples.
Quantile Online Learning for Semiconductor Failure Analysis
Paper ↗
Abstract
With high device integration density and evolving sophisticated device structures in semiconductor chips, detecting defects becomes elusive and complex. Conventionally, machine learning (ML)-guided failure analysis is performed with offline batch mode training. However, the occurrence of new types of failures or changes in the data distribution demands retraining the model. During the manufacturing process, detecting defects in a single-pass online fashion is more challenging and favoured. This paper focuses on novel quantile online learning for semiconductor failure analysis. The proposed method is applied to semiconductor device-level defects: FinFET bridge defect, GAA-FET bridge defect, GAA-FET dislocation defect, and a public database: SECOM. From the obtained results, we observed that the proposed method is able to perform better than the existing methods. Our proposed method achieved an overall accuracy of 86.66% and compared with the second-best existing method it improves 15.50% on the GAA-FET dislocation defect dataset.
MOELA: A Multi-Objective Evolutionary/Learning Design Space Exploration Framework for 3D Heterogeneous Manycore Platforms
Paper ↗
Abstract
To enable emerging applications such as deep machine learning and graph processing, 3D network-on-chip (NoC) enabled heterogeneous manycore platforms that can integrate many processing elements (PEs) are needed. However, designing such complex systems with multiple objectives can be challenging due to the huge associated design space and long evaluation times. To optimize such systems, we propose a new multi-objective design space exploration framework called MOELA that combines the benefits of evolutionary-based search with a learning-based local search to quickly determine PE and communication link placement to optimize multiple objectives (e.g., latency, throughput, and energy) in 3D NoC enabled heterogeneous manycore systems. Compared to state-of-the-art approaches, MOELA increases the speed of finding solutions by up to 128x, leads to a better Pareto Hypervolume (PHV) by up to 12.14x and improves energy-delay-product (EDP) by up to 7.7% in a 5-objective scenario.
Quantum Power Electronics: From Theory to Implementation
Paper ↗
Abstract
While impressive progress has been already achieved in wide-bandgap (WBG) semicon-ductors such as 4H-SiC and GaN technologies, the lack of intelligent methodologies to control the gate drives prevented to the exploit the maximum potential of semiconductor chips, from obtaining the desired devices operations. Thus, a potent ongoing trend is to design a fast gate driver switching scheme to upgrade the performance of electronic equipment at the system level. To address this issue, this work proposes a novel intelligent scheme for the control of gate driver switching using the concept of quantum computation in machine learning. In particular, the quantum principle is incorporated into deep reinforcement learning (DRL) to address the hardware limitations of con-ventional computers and the growing amount of data sets. Taking potential benefits of quantum theory, the DRL algorithm influenced by quantum specifications (referred to as QDRL) will not only ameliorate the performance of the native algorithm on traditional computers, but also enhance the progress of relevant research fields like quantum computing and machine learning. To test the prac-ticability and usefulness of QDRL, a dc/dc parallel boost converters feeding constant power loads (CPLs) is chosen as the case study, and several Power Hard-ware-in-the-loop (PHiL) experiments and comparative analysis are given.
Xel-FPGAs: An End-to-End Automated Exploration Framework for Approximate Accelerators in FPGA-Based Systems
Paper ↗
Abstract
Generation and exploration of approximate circuits and accelerators has been a prominent research domain to achieve energy-efficiency and/or performance improvements. This research has predominantly focused on ASICs, while not achieving similar gains when deployed for FPGA-based accelerator systems, due to the inherent architectural differences between the two. In this work, we propose a novel framework, Xel-FPGAs, which leverages statistical or machine learning models to effectively explore the architecture-space of state-of-the-art ASIC-based approximate circuits to cater them for FPGA-based systems given a simple RTL description of the target application. We have also evaluated the scalability of our framework on a multi-stage application using a hierarchical search strategy. The Xel-FPGAs framework is capable of reducing the exploration time by up to 95%, when compared to the default synthesis, place, and route approaches, while identifying an improved set of Pareto-optimal designs for a given application, when compared to the state-of-the-art. The complete framework is open-source and available online at https://github.com/ehw-fit/xel-fpgas.
ALMOST: Adversarial Learning to Mitigate Oracle-less ML Attacks via Synthesis Tuning
Paper ↗
Abstract
Oracle-less machine learning (ML) attacks have broken various logic locking schemes. Regular synthesis, which is tailored for area-power-delay optimization, yields netlists where key-gate localities are vulnerable to learning. Thus, we call for security-aware logic synthesis. We propose ALMOST, a framework for adversarial learning to mitigate oracle-less ML attacks via synthesis tuning. ALMOST uses a simulated-annealing-based synthesis recipe generator, employing adversarially trained models that can predict state-of-the-art attacks' accuracies over wide ranges of recipes and key-gate localities. Experiments on ISCAS benchmarks confirm the attacks' accuracies drops to around 50\% for ALMOST-synthesized circuits, all while not undermining design optimization.
DeepSeq: Deep Sequential Circuit Learning
Paper ↗
Abstract
Circuit representation learning is a promising research direction in the electronic design automation (EDA) field. With sufficient data for pre-training, the learned general yet effective representation can help to solve multiple downstream EDA tasks by fine-tuning it on a small set of task-related data. However, existing solutions only target combinational circuits, significantly limiting their applications. In this work, we propose DeepSeq, a novel representation learning framework for sequential netlists. Specifically, we introduce a dedicated graph neural network (GNN) with a customized propagation scheme to exploit the temporal correlations between gates in sequential circuits. To ensure effective learning, we propose to use a multi-task training objective with two sets of strongly related supervision: logic probability and transition probability at each node. A novel dual attention aggregation mechanism is introduced to facilitate learning both tasks efficiently. Experimental results on various benchmark circuits show that DeepSeq outperforms other GNN models for sequential circuit learning. We evaluate the generalization capability of DeepSeq on a downstream power estimation task. After fine-tuning, DeepSeq can accurately estimate power across various circuits under different workloads.
AutoML for neuromorphic computing and application-driven co-design: asynchronous, massively parallel optimization of spiking architectures
Paper ↗
Abstract
In this work we have extended AutoML inspired approaches to the exploration and optimization of neuromorphic architectures. Through the integration of a parallel asynchronous model-based search approach with a simulation framework to simulate spiking architectures, we are able to efficiently explore the configuration space of neuromorphic architectures and identify the subset of conditions leading to the highest performance in a targeted application. We have demonstrated this approach on an exemplar case of real time, on-chip learning application. Our results indicate that we can effectively use optimization approaches to optimize complex architectures, therefore providing a viable pathway towards application-driven codesign.
DeepOHeat: Operator Learning-based Ultra-fast Thermal Simulation in 3D-IC Design
Paper ↗
Abstract
Thermal issue is a major concern in 3D integrated circuit (IC) design. Thermal optimization of 3D IC often requires massive expensive PDE simulations. Neural network-based thermal prediction models can perform real-time prediction for many unseen new designs. However, existing works either solve 2D temperature fields only or do not generalize well to new designs with unseen design configurations (e.g., heat sources and boundary conditions). In this paper, for the first time, we propose DeepOHeat, a physics-aware operator learning framework to predict the temperature field of a family of heat equations with multiple parametric or non-parametric design configurations. This framework learns a functional map from the function space of multiple key PDE configurations (e.g., boundary conditions, power maps, heat transfer coefficients) to the function space of the corresponding solution (i.e., temperature fields), enabling fast thermal analysis and optimization by changing key design configurations (rather than just some parameters). We test DeepOHeat on some industrial design cases and compare it against Celsius 3D from Cadence Design Systems. Our results show that, for the unseen testing cases, a well-trained DeepOHeat can produce accurate results with $1000\times$ to $300000\times$ speedup.
Machine Learning-based Low Overhead Congestion Control Algorithm for Industrial NoCs
Paper ↗
Abstract
Network-on-Chip (NoC) congestion builds up during heavy traffic load and cripples the system performance by stalling the cores. Moreover, congestion leads to wasted link bandwidth due to blocked buffers and bouncing packets. Existing approaches throttle the cores after congestion is detected, reducing efficiency and wasting line bandwidth unnecessarily. In contrast, we propose a lightweight machine learning-based technique that helps predict congestion in the network. Specifically, our proposed technique collects the features related to traffic at each destination. Then, it labels the features using a novel time reversal approach. The labeled data is used to design a low overhead and an explainable decision tree model used at runtime congestion control. Experimental evaluations with synthetic and real traffic on industrial 6$\times$6 NoC show that the proposed approach increases fairness and memory read bandwidth by up to 114\% with respect to existing congestion control technique while incurring less than 0.01\% of overhead.
HLSDataset: Open-Source Dataset for ML-Assisted FPGA Design using High Level Synthesis
Paper ↗
Abstract
Machine Learning (ML) has been widely adopted in design exploration using high level synthesis (HLS) to give a better and faster performance, and resource and power estimation at very early stages for FPGA-based design. To perform prediction accurately, high-quality and large-volume datasets are required for training ML models.This paper presents a dataset for ML-assisted FPGA design using HLS, called HLSDataset. The dataset is generated from widely used HLS C benchmarks including Polybench, Machsuite, CHStone and Rossetta. The Verilog samples are generated with a variety of directives including loop unroll, loop pipeline and array partition to make sure optimized and realistic designs are covered. The total number of generated Verilog samples is nearly 9,000 per FPGA type. To demonstrate the effectiveness of our dataset, we undertake case studies to perform power estimation and resource usage estimation with ML models trained with our dataset. All the codes and dataset are public at the github repo.We believe that HLSDataset can save valuable time for researchers by avoiding the tedious process of running tools, scripting and parsing files to generate the dataset, and enable them to spend more time where it counts, that is, in training ML models.
Qualitative Data Augmentation for Performance Prediction in VLSI circuits
Paper ↗
Abstract
Various studies have shown the advantages of using Machine Learning (ML) techniques for analog and digital IC design automation and optimization. Data scarcity is still an issue for electronic designs, while training highly accurate ML models. This work proposes generating and evaluating artificial data using generative adversarial networks (GANs) for circuit data to aid and improve the accuracy of ML models trained with a small training data set. The training data is obtained by various simulations in the Cadence Virtuoso, HSPICE, and Microcap design environment with TSMC 180nm and 22nm CMOS technology nodes. The artificial data is generated and tested for an appropriate set of analog and digital circuits. The experimental results show that the proposed artificial data generation significantly improves ML models and reduces the percentage error by more than 50\% of the original percentage error, which were previously trained with insufficient data. Furthermore, this research aims to contribute to the extensive application of AI/ML in the field of VLSI design and technology by relieving the training data availability-related challenges.
Semiconductor Fab Scheduling with Self-Supervised and Reinforcement Learning
Paper ↗
Abstract
Semiconductor manufacturing is a notoriously complex and costly multi-step process involving a long sequence of operations on expensive and quantity-limited equipment. Recent chip shortages and their impacts have highlighted the importance of semiconductors in the global supply chains and how reliant on those our daily lives are. Due to the investment cost, environmental impact, and time scale needed to build new factories, it is difficult to ramp up production when demand spikes. This work introduces a method to successfully learn to schedule a semiconductor manufacturing facility more efficiently using deep reinforcement and self-supervised learning. We propose the first adaptive scheduling approach to handle complex, continuous, stochastic, dynamic, modern semiconductor manufacturing models. Our method outperforms the traditional hierarchical dispatching strategies typically used in semiconductor manufacturing plants, substantially reducing each order's tardiness and time until completion. As a result, our method yields a better allocation of resources in the semiconductor manufacturing process.
SF-SGL: Solver-Free Spectral Graph Learning from Linear Measurements
Paper ↗
Abstract
This work introduces a highly-scalable spectral graph densification framework (SGL) for learning resistor networks with linear measurements, such as node voltages and currents. We show that the proposed graph learning approach is equivalent to solving the classical graphical Lasso problems with Laplacian-like precision matrices. We prove that given $O(\log N)$ pairs of voltage and current measurements, it is possible to recover sparse $N$-node resistor networks that can well preserve the effective resistance distances on the original graph. In addition, the learned graphs also preserve the structural (spectral) properties of the original graph, which can potentially be leveraged in many circuit design and optimization tasks. To achieve more scalable performance, we also introduce a solver-free method (SF-SGL) that exploits multilevel spectral approximation of the graphs and allows for a scalable and flexible decomposition of the entire graph spectrum (to be learned) into multiple different eigenvalue clusters (frequency bands). Such a solver-free approach allows us to more efficiently identify the most spectrally-critical edges for reducing various ranges of spectral embedding distortions. Through extensive experiments for a variety of real-world test cases, we show that the proposed approach is highly scalable for learning sparse resistor networks without sacrificing solution quality. We also introduce a data-driven EDA algorithm for vectorless power/thermal integrity verifications to allow estimating worst-case voltage/temperature (gradient) distributions across the entire chip by leveraging a few voltage/temperature measurements.
AISYN: AI-driven Reinforcement Learning-Based Logic Synthesis Framework
Paper ↗
Abstract
Logic synthesis is one of the most important steps in design and implementation of digital chips with a big impact on final Quality of Results (QoR). For a most general input circuit modeled by a Directed Acyclic Graph (DAG), many logic synthesis problems such as delay or area minimization are NP-Complete, hence, no optimal solution is available. This is why many classical logic optimization functions tend to follow greedy approaches that are easily trapped in local minima that does not allow improving QoR as much as needed. We believe that Artificial Intelligence (AI) and more specifically Reinforcement Learning (RL) algorithms can help in solving this problem. This is because AI and RL can help minimizing QoR further by exiting from local minima. Our experiments on both open source and industrial benchmark circuits show that significant improvements on important metrics such as area, delay, and power can be achieved by making logic synthesis optimization functions AI-driven. For example, our RL-based rewriting algorithm could improve total cell area post-synthesis by up to 69.3% when compared to a classical rewriting algorithm with no AI awareness.
Fixing Hardware Security Bugs with Large Language Models
Paper ↗
Abstract
Novel AI-based code-writing Large Language Models (LLMs) such as OpenAI's Codex have demonstrated capabilities in many coding-adjacent domains. In this work we consider how LLMs maybe leveraged to automatically repair security relevant bugs present in hardware designs. We focus on bug repair in code written in the Hardware Description Language Verilog. For this study we build a corpus of domain-representative hardware security bugs. We then design and implement a framework to quantitatively evaluate the performance of any LLM tasked with fixing the specified bugs. The framework supports design space exploration of prompts (i.e., prompt engineering) and identifying the best parameters for the LLM. We show that an ensemble of LLMs can repair all ten of our benchmarks. This ensemble outperforms the state-of-the-art Cirfix hardware bug repair tool on its own suite of bugs. These results show that LLMs can repair hardware security bugs and the framework is an important step towards the ultimate goal of an automated end-to-end bug repair framework.
Feature space exploration as an alternative for design space exploration beyond the parametric space
Paper ↗
Abstract
This paper compares the parametric design space with a feature space generated by the extraction of design features using deep learning (DL) as an alternative way for design space exploration. In this comparison, the parametric design space is constructed by creating a synthetic dataset of 15.000 elements using a parametric algorithm and reducing its dimensions for visualization. The feature space - reduced-dimensionality vector space of embedded data features - is constructed by training a DL model on the same dataset. We analyze and compare the extracted design features by reducing their dimension and visualizing the results. We demonstrate that parametric design space is narrow in how it describes the design solutions because it is based on the combination of individual parameters. In comparison, we observed that the feature design space can intuitively represent design solutions according to complex parameter relationships. Based on our results, we discuss the potential of translating the features learned by DL models to provide a mechanism for intuitive design exploration space and visualization of possible design solutions.
Design Optimization of Noise Filter using Quantum Annealer
Paper ↗
Abstract
The use of quantum annealers in black-box optimization to obtain the desired properties of a product with a small number of trials has attracted attention. However, the application of this technique to engineering design problems is still limited. Here, we demonstrate the applicability of black-box optimization with a quantum annealer to the design of electric circuit systems, focusing on $\pi$-type noise filters as an example. We develop a framework that uses quantum annealing to find the optimal location of electrical components and conductor paths connecting the components, and confirm that the learning process appropriately works over a number of trials to efficiently search for a design with high performance. The results show the potential applicability of quantum annealing to design problems of electric circuit systems.
Comprehensive Mapping of Continuous/Switching Circuits in CCM and DCM to Machine Learning Domain using Homogeneous Graph Neural Networks
Paper ↗
Abstract
This paper proposes a method of transferring physical continuous and switching/converter circuits working in continuous conduction mode (CCM) and discontinuous conduction mode (DCM) to graph representation, independent of the connection or the number of circuit components, so that machine learning (ML) algorithms and applications can be easily applied. Such methodology is generalized and is applicable to circuits with any number of switches, components, sources and loads, and can be useful in applications such as artificial intelligence (AI) based circuit design automation, layout optimization, circuit synthesis and performance monitoring and control. The proposed circuit representation and feature extraction methodology is applied to seven types of continuous circuits, ranging from second to fourth order and it is also applied to three of the most common converters (Buck, Boost, and Buck-boost) operating in CCM or DCM. A classifier ML task can easily differentiate between circuit types as well as their mode of operation, showing classification accuracy of 97.37% in continuous circuits and 100% in switching circuits
NoSQL Database Tuning through Machine Learning
Paper ↗
Abstract
NoSQL databases have become an important component of many big data and real-time web applications. Their distributed nature and scalability make them an ideal data storage repository for a variety of use cases. While NoSQL databases are delivered with a default ''off-the-shelf'' configuration, they offer configuration settings to adjust a database's behavior and performance to a specific use case and environment. The abundance and oftentimes imperceptible inter-dependencies of configuration settings make it difficult to optimize and performance-tune a NoSQL system. There is no one-size-fits-all configuration and therefore the workload, the physical design, and available resources need to be taken into account when optimizing the configuration of a NoSQL database. This work explores Machine Learning as a means to automatically tune a NoSQL database for optimal performance. Using Random Forest and Gradient Boosting Decision Tree Machine Learning algorithms, multiple Machine Learning models were fitted with a training dataset that incorporates properties of the NoSQL physical configuration (replication and sharding). The best models were then employed as surrogate models to optimize the Database Management System's configuration settings for throughput and latency using a Black-box Optimization algorithm. Using an Apache Cassandra database, multiple experiments were carried out to demonstrate the feasibility of this approach, even across varying physical configurations. The tuned DBMS configurations yielded throughput improvements of up to 4%, read latency reductions of up to 43%, and write latency reductions of up to 39% when compared to the default configuration settings.
Benchmarking Large Language Models for Automated Verilog RTL Code Generation
Paper ↗
Abstract
Automating hardware design could obviate a significant amount of human error from the engineering process and lead to fewer errors. Verilog is a popular hardware description language to model and design digital systems, thus generating Verilog code is a critical first step. Emerging large language models (LLMs) are able to write high-quality code in other programming languages. In this paper, we characterize the ability of LLMs to generate useful Verilog. For this, we fine-tune pre-trained LLMs on Verilog datasets collected from GitHub and Verilog textbooks. We construct an evaluation framework comprising test-benches for functional analysis and a flow to test the syntax of Verilog code generated in response to problems of varying difficulty. Our findings show that across our problem scenarios, the fine-tuning results in LLMs more capable of producing syntactically correct code (25.9% overall). Further, when analyzing functional correctness, a fine-tuned open-source CodeGen LLM can outperform the state-of-the-art commercial Codex LLM (6.5% overall). Training/evaluation scripts and LLM checkpoints are available: https://github.com/shailja-thakur/VGen.
Compiler Optimization for Quantum Computing Using Reinforcement Learning
Paper ↗
Abstract
Any quantum computing application, once encoded as a quantum circuit, must be compiled before being executable on a quantum computer. Similar to classical compilation, quantum compilation is a sequential process with many compilation steps and numerous possible optimization passes. Despite the similarities, the development of compilers for quantum computing is still in its infancy -- lacking mutual consolidation on the best sequence of passes, compatibility, adaptability, and flexibility. In this work, we take advantage of decades of classical compiler optimization and propose a reinforcement learning framework for developing optimized quantum circuit compilation flows. Through distinct constraints and a unifying interface, the framework supports the combination of techniques from different compilers and optimization tools in a single compilation flow. Experimental evaluations show that the proposed framework -- set up with a selection of compilation passes from IBM's Qiskit and Quantinuum's TKET -- significantly outperforms both individual compilers in 73% of cases regarding the expected fidelity. The framework is available on GitHub (https://github.com/cda-tum/MQTPredictor) as part of the Munich Quantum Toolkit (MQT).
Denoising Diffusion for Sampling SAT Solutions
Paper ↗
Abstract
Generating diverse solutions to the Boolean Satisfiability Problem (SAT) is a hard computational problem with practical applications for testing and functional verification of software and hardware designs. We explore the way to generate such solutions using Denoising Diffusion coupled with a Graph Neural Network to implement the denoising function. We find that the obtained accuracy is similar to the currently best purely neural method and the produced SAT solutions are highly diverse, even if the system is trained with non-random solutions from a standard solver.
Graph Neural Networks: A Powerful and Versatile Tool for Advancing Design, Reliability, and Security of ICs
Paper ↗
Abstract
Graph neural networks (GNNs) have pushed the state-of-the-art (SOTA) for performance in learning and predicting on large-scale data present in social networks, biology, etc. Since integrated circuits (ICs) can naturally be represented as graphs, there has been a tremendous surge in employing GNNs for machine learning (ML)-based methods for various aspects of IC design. Given this trajectory, there is a timely need to review and discuss some powerful and versatile GNN approaches for advancing IC design. In this paper, we propose a generic pipeline for tailoring GNN models toward solving challenging problems for IC design. We outline promising options for each pipeline element, and we discuss selected and promising works, like leveraging GNNs to break SOTA logic obfuscation. Our comprehensive overview of GNNs frameworks covers (i) electronic design automation (EDA) and IC design in general, (ii) design of reliable ICs, and (iii) design as well as analysis of secure ICs. We provide our overview and related resources also in the GNN4IC hub at https://github.com/DfX-NYUAD/GNN4IC. Finally, we discuss interesting open problems for future research.
Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration
Paper ↗
Abstract
Microprocessor architects are increasingly resorting to domain-specific customization in the quest for high-performance and energy-efficiency. As the systems grow in complexity, fine-tuning architectural parameters across multiple sub-systems (e.g., datapath, memory blocks in different hierarchies, interconnects, compiler optimization, etc.) quickly results in a combinatorial explosion of design space. This makes domain-specific customization an extremely challenging task. Prior work explores using reinforcement learning (RL) and other optimization methods to automatically explore the large design space. However, these methods have traditionally relied on single-agent RL/ML formulations. It is unclear how scalable single-agent formulations are as we increase the complexity of the design space (e.g., full stack System-on-Chip design). Therefore, we propose an alternative formulation that leverages Multi-Agent RL (MARL) to tackle this problem. The key idea behind using MARL is an observation that parameters across different sub-systems are more or less independent, thus allowing a decentralized role assigned to each agent. We test this hypothesis by designing domain-specific DRAM memory controller for several workload traces. Our evaluation shows that the MARL formulation consistently outperforms single-agent RL baselines such as Proximal Policy Optimization and Soft Actor-Critic over different target objectives such as low power and latency. To this end, this work opens the pathway for new and promising research in MARL solutions for hardware architecture search.
MaskPlace: Fast Chip Placement via Reinforced Visual Representation Learning
Paper ↗
Abstract
Placement is an essential task in modern chip design, aiming at placing millions of circuit modules on a 2D chip canvas. Unlike the human-centric solution, which requires months of intense effort by hardware engineers to produce a layout to minimize delay and energy consumption, deep reinforcement learning has become an emerging autonomous tool. However, the learning-centric method is still in its early stage, impeded by a massive design space of size ten to the order of a few thousand. This work presents MaskPlace to automatically generate a valid chip layout design within a few hours, whose performance can be superior or comparable to recent advanced approaches. It has several appealing benefits that prior arts do not have. Firstly, MaskPlace recasts placement as a problem of learning pixel-level visual representation to comprehensively describe millions of modules on a chip, enabling placement in a high-resolution canvas and a large action space. It outperforms recent methods that represent a chip as a hypergraph. Secondly, it enables training the policy network by an intuitive reward function with dense reward, rather than a complicated reward function with sparse reward from previous methods. Thirdly, extensive experiments on many public benchmarks show that MaskPlace outperforms existing RL approaches in all key performance metrics, including wirelength, congestion, and density. For example, it achieves 60%-90% wirelength reduction and guarantees zero overlaps. We believe MaskPlace can improve AI-assisted chip layout design. The deliverables are released at https://laiyao1.github.io/maskplace.
DeepFlow: A Cross-Stack Pathfinding Framework for Distributed AI Systems
Paper ↗
Abstract
Over the past decade, machine learning model complexity has grown at an extraordinary rate, as has the scale of the systems training such large models. However there is an alarmingly low hardware utilization (5-20%) in large scale AI systems. The low system utilization is a cumulative effect of minor losses across different layers of the stack, exacerbated by the disconnect between engineers designing different layers spanning across different industries. We propose CrossFlow, a novel framework that enables cross-layer analysis all the way from the technology layer to the algorithmic layer. We also propose DeepFlow (built on top of CrossFlow using machine learning techniques) to automate the design space exploration and co-optimization across different layers of the stack. We have validated CrossFlow accuracy with distributed training on real commercial hardware and showcase several DeepFlow case studies demonstrating pitfalls of not optimizing across the technology-hardware-software stack for what is likely, the most important workload driving large development investments in all aspects of computing stack.
Theta-Resonance: A Single-Step Reinforcement Learning Method for Design Space Exploration
Paper ↗
Abstract
Given an environment (e.g., a simulator) for evaluating samples in a specified design space and a set of weighted evaluation metrics -- one can use Theta-Resonance, a single-step Markov Decision Process (MDP), to train an intelligent agent producing progressively more optimal samples. In Theta-Resonance, a neural network consumes a constant input tensor and produces a policy as a set of conditional probability density functions (PDFs) for sampling each design dimension. We specialize existing policy gradient algorithms in deep reinforcement learning (D-RL) in order to use evaluation feedback (in terms of cost, penalty or reward) to update our policy network with robust algorithmic stability and minimal design evaluations. We study multiple neural architectures (for our policy network) within the context of a simple SoC design space and propose a method of constructing synthetic space exploration problems to compare and improve design space exploration (DSE) algorithms. Although we only present categorical design spaces, we also outline how to use Theta-Resonance in order to explore continuous and mixed continuous-discrete design spaces.
An Adversarial Active Sampling-based Data Augmentation Framework for Manufacturable Chip Design
Paper ↗
Abstract
Lithography modeling is a crucial problem in chip design to ensure a chip design mask is manufacturable. It requires rigorous simulations of optical and chemical models that are computationally expensive. Recent developments in machine learning have provided alternative solutions in replacing the time-consuming lithography simulations with deep neural networks. However, the considerable accuracy drop still impedes its industrial adoption. Most importantly, the quality and quantity of the training dataset directly affect the model performance. To tackle this problem, we propose a litho-aware data augmentation (LADA) framework to resolve the dilemma of limited data and improve the machine learning model performance. First, we pretrain the neural networks for lithography modeling and a gradient-friendly StyleGAN2 generator. We then perform adversarial active sampling to generate informative and synthetic in-distribution mask designs. These synthetic mask images will augment the original limited training dataset used to finetune the lithography model for improved performance. Experimental results demonstrate that LADA can successfully exploits the neural network capacity by narrowing down the performance gap between the training and testing data instances.
Material Prediction for Design Automation Using Graph Representation Learning
Paper ↗
Abstract
Successful material selection is critical in designing and manufacturing products for design automation. Designers leverage their knowledge and experience to create high-quality designs by selecting the most appropriate materials through performance, manufacturability, and sustainability evaluation. Intelligent tools can help designers with varying expertise by providing recommendations learned from prior designs. To enable this, we introduce a graph representation learning framework that supports the material prediction of bodies in assemblies. We formulate the material selection task as a node-level prediction task over the assembly graph representation of CAD models and tackle it using Graph Neural Networks (GNNs). Evaluations over three experimental protocols performed on the Fusion 360 Gallery dataset indicate the feasibility of our approach, achieving a 0.75 top-3 micro-f1 score. The proposed framework can scale to large datasets and incorporate designers' knowledge into the learning process. These capabilities allow the framework to serve as a recommendation system for design automation and a baseline for future work, narrowing the gap between human designers and intelligent design agents.
Material Prediction for Design Automation Using Graph Representation Learning
Paper ↗
Abstract
Successful material selection is critical in designing and manufacturing products for design automation. Designers leverage their knowledge and experience to create high-quality designs by selecting the most appropriate materials through performance, manufacturability, and sustainability evaluation. Intelligent tools can help designers with varying expertise by providing recommendations learned from prior designs. To enable this, we introduce a graph representation learning framework that supports the material prediction of bodies in assemblies. We formulate the material selection task as a node-level prediction task over the assembly graph representation of CAD models and tackle it using Graph Neural Networks (GNNs). Evaluations over three experimental protocols performed on the Fusion 360 Gallery dataset indicate the feasibility of our approach, achieving a 0.75 top-3 micro-f1 score. The proposed framework can scale to large datasets and incorporate designers' knowledge into the learning process. These capabilities allow the framework to serve as a recommendation system for design automation and a baseline for future work, narrowing the gap between human designers and intelligent design agents.
Mining SoC Message Flows with Attention Model
Paper ↗
Abstract
High-quality system-level message flow specifications are necessary for comprehensive validation of system-on-chip (SoC) designs. However, manual development and maintenance of such specifications are daunting tasks. We propose a disruptive method that utilizes deep sequence modeling with the attention mechanism to infer accurate flow specifications from SoC communication traces. The proposed method can overcome the inherent complexity of SoC traces induced by the concurrent executions of SoC designs that existing mining tools often find extremely challenging. We conduct experiments on five highly concurrent traces and find that the proposed approach outperforms several existing state-of-the-art trace mining tools.
A Thermal Machine Learning Solver For Chip Simulation
Paper ↗
Abstract
Thermal analysis provides deeper insights into electronic chips behavior under different temperature scenarios and enables faster design exploration. However, obtaining detailed and accurate thermal profile on chip is very time-consuming using FEM or CFD. Therefore, there is an urgent need for speeding up the on-chip thermal solution to address various system scenarios. In this paper, we propose a thermal machine-learning (ML) solver to speed-up thermal simulations of chips. The thermal ML-Solver is an extension of the recent novel approach, CoAEMLSim (Composable Autoencoder Machine Learning Simulator) with modifications to the solution algorithm to handle constant and distributed HTC. The proposed method is validated against commercial solvers, such as Ansys MAPDL, as well as a latest ML baseline, UNet, under different scenarios to demonstrate its enhanced accuracy, scalability, and generalizability.
Exploiting Nanoelectronic Properties of Memory Chips for Prevention of IC Counterfeiting
Paper ↗
Abstract
This study presents a methodology for anticounterfeiting of Non-Volatile Memory (NVM) chips. In particular, we experimentally demonstrate a generalized methodology for detecting (i) Integrated Circuit (IC) origin, (ii) recycled or used NVM chips, and (iii) identification of used locations (addresses) in the chip. Our proposed methodology inspects latency and variability signatures of Commercial-Off-The-Shelf (COTS) NVM chips. The proposed technique requires low-cycle (~100) pre-conditioning and utilizes Machine Learning (ML) algorithms. We observe different trends in evolution of latency (sector erase or page write) with cycling on different NVM technologies from different vendors. ML assisted approach is utilized for detecting IC manufacturers with 95.1 % accuracy obtained on prepared test dataset consisting of 3 different NVM technologies including 6 different manufacturers (9 types of chips).
TAG: Learning Circuit Spatial Embedding From Layouts
Paper ↗
Abstract
Analog and mixed-signal (AMS) circuit designs still rely on human design expertise. Machine learning has been assisting circuit design automation by replacing human experience with artificial intelligence. This paper presents TAG, a new paradigm of learning the circuit representation from layouts leveraging text, self-attention and graph. The embedding network model learns spatial information without manual labeling. We introduce text embedding and a self-attention mechanism to AMS circuit learning. Experimental results demonstrate the ability to predict layout distances between instances with industrial FinFET technology benchmarks. The effectiveness of the circuit representation is verified by showing the transferability to three other learning tasks with limited data in the case studies: layout matching prediction, wirelength estimation, and net parasitic capacitance prediction.
Deep Neural Network Augmented Wireless Channel Estimation for Preamble-based OFDM PHY on Zynq System on Chip
Paper ↗
Abstract
Reliable and fast channel estimation is crucial for next-generation wireless networks supporting a wide range of vehicular and low-latency services. Recently, deep learning (DL) based channel estimation has been explored as an efficient alternative to conventional least-square (LS) and linear minimum mean square error (LMMSE) approaches. Most of these DL approaches have not been realized on system-on-chip (SoC), and preliminary study shows that their complexity exceeds the complexity of the entire physical layer (PHY). The high latency of DL is another concern. This paper considers the design and implementation of deep neural network (DNN) augmented LS-based channel estimation (LSDNN) for preamble-based orthogonal frequency-division multiplexing (OFDM) physical layer (PHY) on SoC. We demonstrate the gain in performance compared to the conventional LS and LMMSE approaches. Via software-hardware co-design, word-length optimization, and reconfigurable architectures, we demonstrate the superiority of the LSDNN over the LS and LMMSE for a wide range of signal-to-noise ratio (SNR), number of pilots, preamble types, and wireless channels. Further, we evaluate the performance, power, and area (PPA) of the LS and LSDNN application-specific integrated circuit (ASIC) implementations in 45 nm technology. We demonstrate that word-length optimization can substantially improve PPA for the proposed architecture in ASIC implementations.
Neural Approaches to Co-Optimization in Robotics
Paper ↗
Abstract
Robots and intelligent systems that sense or interact with the world are increasingly being used to automate a wide array of tasks. The ability of these systems to complete these tasks depends on a large range of technologies such as the mechanical and electrical parts that make up the physical body of the robot and its sensors, perception algorithms to perceive the environment, and planning and control algorithms to produce meaningful actions. Therefore, it is often necessary to consider the interactions between these components when designing an embodied system. This thesis explores work on the task-driven co-optimization of robotics systems in an end-to-end manner, simultaneously optimizing the physical components of the system with inference or control algorithms directly for task performance. We start by considering the problem of optimizing a beacon-based localization system directly for localization accuracy. Designing such a system involves placing beacons throughout the environment and inferring location from sensor readings. In our work, we develop a deep learning approach to optimize both beacon placement and location inference directly for localization accuracy. We then turn our attention to the related problem of task-driven optimization of robots and their controllers. In our work, we start by proposing a data-efficient algorithm based on multi-task reinforcement learning. Our approach efficiently optimizes both physical design and control parameters directly for task performance by leveraging a design-conditioned controller capable of generalizing over the space of physical designs. We then follow this up with an extension to allow for the optimization over discrete morphological parameters such as the number and configuration of limbs. Finally, we conclude by exploring the fabrication and deployment of optimized soft robots.
Hermes: Accelerating Long-Latency Load Requests via Perceptron-Based Off-Chip Load Prediction
Paper ↗
Abstract
Long-latency load requests continue to limit the performance of high-performance processors. To increase the latency tolerance of a processor, architects have primarily relied on two key techniques: sophisticated data prefetchers and large on-chip caches. In this work, we show that: 1) even a sophisticated state-of-the-art prefetcher can only predict half of the off-chip load requests on average across a wide range of workloads, and 2) due to the increasing size and complexity of on-chip caches, a large fraction of the latency of an off-chip load request is spent accessing the on-chip cache hierarchy. The goal of this work is to accelerate off-chip load requests by removing the on-chip cache access latency from their critical path. To this end, we propose a new technique called Hermes, whose key idea is to: 1) accurately predict which load requests might go off-chip, and 2) speculatively fetch the data required by the predicted off-chip loads directly from the main memory, while also concurrently accessing the cache hierarchy for such loads. To enable Hermes, we develop a new lightweight, perceptron-based off-chip load prediction technique that learns to identify off-chip load requests using multiple program features (e.g., sequence of program counters). For every load request, the predictor observes a set of program features to predict whether or not the load would go off-chip. If the load is predicted to go off-chip, Hermes issues a speculative request directly to the memory controller once the load's physical address is generated. If the prediction is correct, the load eventually misses the cache hierarchy and waits for the ongoing speculative request to finish, thus hiding the on-chip cache hierarchy access latency from the critical path of the off-chip load. Our evaluation shows that Hermes significantly improves performance of a state-of-the-art baseline. We open-source Hermes.
Reinforcement Learning for Hardware Security: Opportunities, Developments, and Challenges
Paper ↗
Abstract
Reinforcement learning (RL) is a machine learning paradigm where an autonomous agent learns to make an optimal sequence of decisions by interacting with the underlying environment. The promise demonstrated by RL-guided workflows in unraveling electronic design automation problems has encouraged hardware security researchers to utilize autonomous RL agents in solving domain-specific problems. From the perspective of hardware security, such autonomous agents are appealing as they can generate optimal actions in an unknown adversarial environment. On the other hand, the continued globalization of the integrated circuit supply chain has forced chip fabrication to off-shore, untrustworthy entities, leading to increased concerns about the security of the hardware. Furthermore, the unknown adversarial environment and increasing design complexity make it challenging for defenders to detect subtle modifications made by attackers (a.k.a. hardware Trojans). In this brief, we outline the development of RL agents in detecting hardware Trojans, one of the most challenging hardware security problems. Additionally, we outline potential opportunities and enlist the challenges of applying RL to solve hardware security problems.
DETERRENT: Detecting Trojans using Reinforcement Learning
Paper ↗
Abstract
Insertion of hardware Trojans (HTs) in integrated circuits is a pernicious threat. Since HTs are activated under rare trigger conditions, detecting them using random logic simulations is infeasible. In this work, we design a reinforcement learning (RL) agent that circumvents the exponential search space and returns a minimal set of patterns that is most likely to detect HTs. Experimental results on a variety of benchmarks demonstrate the efficacy and scalability of our RL agent, which obtains a significant reduction ($169\times$) in the number of test patterns required while maintaining or improving coverage ($95.75\%$) compared to the state-of-the-art techniques.
LEAPER: Fast and Accurate FPGA-based System Performance Prediction via Transfer Learning
Paper ↗
Abstract
Machine learning has recently gained traction as a way to overcome the slow accelerator generation and implementation process on an FPGA. It can be used to build performance and resource usage models that enable fast early-stage design space exploration. First, training requires large amounts of data (features extracted from design synthesis and implementation tools), which is cost-inefficient because of the time-consuming accelerator design and implementation process. Second, a model trained for a specific environment cannot predict performance or resource usage for a new, unknown environment. In a cloud system, renting a platform for data collection to build an ML model can significantly increase the total-cost-ownership (TCO) of a system. Third, ML-based models trained using a limited number of samples are prone to overfitting. To overcome these limitations, we propose LEAPER, a transfer learning-based approach for prediction of performance and resource usage in FPGA-based systems. The key idea of LEAPER is to transfer an ML-based performance and resource usage model trained for a low-end edge environment to a new, high-end cloud environment to provide fast and accurate predictions for accelerator implementation. Experimental results show that LEAPER (1) provides, on average across six workloads and five FPGAs, 85% accuracy when we use our transferred model for prediction in a cloud environment with 5-shot learning and (2) reduces design-space exploration time for accelerator implementation on an FPGA by 10x, from days to only a few hours.
Embracing Graph Neural Networks for Hardware Security (Invited Paper)
Paper ↗
Abstract
Graph neural networks (GNNs) have attracted increasing attention due to their superior performance in deep learning on graph-structured data. GNNs have succeeded across various domains such as social networks, chemistry, and electronic design automation (EDA). Electronic circuits have a long history of being represented as graphs, and to no surprise, GNNs have demonstrated state-of-the-art performance in solving various EDA tasks. More importantly, GNNs are now employed to address several hardware security problems, such as detecting intellectual property (IP) piracy and hardware Trojans (HTs), to name a few. In this survey, we first provide a comprehensive overview of the usage of GNNs in hardware security and propose the first taxonomy to divide the state-of-the-art GNN-based hardware security systems into four categories: (i) HT detection systems, (ii) IP piracy detection systems, (iii) reverse engineering platforms, and (iv) attacks on logic locking. We summarize the different architectures, graph types, node features, benchmark data sets, and model evaluation of the employed GNNs. Finally, we elaborate on the lessons learned and discuss future directions.
CircuitNet: An Open-Source Dataset for Machine Learning Applications in Electronic Design Automation (EDA)
Paper ↗
Abstract
The electronic design automation (EDA) community has been actively exploring machine learning (ML) for very large-scale integrated computer-aided design (VLSI CAD). Many studies explored learning-based techniques for cross-stage prediction tasks in the design flow to achieve faster design convergence. Although building ML models usually requires a large amount of data, most studies can only generate small internal datasets for validation because of the lack of large public datasets. In this essay, we present the first open-source dataset called CircuitNet for ML tasks in VLSI CAD.
Deep Reinforcement Learning for System-on-Chip: Myths and Realities
Paper ↗
Abstract
Neural schedulers based on deep reinforcement learning (DRL) have shown considerable potential for solving real-world resource allocation problems, as they have demonstrated significant performance gain in the domain of cluster computing. In this paper, we investigate the feasibility of neural schedulers for the domain of System-on-Chip (SoC) resource allocation through extensive experiments and comparison with non-neural, heuristic schedulers. The key finding is three-fold. First, neural schedulers designed for cluster computing domain do not work well for SoC due to i) heterogeneity of SoC computing resources and ii) variable action set caused by randomness in incoming jobs. Second, our novel neural scheduler technique, Eclectic Interaction Matching (EIM), overcomes the above challenges, thus significantly improving the existing neural schedulers. Specifically, we rationalize the underlying reasons behind the performance gain by the EIM-based neural scheduler. Third, we discover that the ratio of the average processing elements (PE) switching delay and the average PE computation time significantly impacts the performance of neural SoC schedulers even with EIM. Consequently, future neural SoC scheduler design must consider this metric as well as its implementation overhead for practical utility.
EVHA: Explainable Vision System for Hardware Testing and Assurance -- An Overview
Paper ↗
Abstract
Due to the ever-growing demands for electronic chips in different sectors the semiconductor companies have been mandated to offshore their manufacturing processes. This unwanted matter has made security and trustworthiness of their fabricated chips concerning and caused creation of hardware attacks. In this condition, different entities in the semiconductor supply chain can act maliciously and execute an attack on the design computing layers, from devices to systems. Our attack is a hardware Trojan that is inserted during mask generation/fabrication in an untrusted foundry. The Trojan leaves a footprint in the fabricated through addition, deletion, or change of design cells. In order to tackle this problem, we propose Explainable Vision System for Hardware Testing and Assurance (EVHA) in this work that can detect the smallest possible change to a design in a low-cost, accurate, and fast manner. The inputs to this system are Scanning Electron Microscopy (SEM) images acquired from the Integrated Circuits (ICs) under examination. The system output is determination of IC status in terms of having any defect and/or hardware Trojan through addition, deletion, or change in the design cells at the cell-level. This article provides an overview on the design, development, implementation, and analysis of our defense system.
Bayesian Optimization for Macro Placement
Paper ↗
Abstract
Macro placement is the problem of placing memory blocks on a chip canvas. It can be formulated as a combinatorial optimization problem over sequence pairs, a representation which describes the relative positions of macros. Solving this problem is particularly challenging since the objective function is expensive to evaluate. In this paper, we develop a novel approach to macro placement using Bayesian optimization (BO) over sequence pairs. BO is a machine learning technique that uses a probabilistic surrogate model and an acquisition function that balances exploration and exploitation to efficiently optimize a black-box objective function. BO is more sample-efficient than reinforcement learning and therefore can be used with more realistic objectives. Additionally, the ability to learn from data and adapt the algorithm to the objective function makes BO an appealing alternative to other black-box optimization methods such as simulated annealing, which relies on problem-dependent heuristics and parameter-tuning. We benchmark our algorithm on the fixed-outline macro placement problem with the half-perimeter wire length objective and demonstrate competitive performance.
RobustAnalog: Fast Variation-Aware Analog Circuit Design Via Multi-task RL
Paper ↗
Abstract
Analog/mixed-signal circuit design is one of the most complex and time-consuming stages in the whole chip design process. Due to various process, voltage, and temperature (PVT) variations from chip manufacturing, analog circuits inevitably suffer from performance degradation. Although there has been plenty of work on automating analog circuit design under the typical condition, limited research has been done on exploring robust designs under real and unpredictable silicon variations. Automatic analog design against variations requires prohibitive computation and time costs. To address the challenge, we present RobustAnalog, a robust circuit design framework that involves the variation information in the optimization process. Specifically, circuit optimizations under different variations are considered as a set of tasks. Similarities among tasks are leveraged and competitions are alleviated to realize a sample-efficient multi-task training. Moreover, RobustAnalog prunes the task space according to the current performance in each iteration, leading to a further simulation cost reduction. In this way, RobustAnalog can rapidly produce a set of circuit parameters that satisfies diverse constraints (e.g. gain, bandwidth, noise...) across variations. We compare RobustAnalog with Bayesian optimization, Evolutionary algorithm, and Deep Deterministic Policy Gradient (DDPG) and demonstrate that RobustAnalog can significantly reduce required optimization time by 14-30 times. Therefore, our study provides a feasible method to handle various real silicon conditions.
Chimera: A Hybrid Machine Learning Driven Multi-Objective Design Space Exploration Tool for FPGA High-Level Synthesis
Paper ↗
Abstract
In recent years, hardware accelerators based on field-programmable gate arrays (FPGAs) have been widely adopted, thanks to FPGAs' extraordinary flexibility. However, with the high flexibility comes the difficulty in design and optimization. Conventionally, these accelerators are designed with low-level hardware descriptive languages, which means creating large designs with complex behavior is extremely difficult. Therefore, high-level synthesis (HLS) tools were created to simplify hardware designs for FPGAs. They enable the user to create hardware designs using high-level languages and provide various optimization directives to help to improve the performance of the synthesized hardware. However, applying these optimizations to achieve high performance is time-consuming and usually requires expert knowledge. To address this difficulty, we present an automated design space exploration tool for applying HLS optimization directives, called Chimera, which significantly reduces the human effort and expertise needed for creating high-performance HLS designs. It utilizes a novel multi-objective exploration method that seamlessly integrates active learning, evolutionary algorithm, and Thompson sampling, making it capable of finding a set of optimized designs on a Pareto curve with only a small number of design points evaluated during the exploration. In the experiments, in less than 24 hours, this hybrid method explored design points that have the same or superior performance compared to highly optimized hand-tuned designs created by expert HLS users from the Rosetta benchmark suite. In addition to discovering the extreme points, it also explores a Pareto frontier, where the elbow point can potentially save up to 26\% of Flip-Flop resource with negligibly higher latency.
A Deep-Learning-Aided Pipeline for Efficient Post-Silicon Tuning
Paper ↗
Abstract
In post-silicon validation, tuning is to find the values for the tuning knobs, potentially as a function of process parameters and/or known operating conditions. In this sense, an more efficient tuning requires identifying the most critical tuning knobs and process parameters in terms of a given figure-of-merit for a Device Under Test (DUT). This is often manually conducted by experienced experts. However, with increasingly complex chips, manual inspection on a large amount of raw variables has become more challenging. In this work, we leverage neural networks to efficiently select the most relevant variables and present a corresponding deep-learning-aided pipeline for efficient tuning.
Homunculus: Auto-Generating Efficient Data-Plane ML Pipelines for Datacenter Networks
Paper ↗
Abstract
Support for Machine Learning (ML) applications in networks has significantly improved over the last decade. The availability of public datasets and programmable switching fabrics (including low-level languages to program them) present a full-stack to the programmer for deploying in-network ML. However, the diversity of tools involved, coupled with complex optimization tasks of ML model design and hyperparameter tuning while complying with the network constraints (like throughput and latency), put the onus on the network operator to be an expert in ML, network design, and programmable hardware. This multi-faceted nature of in-network tools and expertise in ML and hardware is a roadblock for ML to become mainstream in networks, today. We present Homunculus, a high-level framework that enables network operators to specify their ML requirements in a declarative, rather than imperative way. Homunculus takes as input, the training data and accompanying network constraints, and automatically generates and installs a suitable model onto the underlying switching hardware. It performs model design-space exploration, training, and platform code-generation as compiler stages, leaving network operators to focus on acquiring high-quality network data. Our evaluations on real-world ML applications show that Homunculus's generated models achieve up to 12% better F1 score compared to hand-tuned alternatives, while requiring only 30 lines of single-script code on average. We further demonstrate the performance of the generated models on emerging per-packet ML platforms to showcase its timely and practical significance.
Intelligent Circuit Design and Implementation with Machine Learning
Paper ↗
Abstract
The stagnation of EDA technologies roots from insufficient knowledge reuse. In practice, very similar simulation or optimization results may need to be repeatedly constructed from scratch. This motivates my research on introducing more 'intelligence' to EDA with machine learning (ML), which explores complex correlations in design flows based on prior data. Besides design time, I also propose ML solutions to boost IC performance by assisting the circuit management at runtime. In this dissertation, I present multiple fast yet accurate ML models covering a wide range of chip design stages from the register-transfer level (RTL) to sign-off, solving primary chip-design problems about power, timing, interconnect, IR drop, routability, and design flow tuning. Targeting the RTL stage, I present APOLLO, a fully automated power modeling framework. It constructs an accurate per-cycle power model by extracting the most power-correlated signals. The model can be further implemented on chip for runtime power management with unprecedented low hardware costs. Targeting gate-level netlist, I present Net2 for early estimations on post-placement wirelength. It further enables more accurate timing analysis without actual physical design information. Targeting circuit layout, I present RouteNet for early routability prediction. As the first deep learning-based routability estimator, some feature-extraction and model-design principles proposed in it are widely adopted by later works. I also present PowerNet for fast IR drop estimation. It captures spatial and temporal information about power distribution with a customized CNN architecture. Last, besides targeting a single design step, I present FIST to efficiently tune design flow parameters during both logic synthesis and physical design.
Multi-agent Databases via Independent Learning
Paper ↗
Abstract
Machine learning is rapidly being used in database research to improve the effectiveness of numerous tasks included but not limited to query optimization, workload scheduling, physical design, etc. Currently, the research focus has been on replacing a single database component responsible for one task by its learning-based counterpart. However, query performance is not simply determined by the performance of a single component, but by the cooperation of multiple ones. As such, learning based database components need to collaborate during both training and execution in order to develop policies that meet end performance goals. Thus, the paper attempts to address the question "Is it possible to design a database consisting of various learned components that cooperatively work to improve end-to-end query latency?". To answer this question, we introduce MADB (Multi-Agent DB), a proof-of-concept system that incorporates a learned query scheduler and a learned query optimizer. MADB leverages a cooperative multi-agent reinforcement learning approach that allows the two components to exchange the context of their decisions with each other and collaboratively work towards reducing the query latency. Preliminary results demonstrate that MADB can outperform the non-cooperative integration of learned components.
DeepSAT: An EDA-Driven Learning Framework for SAT
Paper ↗
Abstract
We present DeepSAT, a novel end-to-end learning framework for the Boolean satisfiability (SAT) problem. Unlike existing solutions trained on random SAT instances with relatively weak supervision, we propose applying the knowledge of the well-developed electronic design automation (EDA) field for SAT solving. Specifically, we first resort to logic synthesis algorithms to pre-process SAT instances into optimized and-inverter graphs (AIGs). By doing so, the distribution diversity among various SAT instances can be dramatically reduced, which facilitates improving the generalization capability of the learned model. Next, we regard the distribution of SAT solutions being a product of conditional Bernoulli distributions. Based on this observation, we approximate the SAT solving procedure with a conditional generative model, leveraging a novel directed acyclic graph neural network (DAGNN) with two polarity prototypes for conditional SAT modeling. To effectively train the generative model, with the help of logic simulation tools, we obtain the probabilities of nodes in the AIG being logic `1' as rich supervision. We conduct comprehensive experiments on various SAT problems. Our results show that, DeepSAT achieves significant accuracy improvements over state-of-the-art learning-based SAT solutions, especially when generalized to SAT instances that are relatively large or with diverse distributions.
DevFormer: A Symmetric Transformer for Context-Aware Device Placement
Paper ↗
Abstract
In this paper, we present DevFormer, a novel transformer-based architecture for addressing the complex and computationally demanding problem of hardware design optimization. Despite the demonstrated efficacy of transformers in domains including natural language processing and computer vision, their use in hardware design has been limited by the scarcity of offline data. Our approach addresses this limitation by introducing strong inductive biases such as relative positional embeddings and action-permutation symmetricity that effectively capture the hardware context and enable efficient design optimization with limited offline data. We apply DevFoemer to the problem of decoupling capacitor placement and show that it outperforms state-of-the-art methods in both simulated and real hardware, leading to improved performances while reducing the number of components by more than $30\%$. Finally, we show that our approach achieves promising results in other offline contextual learning-based combinatorial optimization tasks.
RACE: A Reinforcement Learning Framework for Improved Adaptive Control of NoC Channel Buffers
Paper ↗
Abstract
Network-on-chip (NoC) architectures rely on buffers to store flits to cope with contention for router resources during packet switching. Recently, reversible multi-function channel (RMC) buffers have been proposed to simultaneously reduce power and enable adaptive NoC buffering between adjacent routers. While adaptive buffering can improve NoC performance by maximizing buffer utilization, controlling the RMC buffer allocations requires a congestion-aware, scalable, and proactive policy. In this work, we present RACE, a novel reinforcement learning (RL) framework that utilizes better awareness of network congestion and a new reward metric ("falsefulls") to help guide the RL agent towards better RMC buffer control decisions. We show that RACE reduces NoC latency by up to 48.9%, and energy consumption by up to 47.1% against state-of-the-art NoC buffer control policies.
Predicting Post-Route Quality of Results Estimates for HLS Designs using Machine Learning
Paper ↗
Abstract
Machine learning (ML) has been widely used to improve the predictability of EDA tools. The use of CAD tools that express designs at higher levels of abstraction makes machine learning even more important to highlight the performance of various design steps. Behavioral descriptions used during the high-level synthesis (HLS) are completely technology independent making it hard for designers to interpret how changes in the synthesis options affect the resultant circuit. FPGA design flows are completely embracing HLS based methodologies so that software engineers with almost no hardware design skills can easily use their tools. HLS tools allow design space exploration by modifying synthesis options, however, they lack accuracy in the Quality of Results (QoR) reported right after HLS. This lack of correctness results in sub-optimal designs with problems in timing closure. This paper presents a robust ML based design flow that can accurately predict post-route QoR for a given behavioral description without the need to synthesize the design. The model is an important design exploration tool where a designer can quickly view the impact on overall design quality when local and global optimization directives are changed. The proposed methodology presents two strong advantages: (i) Accurate prediction of the design quality (QoR), and (ii) complete elimination of the need to execute high-level synthesis for each design option. We predict three post route parameters, (i). Area, (ii). Latency and (iii). Clock Period of a design just by analyzing the high level behavioral code and some intermediate representation codes. We have integrated the methodology with Xilinx HLS tools and have demonstrated accurate estimation on a variety of FPGA families. Our estimated results are within 10\% of actual computed values
Digital Twin for Secure Semiconductor Lifecycle Management: Prospects and Applications
Paper ↗
Abstract
The expansive globalization of the semiconductor supply chain has introduced numerous untrusted entities into different stages of a device's lifecycle. To make matters worse, the increase complexity in the design as well as aggressive time to market requirements of the newer generation of integrated circuits can lead either designers to unintentionally introduce security vulnerabilities or verification engineers to fail in detecting them earlier in the design lifecycle. These overlooked or undetected vulnerabilities can be exploited by malicious entities in subsequent stages of the lifecycle through an ever widening variety of hardware attacks. The ability to ascertain the provenance of these vulnerabilities, therefore, becomes a pressing issue when the security assurance across the whole lifecycle is required to be ensured. We posit that if there is a malicious or unintentional breach of security policies of a device, it will be reflected in the form of anomalies in the traditional design, verification and testing activities throughout the lifecycle. With that, a digital simulacrum of a device's lifecycle, called a digital twin (DT), can be formed by the data gathered from different stages to secure the lifecycle of the device. In this paper, we put forward a realization of intertwined relationships of security vulnerabilities with data available from the silicon lifecycle and formulate different components of an AI driven DT framework. The proposed DT framework leverages these relationships and relational learning to achieve Forward and Backward Trust Analysis functionalities enabling security aware management of the entire lifecycle. Finally, we provide potential future research avenues and challenges for realization of the digital twin framework to enable secure semiconductor lifecycle management.
Demo: low-power communications based on RIS and AI for 6G
Paper ↗
Abstract
Ultra-massive multiple-input-multiple-output (UM-MIMO) is promising to meet the high rate requirements for future 6G. However, due to the large number of antennas and high path loss, the hardware power consumption and computing power consumption of UM-MIMO will be unaffordable. To address this problem, we implement a low-power communication system based on reconfigurable intelligent surface (RIS) and artificial intelligence (AI) for 6G. For hardware design, we employ a 256-element RIS at the base station to replace the traditional phased array. Moreover, a 2304-element RIS is developed as a relay to assist communication with much reduced transmit power. For software implementation, we develop an AI-based transmission design to reduce computing power consumption. By jointly designing the hardware and software, this prototype can realize real-time 4K video transmission with much reduced power consumption.
Routing and Placement of Macros using Deep Reinforcement Learning
Paper ↗
Abstract
Chip placement has been one of the most time consuming task in any semi conductor area, Due to this negligence, many projects are pushed and chips availability in real markets get delayed. An engineer placing macros on a chip also needs to place it optimally to reduce the three important factors like power, performance and time. Looking at these prior problems we wanted to introduce a new method using Reinforcement Learning where we train the model to place the nodes of a chip netlist onto a chip canvas. We want to build a neural architecture that will accurately reward the agent across a wide variety of input netlist correctly.
Supervised Learning for Coverage-Directed Test Selection in Simulation-Based Verification
Paper ↗
Abstract
Constrained random test generation is one of the most widely adopted methods for generating stimuli for simulation-based verification. Randomness leads to test diversity, but tests tend to repeatedly exercise the same design logic. Constraints are written (typically manually) to bias random tests towards interesting, hard-to-reach, and yet-untested logic. However, as verification progresses, most constrained random tests yield little to no effect on functional coverage. If stimuli generation consumes significantly less resources than simulation, then a better approach involves randomly generating a large number of tests, selecting the most effective subset, and only simulating that subset. In this paper, we introduce a novel method for automatic constraint extraction and test selection. This method, which we call coverage-directed test selection, is based on supervised learning from coverage feedback. Our method biases selection towards tests that have a high probability of increasing functional coverage, and prioritises them for simulation. We show how coverage-directed test selection can reduce manual constraint writing, prioritise effective tests, reduce verification resource consumption, and accelerate coverage closure on a large, real-life industrial hardware design.
POViT: Vision Transformer for Multi-objective Design and Characterization of Nanophotonic Devices
Paper ↗
Abstract
We solve a fundamental challenge in semiconductor IC design: the fast and accurate characterization of nanoscale photonic devices. Much like the fusion between AI and EDA, many efforts have been made to apply DNNs such as convolutional neural networks (CNN) to prototype and characterize next-gen optoelectronic devices commonly found in photonic integrated circuits (PIC) and LiDAR. These prior works generally strive to predict the quality factor (Q) and modal volume (V) of for instance, photonic crystals, with ultra-high accuracy and speed. However, state-of-the-art models are still far from being directly applicable in the real-world: e.g. the correlation coefficient of V ($V_{coeff}$ ) is only about 80%, which is much lower than what it takes to generate reliable and reproducible nanophotonic designs. Recently, attention-based transformer models have attracted extensive interests and been widely used in CV and NLP. In this work, we propose the first-ever Transformer model (POViT) to efficiently design and simulate semiconductor photonic devices with multiple objectives. Unlike the standard Vision Transformer (ViT), we supplied photonic crystals as data input and changed the activation layer from GELU to an absolute-value function (ABS). Our experiments show that POViT exceeds results reported by previous models significantly. The correlation coefficient $V_{coeff}$ increases by over 12% (i.e., to 92.0%) and the prediction errors of Q is reduced by an order of magnitude, among several other key metric improvements. Our work has the potential to drive the expansion of EDA to fully automated photonic design. The complete dataset and code will be released to aid researchers endeavoring in the interdisciplinary field of physics and computer science.
PrefixRL: Optimization of Parallel Prefix Circuits using Deep Reinforcement Learning
Paper ↗
Abstract
In this work, we present a reinforcement learning (RL) based approach to designing parallel prefix circuits such as adders or priority encoders that are fundamental to high-performance digital design. Unlike prior methods, our approach designs solutions tabula rasa purely through learning with synthesis in the loop. We design a grid-based state-action representation and an RL environment for constructing legal prefix circuits. Deep Convolutional RL agents trained on this environment produce prefix adder circuits that Pareto-dominate existing baselines with up to 16.0% and 30.2% lower area for the same delay in the 32b and 64b settings respectively. We observe that agents trained with open-source synthesis tools and cell library can design adder circuits that achieve lower area and delay than commercial tool adders in an industrial cell library.
Hardware Trojan Detection Using Unsupervised Deep Learning on Quantum Diamond Microscope Magnetic Field Images
Paper ↗
Abstract
This paper presents a method for hardware trojan detection in integrated circuits. Unsupervised deep learning is used to classify wide field-of-view (4x4 mm$^2$), high spatial resolution magnetic field images taken using a Quantum Diamond Microscope (QDM). QDM magnetic imaging is enhanced using quantum control techniques and improved diamond material to increase magnetic field sensitivity by a factor of 4 and measurement speed by a factor of 16 over previous demonstrations. These upgrades facilitate the first demonstration of QDM magnetic field measurement for hardware trojan detection. Unsupervised convolutional neural networks and clustering are used to infer trojan presence from unlabeled data sets of 600x600 pixel magnetic field images without human bias. This analysis is shown to be more accurate than principal component analysis for distinguishing between field programmable gate arrays configured with trojan free and trojan inserted logic. This framework is tested on a set of scalable trojans that we developed and measured with the QDM. Scalable and TrustHub trojans are detectable down to a minimum trojan trigger size of 0.5% of the total logic. The trojan detection framework can be used for golden-chip free detection, since knowledge of the chips' identities is only used to evaluate detection accuracy
Domain Knowledge-Infused Deep Learning for Automated Analog/Radio-Frequency Circuit Parameter Optimization
Paper ↗
Abstract
The design automation of analog circuits is a longstanding challenge. This paper presents a reinforcement learning method enhanced by graph learning to automate the analog circuit parameter optimization at the pre-layout stage, i.e., finding device parameters to fulfill desired circuit specifications. Unlike all prior methods, our approach is inspired by human experts who rely on domain knowledge of analog circuit design (e.g., circuit topology and couplings between circuit specifications) to tackle the problem. By originally incorporating such key domain knowledge into policy training with a multimodal network, the method best learns the complex relations between circuit parameters and design targets, enabling optimal decisions in the optimization process. Experimental results on exemplary circuits show it achieves human-level design accuracy (99%) 1.5X efficiency of existing best-performing methods. Our method also shows better generalization ability to unseen specifications and optimality in circuit performance optimization. Moreover, it applies to design radio-frequency circuits on emerging semiconductor technologies, breaking the limitations of prior learning methods in designing conventional analog circuits.
Worst-Case Dynamic Power Distribution Network Noise Prediction Using Convolutional Neural Network
Paper ↗
Abstract
Worst-case dynamic PDN noise analysis is an essential step in PDN sign-off to ensure the performance and reliability of chips. However, with the growing PDN size and increasing scenarios to be validated, it becomes very time- and resource-consuming to conduct full-stack PDN simulation to check the worst-case noise for different test vectors. Recently, various works have proposed machine learning based methods for supply noise prediction, many of which still suffer from large training overhead, inefficiency, or non-scalability. Thus, this paper proposed an efficient and scalable framework for the worst-case dynamic PDN noise prediction. The framework first reduces the spatial and temporal redundancy in the PDN and input current vector, and then employs efficient feature extraction as well as a novel convolutional neural network architecture to predict the worst-case dynamic PDN noise. Experimental results show that the proposed framework consistently outperforms the commercial tool and the state-of-the-art machine learning method with only 0.63-1.02% mean relative error and 25-69$\times$ speedup.
Hardware Trojan Detection using Graph Neural Networks
Paper ↗
Abstract
The globalization of the Integrated Circuit (IC) supply chain has moved most of the design, fabrication, and testing process from a single trusted entity to various untrusted third-party entities around the world. The risk of using untrusted third-Party Intellectual Property (3PIP) is the possibility for adversaries to insert malicious modifications known as Hardware Trojans (HTs). These HTs can compromise the integrity, deteriorate the performance, and deny the functionality of the intended design. Various HT detection methods have been proposed in the literature; however, many fall short due to their reliance on a golden reference circuit, a limited detection scope, the need for manual code review, or the inability to scale with large modern designs. We propose a novel golden reference-free HT detection method for both Register Transfer Level (RTL) and gate-level netlists by leveraging Graph Neural Networks (GNNs) to learn the behavior of the circuit through a Data Flow Graph (DFG) representation of the hardware design. We evaluate our model on a custom dataset by expanding the Trusthub HT benchmarks \cite{trusthub1}. The results demonstrate that our approach detects unknown HTs with 97% recall (true positive rate) very fast in 21.1ms for RTL and 84% recall in 13.42s for Gate-Level Netlist.
A Survey and Perspective on Artificial Intelligence for Security-Aware Electronic Design Automation
Paper ↗
Abstract
Artificial intelligence (AI) and machine learning (ML) techniques have been increasingly used in several fields to improve performance and the level of automation. In recent years, this use has exponentially increased due to the advancement of high-performance computing and the ever increasing size of data. One of such fields is that of hardware design; specifically the design of digital and analog integrated circuits~(ICs), where AI/ ML techniques have been extensively used to address ever-increasing design complexity, aggressive time-to-market, and the growing number of ubiquitous interconnected devices (IoT). However, the security concerns and issues related to IC design have been highly overlooked. In this paper, we summarize the state-of-the-art in AL/ML for circuit design/optimization, security and engineering challenges, research in security-aware CAD/EDA, and future research directions and needs for using AI/ML for security-aware circuit design.
Automatic Hardware Trojan Insertion using Machine Learning
Paper ↗
Abstract
Due to the current horizontal business model that promotes increasing reliance on untrusted third-party Intellectual Properties (IPs), CAD tools, and design facilities, hardware Trojan attacks have become a serious threat to the semiconductor industry. Development of effective countermeasures against hardware Trojan attacks requires: (1) fast and reliable exploration of the viable Trojan attack space for a given design and (2) a suite of high-quality Trojan-inserted benchmarks that meet specific standards. The latter has become essential for the development and evaluation of design/verification solutions to achieve quantifiable assurance against Trojan attacks. While existing static benchmarks provide a baseline for comparing different countermeasures, they only enumerate a limited number of handcrafted Trojans from the complete Trojan design space. To accomplish these dual objectives, in this paper, we present MIMIC, a novel AI-guided framework for automatic Trojan insertion, which can create a large population of valid Trojans for a given design by mimicking the properties of a small set of known Trojans. While there exist tools to automatically insert Trojan instances using fixed Trojan templates, they cannot analyze known Trojan attacks for creating new instances that accurately capture the threat model. MIMIC works in two major steps: (1) it analyzes structural and functional features of existing Trojan populations in a multi-dimensional space to train machine learning models and generate a large number of "virtual Trojans" of the given design, (2) next, it binds them into the design by matching their functional/structural properties with suitable nets of the internal logic structure. We have developed a complete tool flow for MIMIC, extensively evaluated the framework by exploring several use-cases, and quantified its effectiveness to demonstrate highly promising results.
DRAGON (Differentiable Graph Execution) : A suite of Hardware Simulation and Optimization tools for Modern AI/Non-AI Workloads
Paper ↗
Abstract
We introduce DRAGON, a fast and explainable hardware simulation and optimization toolchain that enables hardware architects to simulate hardware designs, and to optimize hardware designs to efficiently execute workloads. The DRAGON toolchain provides the following tools: Hardware Model Generator (DGen), Hardware Simulator (DSim) and Hardware Optimizer (DOpt). DSim provides the simulation of running algorithms (represented as data-flow graphs) on hardware described. DGen describes the hardware in detail, with user input architectures/technology (represented in a custom description language). A novel methodology of gradient descent from the simulation allows us optimize the hardware model (giving the directions for improvements in technology parameters and design parameters), provided by Dopt. DRAGON framework (DSim) is much faster than previously avaible works for simulation, which is possible through performance-first code writing practices, mathematical formulas for common computing operations to avoid cycle-accurate simulation steps, efficient algorithms for mapping, and data-structure representations for hardware state. DRAGON framework (Dopt) generates performance optimized architectures for both AI and Non-AI Workloads, and provides technology improvement directions for 100x-1000x better future computing systems.
Flexible Multiple-Objective Reinforcement Learning for Chip Placement
Paper ↗
Abstract
Recently, successful applications of reinforcement learning to chip placement have emerged. Pretrained models are necessary to improve efficiency and effectiveness. Currently, the weights of objective metrics (e.g., wirelength, congestion, and timing) are fixed during pretraining. However, fixed-weighed models cannot generate the diversity of placements required for engineers to accommodate changing requirements as they arise. This paper proposes flexible multiple-objective reinforcement learning (MORL) to support objective functions with inference-time variable weights using just a single pretrained model. Our macro placement results show that MORL can generate the Pareto frontier of multiple objectives effectively.
AdaTest:Reinforcement Learning and Adaptive Sampling for On-chip Hardware Trojan Detection
Paper ↗
Abstract
This paper proposes AdaTest, a novel adaptive test pattern generation framework for efficient and reliable Hardware Trojan (HT) detection. HT is a backdoor attack that tampers with the design of victim integrated circuits (ICs). AdaTest improves the existing HT detection techniques in terms of scalability and accuracy of detecting smaller Trojans in the presence of noise and variations. To achieve high trigger coverage, AdaTest leverages Reinforcement Learning (RL) to produce a diverse set of test inputs. Particularly, we progressively generate test vectors with high reward values in an iterative manner. In each iteration, the test set is evaluated and adaptively expanded as needed. Furthermore, AdaTest integrates adaptive sampling to prioritize test samples that provide more information for HT detection, thus reducing the number of samples while improving the sample quality for faster exploration. We develop AdaTest with a Software/Hardware co-design principle and provide an optimized on-chip architecture solution. AdaTest's architecture minimizes the hardware overhead in two ways:(i) Deploying circuit emulation on programmable hardware to accelerate reward evaluation of the test input; (ii) Pipelining each computation stage in AdaTest by automatically constructing auxiliary circuit for test input generation, reward evaluation, and adaptive sampling. We evaluate AdaTest's performance on various HT benchmarks and compare it with two prior works that use logic testing for HT detection. Experimental results show that AdaTest engenders up to two orders of test generation speedup and two orders of test set size reduction compared to the prior works while achieving the same level or higher Trojan detection rate.
Uncertainty-Aware Search Framework for Multi-Objective Bayesian Optimization
Paper ↗
Abstract
We consider the problem of multi-objective (MO) blackbox optimization using expensive function evaluations, where the goal is to approximate the true Pareto set of solutions while minimizing the number of function evaluations. For example, in hardware design optimization, we need to find the designs that trade-off performance, energy, and area overhead using expensive simulations. We propose a novel uncertainty-aware search framework referred to as USeMO to efficiently select the sequence of inputs for evaluation to solve this problem. The selection method of USeMO consists of solving a cheap MO optimization problem via surrogate models of the true functions to identify the most promising candidates and picking the best candidate based on a measure of uncertainty. We also provide theoretical analysis to characterize the efficacy of our approach. Our experiments on several synthetic and six diverse real-world benchmark problems show that USeMO consistently outperforms the state-of-the-art algorithms.
Design and Experimental Verification of a Novel Error-Backpropagation-Based Background Calibration for Time Interleaved ADC in Digital Communication Receivers
Paper ↗
Abstract
A novel background calibration technique for Time-Interleaved Analog-to-Digital Converters (TI-ADCs) is presented in this paper. This technique is applicable to equalized digital communication receivers. As shown by Tsai et al. [1] and Luna et al. [2], in a digital receiver it is possible to treat the TI-ADC errors as part of the communication channel and take advantage of the adaptive equalizer to compensate them. Therefore calibration becomes an integral part of the channel equalization. No special purpose analog or digital calibration blocks or algorithms are required. However, there is a large class of receivers where the equalization technique cannot be directly applied because other signal processing blocks are located between the TI-ADC and the equalizer. The technique presented here generalizes earlier works to this class of receivers. The error backpropagation algorithm, traditionally used in machine learning, is applied to the error computed at the receiver slicer and used to adapt an auxiliary equalizer adjacent to the TI-ADC, called the Compensation Equalizer (CE). Simulations using a dual polarization optical coherent receiver model demonstrate accurate and robust mismatch compensation across different application scenarios. Several Quadrature Amplitude Modulation (QAM) schemes are tested in simulations and experimentally. Measurements on an emulation platform which includes an 8 bit, 4 GS/s TI-ADC prototype chip fabricated in 130nm CMOS technology, show an almost ideal mitigation of the impact of the mismatches on the receiver performance when 64-QAM and 256-QAM schemes are tested. An absolute improvement in the TI-ADC performance of $\sim$15 dB in both SNDR and SFDR is measured.
Towards Collaborative Intelligence: Routability Estimation based on Decentralized Private Data
Paper ↗
Abstract
Applying machine learning (ML) in design flow is a popular trend in EDA with various applications from design quality predictions to optimizations. Despite its promise, which has been demonstrated in both academic researches and industrial tools, its effectiveness largely hinges on the availability of a large amount of high-quality training data. In reality, EDA developers have very limited access to the latest design data, which is owned by design companies and mostly confidential. Although one can commission ML model training to a design company, the data of a single company might be still inadequate or biased, especially for small companies. Such data availability problem is becoming the limiting constraint on future growth of ML for chip design. In this work, we propose an Federated-Learning based approach for well-studied ML applications in EDA. Our approach allows an ML model to be collaboratively trained with data from multiple clients but without explicit access to the data for respecting their data privacy. To further strengthen the results, we co-design a customized ML model FLNet and its personalization under the decentralized training scenario. Experiments on a comprehensive dataset show that collaborative training improves accuracy by 11% compared with individual local models, and our customized model FLNet significantly outperforms the best of previous routability estimators in this collaborative training flow.
The Dark Side: Security Concerns in Machine Learning for EDA
Paper ↗
Abstract
The growing IC complexity has led to a compelling need for design efficiency improvement through new electronic design automation (EDA) methodologies. In recent years, many unprecedented efficient EDA methods have been enabled by machine learning (ML) techniques. While ML demonstrates its great potential in circuit design, however, the dark side about security problems, is seldomly discussed. This paper gives a comprehensive and impartial summary of all security concerns we have observed in ML for EDA. Many of them are hidden or neglected by practitioners in this field. In this paper, we first provide our taxonomy to define four major types of security concerns, then we analyze different application scenarios and special properties in ML for EDA. After that, we present our detailed analysis of each security concern with experiments.
Generic Lithography Modeling with Dual-band Optics-Inspired Neural Networks
Paper ↗
Abstract
Lithography simulation is a critical step in VLSI design and optimization for manufacturability. Existing solutions for highly accurate lithography simulation with rigorous models are computationally expensive and slow, even when equipped with various approximation techniques. Recently, machine learning has provided alternative solutions for lithography simulation tasks such as coarse-grained edge placement error regression and complete contour prediction. However, the impact of these learning-based methods has been limited due to restrictive usage scenarios or low simulation accuracy. To tackle these concerns, we introduce an dual-band optics-inspired neural network design that considers the optical physics underlying lithography. To the best of our knowledge, our approach yields the first published via/metal layer contour simulation at 1nm^2/pixel resolution with any tile size. Compared to previous machine learning based solutions, we demonstrate that our framework can be trained much faster and offers a significant improvement on efficiency and image quality with 20X smaller model size. We also achieve 85X simulation speedup over traditional lithography simulator with 1% accuracy loss.
Designing ML-Resilient Locking at Register-Transfer Level
Paper ↗
Abstract
Various logic-locking schemes have been proposed to protect hardware from intellectual property piracy and malicious design modifications. Since traditional locking techniques are applied on the gate-level netlist after logic synthesis, they have no semantic knowledge of the design function. Data-driven, machine-learning (ML) attacks can uncover the design flaws within gate-level locking. Recent proposals on register-transfer level (RTL) locking have access to semantic hardware information. We investigate the resilience of ASSURE, a state-of-the-art RTL locking method, against ML attacks. We used the lessons learned to derive two ML-resilient RTL locking schemes built to reinforce ASSURE locking. We developed ML-driven security metrics to evaluate the schemes against an RTL adaptation of the state-of-the-art, ML-based SnapShot attack.
Deep Bidirectional Transformers for SoC Flow Specification Mining
Paper ↗
Abstract
High-quality system-level message flow specifications can lead to comprehensive validation of system-on-chip (SoC) designs. We propose a disruptive method that utilizes an attention mechanism to produce accurate flow specifications from SoC IP communication traces. The proposed method can overcome the inherent complexity of SoC traces induced by the concurrency and parallelism of multicore designs that existing flow specification mining tools often find extremely challenging. Experiments on highly interleaved traces show promising flow reconstruction compared to several tools dedicated to the flow specification mining problem.
Contrastive Graph Convolutional Networks for Hardware Trojan Detection in Third Party IP Cores
Paper ↗
Abstract
The availability of wide-ranging third-party intellectual property (3PIP) cores enables integrated circuit (IC) designers to focus on designing high-level features in ASICs/SoCs. The massive proliferation of ICs brings with it an increased number of bad actors seeking to exploit those circuits for various nefarious reasons. This is not surprising as integrated circuits affect every aspect of society. Thus, malicious logic (Hardware Trojans, HT) being surreptitiously injected by untrusted vendors into 3PIP cores used in IC design is an ever present threat. In this paper, we explore methods for identification of trigger-based HT in designs containing synthesizable IP cores without a golden model. Specifically, we develop methods to detect hardware trojans by detecting triggers embedded in ICs purely based on netlists acquired from the vendor. We propose GATE-Net, a deep learning model based on graph-convolutional networks (GCN) trained using supervised contrastive learning, for flagging designs containing randomly-inserted triggers using only the corresponding netlist. Our proposed architecture achieves significant improvements over state-of-the-art learning models yielding an average 46.99% improvement in detection performance for combinatorial triggers and 21.91% improvement for sequential triggers across a variety of circuit types. Through rigorous experimentation, qualitative and quantitative performance evaluations, we demonstrate effectiveness of GATE-Net and the supervised contrastive training of GATE-Net for HT detection.
Towards Machine Learning for Placement and Routing in Chip Design: a Methodological Overview
Paper ↗
Abstract
Placement and routing are two indispensable and challenging (NP-hard) tasks in modern chip design flows. Compared with traditional solvers using heuristics or expert-well-designed algorithms, machine learning has shown promising prospects by its data-driven nature, which can be of less reliance on knowledge and priors, and potentially more scalable by its advanced computational paradigms (e.g. deep networks with GPU acceleration). This survey starts with the introduction of basics of placement and routing, with a brief description on classic learning-free solvers. Then we present detailed review on recent advance in machine learning for placement and routing. Finally we discuss the challenges and opportunities for future research.
Domain Knowledge-Based Automated Analog Circuit Design with Deep Reinforcement Learning
Paper ↗
Abstract
The design automation of analog circuits is a longstanding challenge in the integrated circuit field. This paper presents a deep reinforcement learning method to expedite the design of analog circuits at the pre-layout stage, where the goal is to find device parameters to fulfill desired circuit specifications. Our approach is inspired by experienced human designers who rely on domain knowledge of analog circuit design (e.g., circuit topology and couplings between circuit specifications) to tackle the problem. Unlike all prior methods, our method originally incorporates such key domain knowledge into policy learning with a graph-based policy network, thereby best modeling the relations between circuit parameters and design targets. Experimental results on exemplary circuits show it achieves human-level design accuracy (~99%) with 1.5x efficiency of existing best-performing methods. Our method also shows better generalization ability to unseen specifications and optimality in circuit performance optimization. Moreover, it applies to designing diverse analog circuits across different semiconductor technologies, breaking the limitations of prior ad-hoc methods in designing one particular type of analog circuits with conventional semiconductor technology.
AI/ML Algorithms and Applications in VLSI Design and Technology
Paper ↗
Abstract
An evident challenge ahead for the integrated circuit (IC) industry in the nanometer regime is the investigation and development of methods that can reduce the design complexity ensuing from growing process variations and curtail the turnaround time of chip manufacturing. Conventional methodologies employed for such tasks are largely manual; thus, time-consuming and resource-intensive. In contrast, the unique learning strategies of artificial intelligence (AI) provide numerous exciting automated approaches for handling complex and data-intensive tasks in very-large-scale integration (VLSI) design and testing. Employing AI and machine learning (ML) algorithms in VLSI design and manufacturing reduces the time and effort for understanding and processing the data within and across different abstraction levels via automated learning algorithms. It, in turn, improves the IC yield and reduces the manufacturing turnaround time. This paper thoroughly reviews the AI/ML automated approaches introduced in the past towards VLSI design and manufacturing. Moreover, we discuss the scope of AI/ML applications in the future at various abstraction levels to revolutionize the field of VLSI design, aiming for high-speed, highly intelligent, and efficient implementations.
Efficient Memory Partitioning in Software Defined Hardware
Paper ↗
Abstract
As programmers turn to software-defined hardware (SDH) to maintain a high level of productivity while programming hardware to run complex algorithms, heavy-lifting must be done by the compiler to automatically partition on-chip arrays. In this paper, we introduce an automatic memory partitioning system that can quickly compute more efficient partitioning schemes than prior systems. Our system employs a variety of resource-saving optimizations and an ML cost model to select the best partitioning scheme from an array of candidates. We compared our system against various state-of-the-art SDH compilers and FPGAs on a variety of benchmarks and found that our system generates solutions that, on average, consume 40.3% fewer logic resources, 78.3% fewer FFs, 54.9% fewer Block RAMs (BRAMs), and 100% fewer DSPs.
PowerGear: Early-Stage Power Estimation in FPGA HLS via Heterogeneous Edge-Centric GNNs
Paper ↗
Abstract
Power estimation is the basis of many hardware optimization strategies. However, it is still challenging to offer accurate power estimation at an early stage such as high-level synthesis (HLS). In this paper, we propose PowerGear, a graph-learning-assisted power estimation approach for FPGA HLS, which features high accuracy, efficiency and transferability. PowerGear comprises two main components: a graph construction flow and a customized graph neural network (GNN) model. Specifically, in the graph construction flow, we introduce buffer insertion, datapath merging, graph trimming and feature annotation techniques to transform HLS designs into graph-structured data, which encode both intra-operation micro-architectures and inter-operation interconnects annotated with switching activities. Furthermore, we propose a novel power-aware heterogeneous edge-centric GNN model which effectively learns heterogeneous edge semantics and structural properties of the constructed graphs via edge-centric neighborhood aggregation, and fits the formulation of dynamic power. Compared with on-board measurement, PowerGear estimates total and dynamic power for new HLS designs with errors of 3.60% and 8.81%, respectively, which outperforms the prior arts in research and the commercial product Vivado. In addition, PowerGear demonstrates a speedup of 4x over Vivado power estimator. Finally, we present a case study in which PowerGear is exploited to facilitate design space exploration for FPGA HLS, leading to a performance gain of up to 11.2%, compared with methods using state-of-the-art predictive models.
LOSTIN: Logic Optimization via Spatio-Temporal Information with Hybrid Graph Models
Paper ↗
Abstract
Despite the stride made by machine learning (ML) based performance modeling, two major concerns that may impede production-ready ML applications in EDA are stringent accuracy requirements and generalization capability. To this end, we propose hybrid graph neural network (GNN) based approaches towards highly accurate quality-of-result (QoR) estimations with great generalization capability, specifically targeting logic synthesis optimization. The key idea is to simultaneously leverage spatio-temporal information from hardware designs and logic synthesis flows to forecast performance (i.e., delay/area) of various synthesis flows on different designs. The structural characteristics inside hardware designs are distilled and represented by GNNs; the temporal knowledge (i.e., relative ordering of logic transformations) in synthesis flows can be imposed on hardware designs by combining a virtually added supernode or a sequence processing model with conventional GNN models. Evaluation on 3.3 million data points shows that the testing mean absolute percentage error (MAPE) on designs seen and unseen during training are no more than 1.2% and 3.1%, respectively, which are 7-15X lower than existing studies.
High-Level Synthesis Performance Prediction using GNNs: Benchmarking, Modeling, and Advancing
Paper ↗
Abstract
Agile hardware development requires fast and accurate circuit quality evaluation from early design stages. Existing work of high-level synthesis (HLS) performance prediction usually needs extensive feature engineering after the synthesis process. To expedite circuit evaluation from as earlier design stage as possible, we propose a rapid and accurate performance modeling, exploiting the representation power of graph neural networks (GNNs) by representing C/C++ programs as graphs. The contribution of this work is three-fold. First, we build a standard benchmark containing 40k C synthesizable programs, which includes both synthetic programs and three sets of real-world HLS benchmarks. Each program is implemented on FPGA to generate ground-truth performance metrics. Second, we formally formulate the HLS performance prediction problem on graphs, and propose multiple modeling strategies with GNNs that leverage different trade-offs between prediction timeliness (early/late prediction) and accuracy. Third, we further propose a novel hierarchical GNN that does not sacrifice timeliness but largely improves prediction accuracy, significantly outperforming HLS tools. We apply extensive evaluations for both synthetic and unseen real-case programs; our proposed predictor largely outperforms HLS by up to 40X and excels existing predictors by 2X to 5X in terms of resource usage and timing prediction.
Deep Learning Assisted End-to-End Synthesis of mm-Wave Passive Networks with 3D EM Structures: A Study on A Transformer-Based Matching Network
Paper ↗
Abstract
This paper presents a deep learning assisted synthesis approach for direct end-to-end generation of RF/mm-wave passive matching network with 3D EM structures. Different from prior approaches that synthesize EM structures from target circuit component values and target topologies, our proposed approach achieves the direct synthesis of the passive network given the network topology from desired performance values as input. We showcase the proposed synthesis Neural Network (NN) model on an on-chip 1:1 transformer-based impedance matching network. By leveraging parameter sharing, the synthesis NN model successfully extracts relevant features from the input impedance and load capacitors, and predict the transformer 3D EM geometry in a 45nm SOI process that will match the standard 50$\Omega$ load to the target input impedance while absorbing the two loading capacitors. As a proof-of-concept, several example transformer geometries were synthesized, and verified in Ansys HFSS to provide the desired input impedance.
Using Machine Learning for Anomaly Detection on a System-on-Chip under Gamma Radiation
Paper ↗
Abstract
The emergence of new nanoscale technologies has imposed significant challenges to designing reliable electronic systems in radiation environments. A few types of radiation like Total Ionizing Dose (TID) effects often cause permanent damages on such nanoscale electronic devices, and current state-of-the-art technologies to tackle TID make use of expensive radiation-hardened devices. This paper focuses on a novel and different approach: using machine learning algorithms on consumer electronic level Field Programmable Gate Arrays (FPGAs) to tackle TID effects and monitor them to replace before they stop working. This condition has a research challenge to anticipate when the board results in a total failure due to TID effects. We observed internal measurements of the FPGA boards under gamma radiation and used three different anomaly detection machine learning (ML) algorithms to detect anomalies in the sensor measurements in a gamma-radiated environment. The statistical results show a highly significant relationship between the gamma radiation exposure levels and the board measurements. Moreover, our anomaly detection results have shown that a One-Class Support Vector Machine with Radial Basis Function Kernel has an average Recall score of 0.95. Also, all anomalies can be detected before the boards stop working.
A Survey of Deep Learning Techniques for Dynamic Branch Prediction
Paper ↗
Abstract
Branch prediction is an architectural feature that speeds up the execution of branch instruction on pipeline processors and reduces the cost of branching. Recent advancements of Deep Learning (DL) in the post Moore's Law era is accelerating areas of automated chip design, low-power computer architectures, and much more. Traditional computer architecture design and algorithms could benefit from dynamic predictors based on deep learning algorithms which learns from experience by optimizing its parameters on large number of data. In this survey paper, we focus on traditional branch prediction algorithms, analyzes its limitations, and presents a literature survey of how deep learning techniques can be applied to create dynamic branch predictors capable of predicting conditional branch instructions. Prior surveys in this field focus on dynamic branch prediction techniques based on neural network perceptrons. We plan to improve the survey based on latest research in DL and advanced Machine Learning (ML) based branch predictors.
Machine Learning in Congestion Control: A Survey on Selected Algorithms and a New Roadmap to their Implementation
Paper ↗
Abstract
With the emergence of new technologies, computer networks are becoming more structurally complex, diverse and heterogenous. The increasing discrepancy (among the interconnected networks) in data rates, delays, packet loss, and transmission scenarios, influence significantly the dynamics of congestion control (CC) parametrization. In contrast to the traditional endto-end CC algorithms that rely on strict rules, new approaches aim to involve machine learning in order to continuously adapt the CC to real-time network requirements. However, due to the high computational complexity and memory consumption, the feasibility of these schemes may still be questioned. This paper surveys selected machine-learning based approaches to CC and proposes a roadmap to their implementation in computer systems, by using dataflow computing and Gallium Arsenide (GaAs) chips.
TAFA: Design Automation of Analog Mixed-Signal FIR Filters Using Time Approximation Architecture
Paper ↗
Abstract
A digital finite impulse response (FIR) filter design is fully synthesizable, thanks to the mature CAD support of digital circuitry. On the contrary, analog mixed-signal (AMS) filter design is mostly a manual process, including architecture selection, schematic design, and layout. This work presents a systematic design methodology to automate AMS FIR filter design using a time approximation architecture without any tunable passive component, such as switched capacitor or resistor. It not only enhances the flexibility of the filter but also facilitates design automation with reduced analog complexity. The proposed design flow features a hybrid approximation scheme that automatically optimize the filter's impulse response in light of time quantization effects, which shows significant performance improvement with minimum designer's efforts in the loop. Additionally, a layout-aware regression model based on an artificial neural network (ANN), in combination with gradient-based search algorithm, is used to automate and expedite the filter design. With the proposed framework, we demonstrate rapid synthesis of AMS FIR filters in 65nm process from specification to layout.
Analog/Mixed-Signal Circuit Synthesis Enabled by the Advancements of Circuit Architectures and Machine Learning Algorithms
Paper ↗
Abstract
Analog mixed-signal (AMS) circuit architecture has evolved towards more digital friendly due to technology scaling and demand for higher flexibility/reconfigurability. Meanwhile, the design complexity and cost of AMS circuits has substantially increased due to the necessity of optimizing the circuit sizing, layout, and verification of a complex AMS circuit. On the other hand, machine learning (ML) algorithms have been under exponential growth over the past decade and actively exploited by the electronic design automation (EDA) community. This paper will identify the opportunities and challenges brought about by this trend and overview several emerging AMS design methodologies that are enabled by the recent evolution of AMS circuit architectures and machine learning algorithms. Specifically, we will focus on using neural-network-based surrogate models to expedite the circuit design parameter search and layout iterations. Lastly, we will demonstrate the rapid synthesis of several AMS circuit examples from specification to silicon prototype, with significantly reduced human intervention.
MuxLink: Circumventing Learning-Resilient MUX-Locking Using Graph Neural Network-based Link Prediction
Paper ↗
Abstract
Logic locking has received considerable interest as a prominent technique for protecting the design intellectual property from untrusted entities, especially the foundry. Recently, machine learning (ML)-based attacks have questioned the security guarantees of logic locking, and have demonstrated considerable success in deciphering the secret key without relying on an oracle, hence, proving to be very useful for an adversary in the fab. Such ML-based attacks have triggered the development of learning-resilient locking techniques. The most advanced state-of-the-art deceptive MUX-based locking (D-MUX) and the symmetric MUX-based locking techniques have recently demonstrated resilience against existing ML-based attacks. Both defense techniques obfuscate the design by inserting key-controlled MUX logic, ensuring that all the secret inputs to the MUXes are equiprobable. In this work, we show that these techniques primarily introduce local and limited changes to the circuit without altering the global structure of the design. By leveraging this observation, we propose a novel graph neural network (GNN)-based link prediction attack, MuxLink, that successfully breaks both the D-MUX and symmetric MUX-locking techniques, relying only on the underlying structure of the locked design, i.e., in an oracle-less setting. Our trained GNN model learns the structure of the given circuit and the composition of gates around the non-obfuscated wires, thereby generating meaningful link embeddings that help decipher the secret inputs to the MUXes. The proposed MuxLink achieves key prediction accuracy and precision up to 100% on D-MUX and symmetric MUX-locked ISCAS-85 and ITC-99 benchmarks, fully unlocking the designs. We open-source MuxLink [1].
Bayesian Optimization over Permutation Spaces
Paper ↗
Abstract
Optimizing expensive to evaluate black-box functions over an input space consisting of all permutations of d objects is an important problem with many real-world applications. For example, placement of functional blocks in hardware design to optimize performance via simulations. The overall goal is to minimize the number of function evaluations to find high-performing permutations. The key challenge in solving this problem using the Bayesian optimization (BO) framework is to trade-off the complexity of statistical model and tractability of acquisition function optimization. In this paper, we propose and evaluate two algorithms for BO over Permutation Spaces (BOPS). First, BOPS-T employs Gaussian process (GP) surrogate model with Kendall kernels and a Tractable acquisition function optimization approach based on Thompson sampling to select the sequence of permutations for evaluation. Second, BOPS-H employs GP surrogate model with Mallow kernels and a Heuristic search approach to optimize expected improvement acquisition function. We theoretically analyze the performance of BOPS-T to show that their regret grows sub-linearly. Our experiments on multiple synthetic and real-world benchmarks show that both BOPS-T and BOPS-H perform better than the state-of-the-art BO algorithm for combinatorial spaces. To drive future research on this important problem, we make new resources and real-world benchmarks available to the community.
Third-Party Hardware IP Assurance against Trojans through Supervised Learning and Post-processing
Paper ↗
Abstract
System-on-chip (SoC) developers increasingly rely on pre-verified hardware intellectual property (IP) blocks acquired from untrusted third-party vendors. These IPs might contain hidden malicious functionalities or hardware Trojans to compromise the security of the fabricated SoCs. Recently, supervised machine learning (ML) techniques have shown promising capability in identifying nets of potential Trojans in third party IPs (3PIPs). However, they bring several major challenges. First, they do not guide us to an optimal choice of features that reliably covers diverse classes of Trojans. Second, they require multiple Trojan-free/trusted designs to insert known Trojans and generate a trained model. Even if a set of trusted designs are available for training, the suspect IP could be inherently very different from the set of trusted designs, which may negatively impact the verification outcome. Third, these techniques only identify a set of suspect Trojan nets that require manual intervention to understand the potential threat. In this paper, we present VIPR, a systematic machine learning (ML) based trust verification solution for 3PIPs that eliminates the need for trusted designs for training. We present a comprehensive framework, associated algorithms, and a tool flow for obtaining an optimal set of features, training a targeted machine learning model, detecting suspect nets, and identifying Trojan circuitry from the suspect nets. We evaluate the framework on several Trust-Hub Trojan benchmarks and provide a comparative analysis of detection performance across different trained models, selection of features, and post-processing techniques. The proposed post-processing algorithms reduce false positives by up to 92.85%.
A Graph Deep Learning Framework for High-Level Synthesis Design Space Exploration
Paper ↗
Abstract
The design of efficient hardware accelerators for high-throughput data-processing applications, e.g., deep neural networks, is a challenging task in computer architecture design. In this regard, High-Level Synthesis (HLS) emerges as a solution for fast prototyping application-specific hardware starting from a behavioural description of the application computational flow. This Design-Space Exploration (DSE) aims at identifying Pareto optimal synthesis configurations whose exhaustive search is often unfeasible due to the design-space dimensionality and the prohibitive computational cost of the synthesis process. Within this framework, we effectively and efficiently address the design problem by proposing, for the first time in the literature, graph neural networks that jointly predict acceleration performance and hardware costs of a synthesized behavioral specification given optimization directives. The learned model can be used to rapidly approach the Pareto curve by guiding the DSE, taking into account performance and cost estimates. The proposed method outperforms traditional HLS-driven DSE approaches, by accounting for arbitrary length of computer programs and the invariant properties of the input. We propose a novel hybrid control and data flow graph representation that enables training the graph neural network on specifications of different hardware accelerators; the methodology naturally transfers to unseen data-processing applications too. Moreover, we show that our approach achieves prediction accuracy comparable with that of commonly used simulators without having access to analytical models of the HLS compiler and the target FPGA, while being orders of magnitude faster. Finally, the learned representation can be exploited for DSE in unexplored configuration spaces by fine-tuning on a small number of samples from the new target domain.
DeepGate: Learning Neural Representations of Logic Gates
Paper ↗
Abstract
Applying deep learning (DL) techniques in the electronic design automation (EDA) field has become a trending topic. Most solutions apply well-developed DL models to solve specific EDA problems. While demonstrating promising results, they require careful model tuning for every problem. The fundamental question on "How to obtain a general and effective neural representation of circuits?" has not been answered yet. In this work, we take the first step towards solving this problem. We propose DeepGate, a novel representation learning solution that effectively embeds both logic function and structural information of a circuit as vectors on each gate. Specifically, we propose transforming circuits into unified and-inverter graph format for learning and using signal probabilities as the supervision task in DeepGate. We then introduce a novel graph neural network that uses strong inductive biases in practical circuits as learning priors for signal probability prediction. Our experimental results show the efficacy and generalization capability of DeepGate.
Vulcan: Solving the Steiner Tree Problem with Graph Neural Networks and Deep Reinforcement Learning
Paper ↗
Abstract
Steiner Tree Problem (STP) in graphs aims to find a tree of minimum weight in the graph that connects a given set of vertices. It is a classic NP-hard combinatorial optimization problem and has many real-world applications (e.g., VLSI chip design, transportation network planning and wireless sensor networks). Many exact and approximate algorithms have been developed for STP, but they suffer from high computational complexity and weak worst-case solution guarantees, respectively. Heuristic algorithms are also developed. However, each of them requires application domain knowledge to design and is only suitable for specific scenarios. Motivated by the recently reported observation that instances of the same NP-hard combinatorial problem may maintain the same or similar combinatorial structure but mainly differ in their data, we investigate the feasibility and benefits of applying machine learning techniques to solving STP. To this end, we design a novel model Vulcan based on novel graph neural networks and deep reinforcement learning. The core of Vulcan is a novel, compact graph embedding that transforms highdimensional graph structure data (i.e., path-changed information) into a low-dimensional vector representation. Given an STP instance, Vulcan uses this embedding to encode its pathrelated information and sends the encoded graph to a deep reinforcement learning component based on a double deep Q network (DDQN) to find solutions. In addition to STP, Vulcan can also find solutions to a wide range of NP-hard problems (e.g., SAT, MVC and X3C) by reducing them to STP. We implement a prototype of Vulcan and demonstrate its efficacy and efficiency with extensive experiments using real-world and synthetic datasets.
A photosensor employing data-driven binning for ultrafast image recognition
Paper ↗
Abstract
Pixel binning is a technique, widely used in optical image acquisition and spectroscopy, in which adjacent detector elements of an image sensor are combined into larger pixels. This reduces the amount of data to be processed as well as the impact of noise, but comes at the cost of a loss of information. Here, we push the concept of binning to its limit by combining a large fraction of the sensor elements into a single superpixel that extends over the whole face of the chip. For a given pattern recognition task, its optimal shape is determined from training data using a machine learning algorithm. We demonstrate the classification of optically projected images from the MNIST dataset on a nanosecond timescale, with enhanced sensitivity and without loss of classification accuracy. Our concept is not limited to imaging alone but can also be applied in optical spectroscopy or other sensing applications.
Self-Learning Tuning for Post-Silicon Validation
Paper ↗
Abstract
Increasing complexity of modern chips makes design validation more difficult. Existing approaches are not able anymore to cope with the complexity of tasks such as robust performance tuning in post-silicon validation. Therefore, we propose a novel approach based on learn-to-optimize and reinforcement learning in order to solve complex and mixed-type tuning tasks in a efficient and robust way.
Enabling Automated FPGA Accelerator Optimization Using Graph Neural Networks
Paper ↗
Abstract
High-level synthesis (HLS) has freed the computer architects from developing their designs in a very low-level language and needing to exactly specify how the data should be transferred in register-level. With the help of HLS, the hardware designers must describe only a high-level behavioral flow of the design. Despite this, it still can take weeks to develop a high-performance architecture mainly because there are many design choices at a higher level that requires more time to explore. It also takes several minutes to hours to get feedback from the HLS tool on the quality of each design candidate. In this paper, we propose to solve this problem by modeling the HLS tool with a graph neural network (GNN) that is trained to be used for a wide range of applications. The experimental results demonstrate that by employing the GNN-based model, we are able to estimate the quality of design in milliseconds with high accuracy which can help us search through the solution space very quickly.
Generalizable Cross-Graph Embedding for GNN-based Congestion Prediction
Paper ↗
Abstract
Presently with technology node scaling, an accurate prediction model at early design stages can significantly reduce the design cycle. Especially during logic synthesis, predicting cell congestion due to improper logic combination can reduce the burden of subsequent physical implementations. There have been attempts using Graph Neural Network (GNN) techniques to tackle congestion prediction during the logic synthesis stage. However, they require informative cell features to achieve reasonable performance since the core idea of GNNs is built on the message passing framework, which would be impractical at the early logic synthesis stage. To address this limitation, we propose a framework that can directly learn embeddings for the given netlist to enhance the quality of our node features. Popular random-walk based embedding methods such as Node2vec, LINE, and DeepWalk suffer from the issue of cross-graph alignment and poor generalization to unseen netlist graphs, yielding inferior performance and costing significant runtime. In our framework, we introduce a superior alternative to obtain node embeddings that can generalize across netlist graphs using matrix factorization methods. We propose an efficient mini-batch training method at the sub-graph level that can guarantee parallel training and satisfy the memory restriction for large-scale netlists. We present results utilizing open-source EDA tools such as DREAMPLACE and OPENROAD frameworks on a variety of openly available circuits. By combining the learned embedding on top of the netlist with the GNNs, our method improves prediction performance, generalizes to new circuit lines, and is efficient in training, potentially saving over $90 \%$ of runtime.
Defect Detection on Semiconductor Wafers by Distribution Analysis
Paper ↗
Abstract
A method for object classification that is based on distribution analysis is proposed. In addition, a method for finding relevant features and the unification of this algorithm with another classification algorithm is proposed. The presented classification algorithm has been applied successfully to real-world measurement data from wafer fabrication of close to hundred thousand chips of several product types. The presented algorithm prefers finding the best rater in a low-dimensional search space over finding a good rater in a high-dimensional search space. Our approach is interesting in that it is fast (quasi-linear) and reached good to excellent prediction or detection quality for real-world wafer data.
On Joint Learning for Solving Placement and Routing in Chip Design
Paper ↗
Abstract
For its advantage in GPU acceleration and less dependency on human experts, machine learning has been an emerging tool for solving the placement and routing problems, as two critical steps in modern chip design flow. Being still in its early stage, there are fundamental issues: scalability, reward design, and end-to-end learning paradigm etc. To achieve end-to-end placement learning, we first propose a joint learning method termed by DeepPlace for the placement of macros and standard cells, by the integration of reinforcement learning with a gradient based optimization scheme. To further bridge the placement with the subsequent routing task, we also develop a joint learning approach via reinforcement learning to fulfill both macro placement and routing, which is called DeepPR. One key design in our (reinforcement) learning paradigm involves a multi-view embedding model to encode both global graph level and local node level information of the input macros. Moreover, the random network distillation is devised to encourage exploration. Experiments on public chip design benchmarks show that our method can effectively learn from experience and also provides intermediate placement for the post standard cell placement, within few hours for training.
Encoder-Decoder Networks for Analyzing Thermal and Power Delivery Networks
Paper ↗
Abstract
Power delivery network (PDN) analysis and thermal analysis are computationally expensive tasks that are essential for successful IC design. Algorithmically, both these analyses have similar computational structure and complexity as they involve the solution to a partial differential equation of the same form. This paper converts these analyses into image-to-image and sequence-to-sequence translation tasks, which allows leveraging a class of machine learning models with an encoder-decoder-based generative (EDGe) architecture to address the time-intensive nature of these tasks. For PDN analysis, we propose two networks: (i) IREDGe: a full-chip static and dynamic IR drop predictor and (ii) EMEDGe: electromigration (EM) hotspot classifier based on input power, power grid distribution, and power pad distribution patterns. For thermal analysis, we propose ThermEDGe, a full-chip static and dynamic temperature estimator based on input power distribution patterns for thermal analysis. These networks are transferable across designs synthesized within the same technology and packing solution. The networks predict on-chip IR drop, EM hotspot locations, and temperature in milliseconds with negligibly small errors against commercial tools requiring several hours.
OpeNPDN: A Neural-network-based Framework for Power Delivery Network Synthesis
Paper ↗
Abstract
Power delivery network (PDN) design is a nontrivial, time-intensive, and iterative task. Correct PDN design must account for considerations related to power bumps, currents, blockages, and signal congestion distribution patterns. This work proposes a machine learning-based methodology that employs a set of predefined PDN templates. At the floorplan stage, coarse estimates of current, congestion, macro/blockages, and C4 bump distributions are used to synthesize a grid for early design. At the placement stage, the grid is incrementally refined based on more accurate and fine-grained distributions of current and congestion. At each stage, a convolutional neural network (CNN) selects an appropriate PDN template for each region on the chip, building a safe-by-construction PDN that meets IR drop and electromigration (EM) specifications. The CNN is initially trained using a large synthetically-created dataset, following which transfer learning is leveraged to bridge the gap between real-circuit data (with a limited dataset size) and synthetically-generated data. On average, the optimization of the PDN frees thousands of routing tracks in congestion-critical regions, when compared to a globally uniform PDN, while staying within the IR drop and EM limits.
OpenABC-D: A Large-Scale Dataset For Machine Learning Guided Integrated Circuit Synthesis
Paper ↗
Abstract
Logic synthesis is a challenging and widely-researched combinatorial optimization problem during integrated circuit (IC) design. It transforms a high-level description of hardware in a programming language like Verilog into an optimized digital circuit netlist, a network of interconnected Boolean logic gates, that implements the function. Spurred by the success of ML in solving combinatorial and graph problems in other domains, there is growing interest in the design of ML-guided logic synthesis tools. Yet, there are no standard datasets or prototypical learning tasks defined for this problem domain. Here, we describe OpenABC-D,a large-scale, labeled dataset produced by synthesizing open source designs with a leading open-source logic synthesis tool and illustrate its use in developing, evaluating and benchmarking ML-guided logic synthesis. OpenABC-D has intermediate and final outputs in the form of 870,000 And-Inverter-Graphs (AIGs) produced from 1500 synthesis runs plus labels such as the optimized node counts, and de-lay. We define a generic learning problem on this dataset and benchmark existing solutions for it. The codes related to dataset creation and benchmark models are available athttps://github.com/NYU-MLDA/OpenABC.git. The dataset generated is available athttps://archive.nyu.edu/handle/2451/63311
Output Space Entropy Search Framework for Multi-Objective Bayesian Optimization
Paper ↗
Abstract
We consider the problem of black-box multi-objective optimization (MOO) using expensive function evaluations (also referred to as experiments), where the goal is to approximate the true Pareto set of solutions by minimizing the total resource cost of experiments. For example, in hardware design optimization, we need to find the designs that trade-off performance, energy, and area overhead using expensive computational simulations. The key challenge is to select the sequence of experiments to uncover high-quality solutions using minimal resources. In this paper, we propose a general framework for solving MOO problems based on the principle of output space entropy (OSE) search: select the experiment that maximizes the information gained per unit resource cost about the true Pareto front. We appropriately instantiate the principle of OSE search to derive efficient algorithms for the following four MOO problem settings: 1) The most basic em single-fidelity setting, where experiments are expensive and accurate; 2) Handling em black-box constraints} which cannot be evaluated without performing experiments; 3) The discrete multi-fidelity setting, where experiments can vary in the amount of resources consumed and their evaluation accuracy; and 4) The em continuous-fidelity setting, where continuous function approximations result in a huge space of experiments. Experiments on diverse synthetic and real-world benchmarks show that our OSE search based algorithms improve over state-of-the-art methods in terms of both computational-efficiency and accuracy of MOO solutions.
Machine Learning for the Control and Monitoring of Electric Machine Drives: Advances and Trends
Paper ↗
Abstract
This review paper systematically summarizes the existing literature on utilizing machine learning (ML) techniques for the control and monitoring of electric machine drives. It is anticipated that with the rapid progress in learning algorithms and specialized embedded hardware platforms, machine learning-based data-driven approaches will become standard tools for the automated high-performance control and monitoring of electric drives. Additionally, this paper also provides some outlook toward promoting its widespread application in the industry with a focus on deploying ML algorithms onto embedded system-on-chip (SoC) field-programmable gate array (FPGA) devices.
DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networks
Paper ↗
Abstract
Analog circuit sizing takes a significant amount of manual effort in a typical design cycle. With rapidly developing technology and tight schedules, bringing automated solutions for sizing has attracted great attention. This paper presents DNN-Opt, a Reinforcement Learning (RL) inspired Deep Neural Network (DNN) based black-box optimization framework for analog circuit sizing. The key contributions of this paper are a novel sample-efficient two-stage deep learning optimization framework leveraging RL actor-critic algorithms, and a recipe to extend it on large industrial circuits using critical device identification. Our method shows 5--30x sample efficiency compared to other black-box optimization methods both on small building blocks and on large industrial circuits with better performance metrics. To the best of our knowledge, this is the first application of DNN-based circuit sizing on industrial scale circuits.
Device-to-System Performance Evaluation: from Transistor/Interconnect Modeling to VLSI Physical Design and Neural-Network Predictor
Paper ↗
Abstract
We present a DevIce-to-System Performance EvaLuation (DISPEL) workflow that integrates transistor and interconnect modeling, parasitic extraction, standard cell library characterization, logic synthesis, cell placement and routing, and timing analysis to evaluate system-level performance of new CMOS technologies. As the impact of parasitic resistances and capacitances continues to increase with dimensional downscaling, component-level optimization alone becomes insufficient, calling for a holistic assessment and optimization methodology across the boundaries between devices, interconnects, circuits, and systems. The physical implementation flow in DISPEL enables realistic analysis of complex wires and vias in VLSI systems and their impact on the chip power, speed, and area, which simple circuit simulations cannot capture. To demonstrate the use of DISPEL, a 32-bit commercial processor core is implemented using theoretical n-type MoS2 and p-type Black Phosphorous (BP) planar FETs at a projected 5-nm node, and the performance is benchmarked against Si FinFETs. While the superior gate control of the MoS2/BP FETs can theoretically provide 51% reduction in the iso-frequency energy consumption, the actual performance can be greatly limited by the source/drain contact resistances. With the large amount of data generated by DISPEL, a neural-network is trained to predict the key performance metrics of the 32-bit processor core using the characteristics of transistors and interconnects as the input features without the need to go through the time-consuming physical implementation flow. The machine learning algorithms show great potentials as a means for evaluation and optimization of new CMOS technologies and identifying the most significant technology design parameters.
Cohmeleon: Learning-Based Orchestration of Accelerator Coherence in Heterogeneous SoCs
Paper ↗
Abstract
One of the most critical aspects of integrating loosely-coupled accelerators in heterogeneous SoC architectures is orchestrating their interactions with the memory hierarchy, especially in terms of navigating the various cache-coherence options: from accelerators accessing off-chip memory directly, bypassing the cache hierarchy, to accelerators having their own private cache. By running real-size applications on FPGA-based prototypes of many-accelerator multi-core SoCs, we show that the best cache-coherence mode for a given accelerator varies at runtime, depending on the accelerator's characteristics, the workload size, and the overall SoC status. Cohmeleon applies reinforcement learning to select the best coherence mode for each accelerator dynamically at runtime, as opposed to statically at design time. It makes these selections adaptively, by continuously observing the system and measuring its performance. Cohmeleon is accelerator-agnostic, architecture-independent, and it requires minimal hardware support. Cohmeleon is also transparent to application programmers and has a negligible software overhead. FPGA-based experiments show that our runtime approach offers, on average, a 38% speedup with a 66% reduction of off-chip memory accesses compared to state-of-the-art design-time approaches. Moreover, it can match runtime solutions that are manually tuned for the target architecture.
Delving into Macro Placement with Reinforcement Learning
Paper ↗
Abstract
In physical design, human designers typically place macros via trial and error, which is a Markov decision process. Reinforcement learning (RL) methods have demonstrated superhuman performance on the macro placement. In this paper, we propose an extension to this prior work (Mirhoseini et al., 2020). We first describe the details of the policy and value network architecture. We replace the force-directed method with DREAMPlace for placing standard cells in the RL environment. We also compare our improved method with other academic placers on public benchmarks.
Fast Accurate Defect Detection in Wafer Fabrication
Paper ↗
Abstract
A generic fast method for object classification is proposed. In addition, a method for dimensional reduction is presented. The presented algorithms have been applied to real-world data from chip fabrication successfully to the task of predicting defect states of tens of thousands of chips of several products based on measurements or even just part of measurements. Unlike typical neural networks with a large number of weights to optimize over, the presented algorithm tries optimizing only over a very small number of variables in order to increase chances to find a global optimum. Our approach is interesting in that it is fast, led to good to very good performance with real-world wafer data, allows for short implementations and computes values which have a clear meaning easy to explain.
No DBA? No regret! Multi-armed bandits for index tuning of analytical and HTAP workloads with provable guarantees
Paper ↗
Abstract
Automating physical database design has remained a long-term interest in database research due to substantial performance gains afforded by optimised structures. Despite significant progress, a majority of today's commercial solutions are highly manual, requiring offline invocation by database administrators (DBAs) who are expected to identify and supply representative training workloads. Even the latest advancements like query stores provide only limited support for dynamic environments. This status quo is untenable: identifying representative static workloads is no longer realistic; and physical design tools remain susceptible to the query optimiser's cost misestimates. Furthermore, modern application environments such as hybrid transactional and analytical processing (HTAP) systems render analytical modelling next to impossible. We propose a self-driving approach to online index selection that eschews the DBA and query optimiser, and instead learns the benefits of viable structures through strategic exploration and direct performance observation. We view the problem as one of sequential decision making under uncertainty, specifically within the bandit learning setting. Multi-armed bandits balance exploration and exploitation to provably guarantee average performance that converges to policies that are optimal with perfect hindsight. Our comprehensive empirical evaluation against a state-of-the-art commercial tuning tool demonstrates up to 75% speed-up on shifting and ad-hoc workloads and up to 28% speed-up on static workloads in analytical processing environments. In HTAP environments, our solution provides up to 59% speed-up on shifting and 51% speed-up on static workloads. Furthermore, our bandit framework outperforms deep reinforcement learning (RL) in terms of convergence speed and performance volatility (providing up to 58% speed-up).
Mining Secure Behavior of Hardware Designs
Paper ↗
Abstract
Specification mining offers a solution by automating security specification for hardware. Specification miners use a form of machine learning to specify behaviors of a system by studying a system in execution. However, specification mining was first developed for use with software. Complex hardware designs offer unique challenges for this technique. Further, specification miners traditionally capture functional specifications without a notion of security, and may not use the specification logics necessary to describe some security requirements. This work demonstrates specification mining for hardware security. On CISC architectures such as x86, I demonstrate that a miner partitioning the design state space along control signals discovers a specification that includes manually defined properties and, if followed, would secure CPU designs against Memory Sinkhole and SYSRET privilege escalation. For temporal properties, I demonstrate that a miner using security specific linear temporal logic (LTL) templates for specification detection may find properties that, if followed, would secure designs against historical documented security vulnerabilities and against potential future attacks targeting system initialization. For information--flow hyperproperties, I demonstrate that a miner may use Information Flow Tracking (IFT) to develop output properties containing designer specified information--flow security properties as well as properties that demonstrate a design does not contain certain Common Weakness Enumerations (CWEs).
AIRCHITECT: Learning Custom Architecture Design and Mapping Space
Paper ↗
Abstract
Design space exploration is an important but costly step involved in the design/deployment of custom architectures to squeeze out maximum possible performance and energy efficiency. Conventionally, optimizations require iterative sampling of the design space using simulation or heuristic tools. In this paper we investigate the possibility of learning the optimization task using machine learning and hence using the learnt model to predict optimal parameters for the design and mapping space of custom architectures, bypassing any exploration step. We use three case studies involving the optimal array design, SRAM buffer sizing, mapping, and schedule determination for systolic-array-based custom architecture design and mapping space. Within the purview of these case studies, we show that it is possible to capture the design space and train a model to "generalize" prediction the optimal design and mapping parameters when queried with workload and design constraints. We perform systematic design-aware and statistical analysis of the optimization space for our case studies and highlight the patterns in the design space. We formulate the architecture design and mapping as a machine learning problem that allows us to leverage existing ML models for training and inference. We design and train a custom network architecture called AIRCHITECT, which is capable of learning the architecture design space with as high as 94.3% test accuracy and predicting optimal configurations which achieve on average (GeoMean) of 99.9% the best possible performance on a test dataset with $10^5$ GEMM workloads.
VeRLPy: Python Library for Verification of Digital Designs with Reinforcement Learning
Paper ↗
Abstract
Digital hardware is verified by comparing its behavior against a reference model on a range of randomly generated input signals. The random generation of the inputs hopes to achieve sufficient coverage of the different parts of the design. However, such coverage is often difficult to achieve, amounting to large verification efforts and delays. An alternative is to use Reinforcement Learning (RL) to generate the inputs by learning to prioritize those inputs which can more efficiently explore the design under test. In this work, we present VeRLPy an open-source library to allow RL-driven verification with limited additional engineering overhead. This contributes to two broad movements within the EDA community of (a) moving to open-source toolchains and (b) reducing barriers for development with Python support. We also demonstrate the use of VeRLPy for a few designs and establish its value over randomly generated input signals.
BoA-PTA, A Bayesian Optimization Accelerated Error-Free SPICE Solver
Paper ↗
Abstract
One of the greatest challenges in IC design is the repeated executions of computationally expensive SPICE simulations, particularly when highly complex chip testing/verification is involved. Recently, pseudo transient analysis (PTA) has shown to be one of the most promising continuation SPICE solver. However, the PTA efficiency is highly influenced by the inserted pseudo-parameters. In this work, we proposed BoA-PTA, a Bayesian optimization accelerated PTA that can substantially accelerate simulations and improve convergence performance without introducing extra errors. Furthermore, our method does not require any pre-computation data or offline training. The acceleration framework can either be implemented to speed up ongoing repeated simulations immediately or to improve new simulations of completely different circuits. BoA-PTA is equipped with cutting-edge machine learning techniques, e.g., deep learning, Gaussian process, Bayesian optimization, non-stationary monotonic transformation, and variational inference via parameterization. We assess BoA-PTA in 43 benchmark circuits against other SOTA SPICE solvers and demonstrate an average 2.3x (maximum 3.5x) speed-up over the original CEPTA.
Technical Report for HW2VEC -- A Graph Learning Tool for Automating Hardware Security
Paper ↗
Abstract
In this technical report, we present HW2VEC [11], an open-source graph learning tool for hardware security, and its implementation details (Figure 1). HW2VEC provides toolboxes for graph representation extraction in the form of Data Flow Graphs (DFGs) or Abstract Syntax Trees (ASTs) from hardware designs at RTL and GLN levels. Besides, HW2VEC also offers graph learning tools for representing hardware designs in vectors that preserve both structural features and behavioral features. To the best of our knowledge, HW2VEC is the first open-source research tool that supports applying graph learning methods to hardware designs in different abstraction levels for hardware security. We organize the remainder of this technical report as follows: Section 2 introduces the architecture of HW2VEC; Section 3 gives information about the use-case implementations; Section 4 provides the experimental results and demonstrates the performance of HW2VEC for two hardware security applications: HT detection and IP piracy detection; finally, Section 5 will conclude this report.
HW2VEC: A Graph Learning Tool for Automating Hardware Security
Paper ↗
Abstract
The time-to-market pressure and continuous growing complexity of hardware designs have promoted the globalization of the Integrated Circuit (IC) supply chain. However, such globalization also poses various security threats in each phase of the IC supply chain. Although the advancements of Machine Learning (ML) have pushed the frontier of hardware security, most conventional ML-based methods can only achieve the desired performance by manually finding a robust feature representation for circuits that are non-Euclidean data. As a result, modeling these circuits using graph learning to improve design flows has attracted research attention in the Electronic Design Automation (EDA) field. However, due to the lack of supporting tools, only a few existing works apply graph learning to resolve hardware security issues. To attract more attention, we propose HW2VEC, an open-source graph learning tool that lowers the threshold for newcomers to research hardware security applications with graphs. HW2VEC provides an automated pipeline for extracting a graph representation from a hardware design in various abstraction levels (register transfer level or gate-level netlist). Besides, HW2VEC users can automatically transform the non-Euclidean hardware designs into Euclidean graph embeddings for solving their problems. In this paper, we demonstrate that HW2VEC can achieve state-of-the-art performance on two hardware security-related tasks: Hardware Trojan Detection and Intellectual Property Piracy Detection. We provide the time profiling results for the graph extraction and the learning pipelines in HW2VEC.
GNN4IP: Graph Neural Network for Hardware Intellectual Property Piracy Detection
Paper ↗
Abstract
Aggressive time-to-market constraints and enormous hardware design and fabrication costs have pushed the semiconductor industry toward hardware Intellectual Properties (IP) core design. However, the globalization of the integrated circuits (IC) supply chain exposes IP providers to theft and illegal redistribution of IPs. Watermarking and fingerprinting are proposed to detect IP piracy. Nevertheless, they come with additional hardware overhead and cannot guarantee IP security as advanced attacks are reported to remove the watermark, forge, or bypass it. In this work, we propose a novel methodology, GNN4IP, to assess similarities between circuits and detect IP piracy. We model the hardware design as a graph and construct a graph neural network model to learn its behavior using the comprehensive dataset of register transfer level codes and gate-level netlists that we have gathered. GNN4IP detects IP piracy with 96% accuracy in our dataset and recognizes the original IP in its obfuscated version with 100% accuracy.
Transformer-based Machine Learning for Fast SAT Solvers and Logic Synthesis
Paper ↗
Abstract
CNF-based SAT and MaxSAT solvers are central to logic synthesis and verification systems. The increasing popularity of these constraint problems in electronic design automation encourages studies on different SAT problems and their properties for further computational efficiency. There has been both theoretical and practical success of modern Conflict-driven clause learning SAT solvers, which allows solving very large industrial instances in a relatively short amount of time. Recently, machine learning approaches provide a new dimension to solving this challenging problem. Neural symbolic models could serve as generic solvers that can be specialized for specific domains based on data without any changes to the structure of the model. In this work, we propose a one-shot model derived from the Transformer architecture to solve the MaxSAT problem, which is the optimization version of SAT where the goal is to satisfy the maximum number of clauses. Our model has a scale-free structure which could process varying size of instances. We use meta-path and self-attention mechanism to capture interactions among homogeneous nodes. We adopt cross-attention mechanisms on the bipartite graph to capture interactions among heterogeneous nodes. We further apply an iterative algorithm to our model to satisfy additional clauses, enabling a solution approaching that of an exact-SAT problem. The attention mechanisms leverage the parallelism for speedup. Our evaluation indicates improved speedup compared to heuristic approaches and improved completion rate compared to machine learning approaches.
CNN-Cap: Effective Convolutional Neural Network Based Capacitance Models for Full-Chip Parasitic Extraction
Paper ↗
Abstract
Accurate capacitance extraction is becoming more important for designing integrated circuits under advanced process technology. The pattern matching based full-chip extraction methodology delivers fast computational speed, but suffers from large error, and tedious efforts on building capacitance models of the increasing structure patterns. In this work, we propose an effective method for building convolutional neural network (CNN) based capacitance models (called CNN-Cap) for two-dimensional (2-D) structures in full-chip capacitance extraction. With a novel grid-based data representation, the proposed method is able to model the pattern with a variable number of conductors, so that largely reduce the number of patterns. Based on the ability of ResNet architecture on capturing spatial information and the proposed training skills, the obtained CNN-Cap exhibits much better performance over the multilayer perception neural network based capacitance model while being more versatile. Extensive experiments on a 55nm and a 15nm process technologies have demonstrated that the error of total capacitance produced with CNN-Cap is always within 1.3% and the error of produced coupling capacitance is less than 10% in over 99.5% probability. CNN-Cap runs more than 4000X faster than 2-D field solver on a GPU server, while it consumes negligible memory compared to the look-up table based capacitance model.
Deep Learning Assisted Compact Modeling of Nanoscale Transistor
Paper ↗
Abstract
Transistors are the basic building blocks for all electronics. Accurate prediction of their current-voltage (IV) characteristics enables circuit simulations before the expensive silicon tape-out. In this work, we propose using deep neural network to improve the accuracy for the conventional, physics-based compact model for nanoscale transistors. Physics-driven requirements on the neural network are discussed. Using finite element simulation as the input dataset, together with a neural network with roughly 30 neurons, the final IV model can well-predict the IV to within 1%. The trained model can readily be implemented by the hardware description language (HDL) such as VerilogA for circuit simulation.
Multi-armed Bandit Algorithms on System-on-Chip: Go Frequentist or Bayesian?
Paper ↗
Abstract
Multi-armed Bandit (MAB) algorithms identify the best arm among multiple arms via exploration-exploitation trade-off without prior knowledge of arm statistics. Their usefulness in wireless radio, IoT, and robotics demand deployment on edge devices, and hence, a mapping on system-on-chip (SoC) is desired. Theoretically, the Bayesian approach-based Thompson Sampling (TS) algorithm offers better performance than the frequentist approach-based Upper Confidence Bound (UCB) algorithm. However, TS is not synthesizable due to Beta function. We address this problem by approximating it via a pseudo-random number generator-based approach and efficiently realize the TS algorithm on Zynq SoC. In practice, the type of arms distribution (e.g., Bernoulli, Gaussian, etc.) is unknown and hence, a single algorithm may not be optimal. We propose a reconfigurable and intelligent MAB (RI-MAB) framework. Here, intelligence enables the identification of appropriate MAB algorithms for a given environment, and reconfigurability allows on-the-fly switching between algorithms on the SoC. This eliminates the need for parallel implementation of algorithms resulting in huge savings in resources and power consumption. We analyze the functional correctness, area, power, and execution time of the proposed and existing architectures for various arm distributions, word-length, and hardware-software co-design approaches. We demonstrate the superiority of the RI-MAB over TS and UCB only architectures.
Improving Semiconductor Device Modeling for Electronic Design Automation by Machine Learning Techniques
Paper ↗
Abstract
The semiconductors industry benefits greatly from the integration of Machine Learning (ML)-based techniques in Technology Computer-Aided Design (TCAD) methods. The performance of ML models however relies heavily on the quality and quantity of training datasets. They can be particularly difficult to obtain in the semiconductor industry due to the complexity and expense of the device fabrication. In this paper, we propose a self-augmentation strategy for improving ML-based device modeling using variational autoencoder-based techniques. These techniques require a small number of experimental data points and does not rely on TCAD tools. To demonstrate the effectiveness of our approach, we apply it to a deep neural network-based prediction task for the Ohmic resistance value in Gallium Nitride devices. A 70% reduction in mean absolute error when predicting experimental results is achieved. The inherent flexibility of our approach allows easy adaptation to various tasks, thus making it highly relevant to many applications of the semiconductor industry.
Continual Learning Approach for Improving the Data and Computation Mapping in Near-Memory Processing System
Paper ↗
Abstract
The resurgence of near-memory processing (NMP) with the advent of big data has shifted the computation paradigm from processor-centric to memory-centric computing. To meet the bandwidth and capacity demands of memory-centric computing, 3D memory has been adopted to form a scalable memory-cube network. Along with NMP and memory system development, the mapping for placing data and guiding computation in the memory-cube network has become crucial in driving the performance improvement in NMP. However, it is very challenging to design a universal optimal mapping for all applications due to unique application behavior and intractable decision space. In this paper, we propose an artificially intelligent memory mapping scheme, AIMM, that optimizes data placement and resource utilization through page and computation remapping. Our proposed technique involves continuously evaluating and learning the impact of mapping decisions on system performance for any application. AIMM uses a neural network to achieve a near-optimal mapping during execution, trained using a reinforcement learning algorithm that is known to be effective for exploring a vast design space. We also provide a detailed AIMM hardware design that can be adopted as a plugin module for various NMP systems. Our experimental evaluation shows that AIMM improves the baseline NMP performance in single and multiple program scenario by up to 70% and 50%, respectively.
SGL: Spectral Graph Learning from Measurements
Paper ↗
Abstract
This work introduces a highly scalable spectral graph densification framework for learning resistor networks with linear measurements, such as node voltages and currents. We prove that given $O(\log N)$ pairs of voltage and current measurements, it is possible to recover ultra-sparse $N$-node resistor networks which can well preserve the effective resistance distances on the graph. Also, the learned graphs preserve the structural (spectral) properties of the original graph, which can potentially be leveraged in many circuit design and optimization tasks. We show that the proposed graph learning approach is equivalent to solving the classical graphical Lasso problems with Laplacian-like precision matrices. Through extensive experiments for a variety of real-world test cases, we show that the proposed approach is highly scalable for learning ultra-sparse resistor networks without sacrificing solution quality.
SGL: Spectral Graph Learning from Measurements
Paper ↗
Abstract
This work introduces a highly scalable spectral graph densification framework for learning resistor networks with linear measurements, such as node voltages and currents. We prove that given $O(\log N)$ pairs of voltage and current measurements, it is possible to recover ultra-sparse $N$-node resistor networks which can well preserve the effective resistance distances on the graph. Also, the learned graphs preserve the structural (spectral) properties of the original graph, which can potentially be leveraged in many circuit design and optimization tasks. We show that the proposed graph learning approach is equivalent to solving the classical graphical Lasso problems with Laplacian-like precision matrices. Through extensive experiments for a variety of real-world test cases, we show that the proposed approach is highly scalable for learning ultra-sparse resistor networks without sacrificing solution quality.
Fast Design Space Exploration of Nonlinear Systems: Part II
Paper ↗
Abstract
Nonlinear system design is often a multi-objective optimization problem involving search for a design that satisfies a number of predefined constraints. The design space is typically very large since it includes all possible system architectures with different combinations of components composing each architecture. In this article, we address nonlinear system design space exploration through a two-step approach encapsulated in a framework called Fast Design Space Exploration of Nonlinear Systems (ASSENT). In the first step, we use a genetic algorithm to search for system architectures that allow discrete choices for component values or else only component values for a fixed architecture. This step yields a coarse design since the system may or may not meet the target specifications. In the second step, we use an inverse design to search over a continuous space and fine-tune the component values with the goal of improving the value of the objective function. We use a neural network to model the system response. The neural network is converted into a mixed-integer linear program for active learning to sample component values efficiently. We illustrate the efficacy of ASSENT on problems ranging from nonlinear system design to design of electrical circuits. Experimental results show that ASSENT achieves the same or better value of the objective function compared to various other optimization techniques for nonlinear system design by up to 54%. We improve sample efficiency by 6-10x compared to reinforcement learning based synthesis of electrical circuits.
The Validation of Graph Model-Based, Gate Level Low-Dimensional Feature Data for Machine Learning Applications
Paper ↗
Abstract
As an alternative to traditional fault injection-based methodologies and to explore the applicability of modern machine learning algorithms in the field of reliability engineering, this paper proposes a systemic framework that explores gate-level netlist circuit abstractions to extract and exploit relevant feature representations in a low-dimensional vector space. A scalable feature learning method on a graphical domain called node2vec algorithm had been utilized for efficiently extracting structural features of the netlist, providing a valuable database to exercise a selection of machine learning (ML) or deep learning (DL) algorithms aiming at predicting fault propagation metrics. The current work proposes to model the gate-level netlist as a Probabilistic Bayesian Graph (PGB) in the form of a Graph Modeling Language (GML) format. To accomplish this goal, a Verilog Procedural Interface (VPI) library linked to standard simulation tools has been built to map gate-level netlist into the graph model. The extracted features have been used for predicting the Functional Derating (FDR) factors of individual flip-flops of a given circuit through Support Vector Machine (SVM) and Deep Neural Network (DNN) algorithms. The results of the approach have been compared against data obtained through first-principles approaches. The whole experiment was implemented on the features extracted from the 10-Gigabit Ethernet MAC IEEE 802.3 standard circuit.
Fast Design Space Exploration of Nonlinear Systems: Part I
Paper ↗
Abstract
System design tools are often only available as input-output blackboxes: for a given design as input they compute an output representing system behavior. Blackboxes are intended to be run in the forward direction. This paper presents a new method of solving the inverse design problem namely, given requirements or constraints on output, find an input that also optimizes an objective function. This problem is challenging for several reasons. First, blackboxes are not designed to be run in reverse. Second, inputs and outputs can be discrete and continuous. Third, finding designs concurrently satisfying a set of requirements is hard because designs satisfying individual requirements may conflict with each other. Fourth, blackbox evaluations can be expensive. Finally, blackboxes can sometimes fail to produce an output. This paper presents CNMA, a new method of solving the inverse problem that overcomes these challenges. CNMA tries to sample only the part of the design space relevant to solving the problem, leveraging the power of neural networks, Mixed Integer Linear Programs, and a new learning-from-failure feedback loop. The paper also presents a parallel version of CNMA that improves the efficiency and quality of solutions over the sequential version, and tries to steer it away from local optima. CNMA's performance is evaluated against conventional optimization methods for seven nonlinear design problems of 8 (two problems), 10, 15, 36 and 60 real-valued dimensions and one with 186 binary dimensions. Conventional methods evaluated are off-the-shelf implementations of Bayesian Optimization with Gaussian Processes, Nelder Mead and Random Search. The first two do not solve problems that are high-dimensional, have discrete and continuous variables or whose blackboxes can fail to return values. CNMA solves all problems, and surpasses the performance of conventional methods by up to 87%.
UDO: Universal Database Optimization using Reinforcement Learning
Paper ↗
Abstract
UDO is a versatile tool for offline tuning of database systems for specific workloads. UDO can consider a variety of tuning choices, reaching from picking transaction code variants over index selections up to database system parameter tuning. UDO uses reinforcement learning to converge to near-optimal configurations, creating and evaluating different configurations via actual query executions (instead of relying on simplifying cost models). To cater to different parameter types, UDO distinguishes heavy parameters (which are expensive to change, e.g. physical design parameters) from light parameters. Specifically for optimizing heavy parameters, UDO uses reinforcement learning algorithms that allow delaying the point at which the reward feedback becomes available. This gives us the freedom to optimize the point in time and the order in which different configurations are created and evaluated (by benchmarking a workload sample). UDO uses a cost-based planner to minimize reconfiguration overheads. For instance, it aims to amortize the creation of expensive data structures by consecutively evaluating configurations using them. We evaluate UDO on Postgres as well as MySQL and on TPC-H as well as TPC-C, optimizing a variety of light and heavy parameters concurrently.
IronMan: GNN-assisted Design Space Exploration in High-Level Synthesis via Reinforcement Learning
Paper ↗
Abstract
Despite the great success of High-Level Synthesis (HLS) tools, we observe several unresolved challenges: 1) the high-level abstraction of programming styles in HLS sometimes conceals optimization opportunities; 2) existing HLS tools do not provide flexible trade-off (Pareto) solutions among different objectives and constraints; 3) the actual quality of the resulting RTL designs is hard to predict. To address these challenges, we propose an end-to-end framework, namelyIronMan. The primary goal is to enable a flexible and automated design space exploration (DSE), to provide either optimal solutions under user-specified constraints, or various trade-offs among different objectives (such as different types of resources, area, and latency). Such DSE either requires tedious manual efforts or is not achievable to attain these goals through existing HLS tools. There are three components in IronMan: 1) GPP, a highly accurate graph-neural-network-based performance and resource predictor; 2) RLMD, a reinforcement-learning-based multi-objective DSE engine that explores the optimal resource allocation strategy, to provide Pareto solutions between different objectives; 3) CT, a code transformer to assist RLMD and GPP, which extracts the data flow graph from original HLS C/C++ and automatically generates synthesizable code with HLS directives. The experimental results show that: 1) GPP achieves high prediction accuracy, reducing prediction errors of HLS tools by 10.9x in resource utilization and 5.7x in timing; 2) RLMD obtains optimal or Pareto solutions that outperform the genetic algorithm and simulated annealing by 12.7% and 12.9%, respectively; 3) IronMan is able to find optimized solutions perfectly matching various DSP constraints, with 2.54x fewer DSPs and up to 6x shorter latency than those of HLS tools while being up to 400x faster than the heuristic algorithms and HLS tools.
A Survey of Machine Learning for Computer Architecture and Systems
Paper ↗
Abstract
It has been a long time that computer architecture and systems are optimized for efficient execution of machine learning (ML) models. Now, it is time to reconsider the relationship between ML and systems, and let ML transform the way that computer architecture and systems are designed. This embraces a twofold meaning: improvement of designers' productivity, and completion of the virtuous cycle. In this paper, we present a comprehensive review of the work that applies ML for computer architecture and system design. First, we perform a high-level taxonomy by considering the typical role that ML techniques take in architecture/system design, i.e., either for fast predictive modeling or as the design methodology. Then, we summarize the common problems in computer architecture/system design that can be solved by ML techniques, and the typical ML techniques employed to resolve each of them. In addition to emphasis on computer architecture in a narrow sense, we adopt the concept that data centers can be recognized as warehouse-scale computers; sketchy discussions are provided in adjacent computer systems, such as code generation and compiler; we also give attention to how ML techniques can aid and transform design automation. We further provide a future vision of opportunities and potential directions, and envision that applying ML for computer architecture and systems would thrive in the community.
Feature Engineering for Scalable Application-Level Post-Silicon Debugging
Paper ↗
Abstract
We present systematic and efficient solutions for both observability enhancement and root-cause diagnosis of post-silicon System-on-Chips (SoCs) validation with diverse usage scenarios. We model specification of interacting flows in typical applications for message selection. Our method for message selection optimizes flow specification coverage and trace buffer utilization. We define the diagnosis problem as identifying buggy traces as outliers and bug-free traces as inliers/normal behaviors, for which we use unsupervised learning algorithms for outlier detection. Instead of direct application of machine learning algorithms over trace data using the signals as raw features, we use feature engineering to transform raw features into more sophisticated features using domain specific operations. The engineered features are highly relevant to the diagnosis task and are generic to be applied across any hardware designs. We present debugging and root cause analysis of subtle post-silicon bugs in industry-scale OpenSPARC T2 SoC. We achieve a trace buffer utilization of 98.96\% with a flow specification coverage of 94.3\% (average). Our diagnosis method was able to diagnose up to 66.7\% more bugs and took up to 847$\times$ less diagnosis time as compared to the manual debugging with a diagnosis precision of 0.769.
AutoPilot: Automating SoC Design Space Exploration for SWaP Constrained Autonomous UAVs
Paper ↗
Abstract
Building domain-specific accelerators for autonomous unmanned aerial vehicles (UAVs) is challenging due to a lack of systematic methodology for designing onboard compute. Balancing a computing system for a UAV requires considering both the cyber (e.g., sensor rate, compute performance) and physical (e.g., payload weight) characteristics that affect overall performance. Iterating over the many component choices results in a combinatorial explosion of the number of possible combinations: from 10s of thousands to billions, depending on implementation details. Manually selecting combinations of these components is tedious and expensive. To navigate the {cyber-physical design space} efficiently, we introduce \emph{AutoPilot}, a framework that automates full-system UAV co-design. AutoPilot uses Bayesian optimization to navigate a large design space and automatically select a combination of autonomy algorithm and hardware accelerator while considering the cross-product effect of other cyber and physical UAV components. We show that the AutoPilot methodology consistently outperforms general-purpose hardware selections like Xavier NX and Jetson TX2, as well as dedicated hardware accelerators built for autonomous UAVs, across a range of representative scenarios (three different UAV types and three deployment environments). Designs generated by AutoPilot increase the number of missions on average by up to 2.25x, 1.62x, and 1.43x for nano, micro, and mini-UAVs respectively over baselines. Our work demonstrates the need for holistic full-UAV co-design to achieve maximum overall UAV performance and the need for automated flows to simplify the design process for autonomous cyber-physical systems.
Machine Learning for Electronic Design Automation: A Survey
Paper ↗
Abstract
With the down-scaling of CMOS technology, the design complexity of very large-scale integrated (VLSI) is increasing. Although the application of machine learning (ML) techniques in electronic design automation (EDA) can trace its history back to the 90s, the recent breakthrough of ML and the increasing complexity of EDA tasks have aroused more interests in incorporating ML to solve EDA tasks. In this paper, we present a comprehensive review of existing ML for EDA studies, organized following the EDA hierarchy.
MAVIREC: ML-Aided Vectored IR-DropEstimation and Classification
Paper ↗
Abstract
Vectored IR drop analysis is a critical step in chip signoff that checks the power integrity of an on-chip power delivery network. Due to the prohibitive runtimes of dynamic IR drop analysis, the large number of test patterns must be whittled down to a small subset of worst-case IR vectors. Unlike the traditional slow heuristic method that select a few vectors with incomplete coverage, MAVIREC uses machine learning techniques -- 3D convolutions and regression-like layers -- for accurately recommending a larger subset of test patterns that exercise worst-case scenarios. In under 30 minutes, MAVIREC profiles 100K-cycle vectors and provides better coverage than a state-of-the-art industrial flow. Further, MAVIREC's IR drop predictor shows 10x speedup with under 4mV RMSE relative to an industrial flow.
A Dual-Store Structure for Knowledge Graphs
Paper ↗
Abstract
To effectively manage increasing knowledge graphs in various domains, a hot research topic, knowledge graph storage management, has emerged. Existing methods are classified to relational stores and native graph stores. Relational stores are able to store large-scale knowledge graphs and convenient in updating knowledge, but the query performance weakens obviously when the selectivity of a knowledge graph query is large. Native graph stores are efficient in processing complex knowledge graph queries due to its index-free adjacent property, but they are inapplicable to manage a large-scale knowledge graph due to limited storage budgets or inflexible updating process. Motivated by this, we propose a dual-store structure which leverages a graph store to accelerate the complex query process in the relational store. However, it is challenging to determine what data to transfer from relational store to graph store at what time. To address this problem, we formulate it as a Markov Decision Process and derive a physical design tuner DOTIL based on reinforcement learning. With DOTIL, the dual-store structure is adaptive to dynamic changing workloads. Experimental results on real knowledge graphs demonstrate that our proposed dual-store structure improves query performance up to average 43.72% compared with the most commonly used relational stores.
MLComp: A Methodology for Machine Learning-based Performance Estimation and Adaptive Selection of Pareto-Optimal Compiler Optimization Sequences
Paper ↗
Abstract
Embedded systems have proliferated in various consumer and industrial applications with the evolution of Cyber-Physical Systems and the Internet of Things. These systems are subjected to stringent constraints so that embedded software must be optimized for multiple objectives simultaneously, namely reduced energy consumption, execution time, and code size. Compilers offer optimization phases to improve these metrics. However, proper selection and ordering of them depends on multiple factors and typically requires expert knowledge. State-of-the-art optimizers facilitate different platforms and applications case by case, and they are limited by optimizing one metric at a time, as well as requiring a time-consuming adaptation for different targets through dynamic profiling. To address these problems, we propose the novel MLComp methodology, in which optimization phases are sequenced by a Reinforcement Learning-based policy. Training of the policy is supported by Machine Learning-based analytical models for quick performance estimation, thereby drastically reducing the time spent for dynamic profiling. In our framework, different Machine Learning models are automatically tested to choose the best-fitting one. The trained Performance Estimator model is leveraged to efficiently devise Reinforcement Learning-based multi-objective policies for creating quasi-optimal phase sequences. Compared to state-of-the-art estimation models, our Performance Estimator model achieves lower relative error (<2%) with up to 50x faster training time over multiple platforms and application domains. Our Phase Selection Policy improves execution time and energy consumption of a given code by up to 12% and 6%, respectively. The Performance Estimator and the Phase Selection Policy can be trained efficiently for any target platform and application domain.
Logic Synthesis Meets Machine Learning: Trading Exactness for Generalization
Paper ↗
Abstract
Logic synthesis is a fundamental step in hardware design whose goal is to find structural representations of Boolean functions while minimizing delay and area. If the function is completely-specified, the implementation accurately represents the function. If the function is incompletely-specified, the implementation has to be true only on the care set. While most of the algorithms in logic synthesis rely on SAT and Boolean methods to exactly implement the care set, we investigate learning in logic synthesis, attempting to trade exactness for generalization. This work is directly related to machine learning where the care set is the training set and the implementation is expected to generalize on a validation set. We present learning incompletely-specified functions based on the results of a competition conducted at IWLS 2020. The goal of the competition was to implement 100 functions given by a set of care minterms for training, while testing the implementation using a set of validation minterms sampled from the same function. We make this benchmark suite available and offer a detailed comparative analysis of the different approaches to learning
Optimising Design Verification Using Machine Learning: An Open Source Solution
Paper ↗
Abstract
With the complexity of Integrated Circuits increasing, design verification has become the most time consuming part of the ASIC design flow. Nearly 70% of the SoC design cycle is consumed by verification. The most commonly used approach to test all corner cases is through the use of Constrained Random Verification. Random stimulus is given in order to hit all possible combinations and test the design thoroughly. However, this approach often requires significant human expertise to reach all corner cases. This paper presents an alternative using Machine Learning to generate the input stimulus. This will allow for faster thorough verification of the design with less human intervention. Furthermore, it is proposed to use the open source verification environment 'Cocotb'. Based on Python, it is simple, intuitive and has a vast library of functions for machine learning applications. This makes it more convenient to use than the bulkier approach using traditional Hardware Verification Languages such as System Verilog or Specman E.
Automatic Routability Predictor Development Using Neural Architecture Search
Paper ↗
Abstract
The rise of machine learning technology inspires a boom of its applications in electronic design automation (EDA) and helps improve the degree of automation in chip designs. However, manually crafted machine learning models require extensive human expertise and tremendous engineering efforts. In this work, we leverage neural architecture search (NAS) to automate the development of high-quality neural architectures for routability prediction, which can help to guide cell placement toward routable solutions. Our search method supports various operations and highly flexible connections, leading to architectures significantly different from all previous human-crafted models. Experimental results on a large dataset demonstrate that our automatically generated neural architectures clearly outperform multiple representative manually crafted solutions. Compared to the best case of manually crafted models, NAS-generated models achieve 5.85% higher Kendall's $\tau$ in predicting the number of nets with DRC violations and 2.12% better area under ROC curve (ROC-AUC) in DRC hotspot detection. Moreover, compared with human-crafted models, which easily take weeks to develop, our efficient NAS approach finishes the whole automatic search process with only 0.3 days.
Net2: A Graph Attention Network Method Customized for Pre-Placement Net Length Estimation
Paper ↗
Abstract
Net length is a key proxy metric for optimizing timing and power across various stages of a standard digital design flow. However, the bulk of net length information is not available until cell placement, and hence it is a significant challenge to explicitly consider net length optimization in design stages prior to placement, such as logic synthesis. This work addresses this challenge by proposing a graph attention network method with customization, called Net2, to estimate individual net length before cell placement. Its accuracy-oriented version Net2a achieves about 15% better accuracy than several previous works in identifying both long nets and long critical paths. Its fast version Net2f is more than 1000 times faster than placement while still outperforms previous works and other neural network techniques in terms of various accuracy metrics.
PowerNet: Transferable Dynamic IR Drop Estimation via Maximum Convolutional Neural Network
Paper ↗
Abstract
IR drop is a fundamental constraint required by almost all chip designs. However, its evaluation usually takes a long time that hinders mitigation techniques for fixing its violations. In this work, we develop a fast dynamic IR drop estimation technique, named PowerNet, based on a convolutional neural network (CNN). It can handle both vector-based and vectorless IR analyses. Moreover, the proposed CNN model is general and transferable to different designs. This is in contrast to most existing machine learning (ML) approaches, where a model is applicable only to a specific design. Experimental results show that PowerNet outperforms the latest ML method by 9% in accuracy for the challenging case of vectorless IR drop and achieves a 30 times speedup compared to an accurate IR drop commercial tool. Further, a mitigation tool guided by PowerNet reduces IR drop hotspots by 26% and 31% on two industrial designs, respectively, with very limited modification on their power grids.
FIST: A Feature-Importance Sampling and Tree-Based Method for Automatic Design Flow Parameter Tuning
Paper ↗
Abstract
Design flow parameters are of utmost importance to chip design quality and require a painfully long time to evaluate their effects. In reality, flow parameter tuning is usually performed manually based on designers' experience in an ad hoc manner. In this work, we introduce a machine learning-based automatic parameter tuning methodology that aims to find the best design quality with a limited number of trials. Instead of merely plugging in machine learning engines, we develop clustering and approximate sampling techniques for improving tuning efficiency. The feature extraction in this method can reuse knowledge from prior designs. Furthermore, we leverage a state-of-the-art XGBoost model and propose a novel dynamic tree technique to overcome overfitting. Experimental results on benchmark circuits show that our approach achieves 25% improvement in design quality or 37% reduction in sampling cost compared to random forest method, which is the kernel of a highly cited previous work. Our approach is further validated on two industrial designs. By sampling less than 0.02% of possible parameter sets, it reduces area by 1.83% and 1.43% compared to the best solutions hand-tuned by experienced designers.
Fast IR Drop Estimation with Machine Learning
Paper ↗
Abstract
IR drop constraint is a fundamental requirement enforced in almost all chip designs. However, its evaluation takes a long time, and mitigation techniques for fixing violations may require numerous iterations. As such, fast and accurate IR drop prediction becomes critical for reducing design turnaround time. Recently, machine learning (ML) techniques have been actively studied for fast IR drop estimation due to their promise and success in many fields. These studies target at various design stages with different emphasis, and accordingly, different ML algorithms are adopted and customized. This paper provides a review to the latest progress in ML-based IR drop estimation techniques. It also serves as a vehicle for discussing some general challenges faced by ML applications in electronics design automation (EDA), and demonstrating how to integrate ML models with conventional techniques for the better efficiency of EDA tools.
Challenging the Security of Logic Locking Schemes in the Era of Deep Learning: A Neuroevolutionary Approach
Paper ↗
Abstract
Logic locking is a prominent technique to protect the integrity of hardware designs throughout the integrated circuit design and fabrication flow. However, in recent years, the security of locking schemes has been thoroughly challenged by the introduction of various deobfuscation attacks. As in most research branches, deep learning is being introduced in the domain of logic locking as well. Therefore, in this paper we present SnapShot: a novel attack on logic locking that is the first of its kind to utilize artificial neural networks to directly predict a key bit value from a locked synthesized gate-level netlist without using a golden reference. Hereby, the attack uses a simpler yet more flexible learning model compared to existing work. Two different approaches are evaluated. The first approach is based on a simple feedforward fully connected neural network. The second approach utilizes genetic algorithms to evolve more complex convolutional neural network architectures specialized for the given task. The attack flow offers a generic and customizable framework for attacking locking schemes using machine learning techniques. We perform an extensive evaluation of SnapShot for two realistic attack scenarios, comprising both reference benchmark circuits as well as silicon-proven RISC-V core modules. The evaluation results show that SnapShot achieves an average key prediction accuracy of 82.60% for the selected attack scenario, with a significant performance increase of 10.49 percentage points compared to the state of the art. Moreover, SnapShot outperforms the existing technique on all evaluated benchmarks. The results indicate that the security foundation of common logic locking schemes is build on questionable assumptions. The conclusions of the evaluation offer insights into the challenges of designing future logic locking schemes that are resilient to machine learning attacks.
Placement in Integrated Circuits using Cyclic Reinforcement Learning and Simulated Annealing
Paper ↗
Abstract
Physical design and production of Integrated Circuits (IC) is becoming increasingly more challenging as the sophistication in IC technology is steadily increasing. Placement has been one of the most critical steps in IC physical design. Through decades of research, partition-based, analytical-based and annealing-based placers have been enriching the placement solution toolbox. However, open challenges including long run time and lack of ability to generalize continue to restrict wider applications of existing placement tools. We devise a learning-based placement tool based on cyclic application of Reinforcement Learning (RL) and Simulated Annealing (SA) by leveraging the advancement of RL. Results show that the RL module is able to provide a better initialization for SA and thus leads to a better final placement design. Compared to other recent learning-based placers, our method is majorly different with its combination of RL and SA. It leverages the RL model's ability to quickly get a good rough solution after training and the heuristic's ability to realize greedy improvements in the solution.
Fit2Form: 3D Generative Model for Robot Gripper Form Design
Paper ↗
Abstract
The 3D shape of a robot's end-effector plays a critical role in determining it's functionality and overall performance. Many industrial applications rely on task-specific gripper designs to ensure the system's robustness and accuracy. However, the process of manual hardware design is both costly and time-consuming, and the quality of the resulting design is dependent on the engineer's experience and domain expertise, which can easily be out-dated or inaccurate. The goal of this work is to use machine learning algorithms to automate the design of task-specific gripper fingers. We propose Fit2Form, a 3D generative design framework that generates pairs of finger shapes to maximize design objectives (i.e., grasp success, stability, and robustness) for target grasp objects. We model the design objectives by training a Fitness network to predict their values for pairs of gripper fingers and their corresponding grasp objects. This Fitness network then provides supervision to a 3D Generative network that produces a pair of 3D finger geometries for the target grasp object. Our experiments demonstrate that the proposed 3D generative design framework generates parallel jaw gripper finger shapes that achieve more stable and robust grasps compared to other general-purpose and task-specific gripper design algorithms. Video can be found at https://youtu.be/utKHP3qb1bg.
DBA bandits: Self-driving index tuning under ad-hoc, analytical workloads with safety guarantees
Paper ↗
Abstract
Automating physical database design has remained a long-term interest in database research due to substantial performance gains afforded by optimised structures. Despite significant progress, a majority of today's commercial solutions are highly manual, requiring offline invocation by database administrators (DBAs) who are expected to identify and supply representative training workloads. Unfortunately, the latest advancements like query stores provide only limited support for dynamic environments. This status quo is untenable: identifying representative static workloads is no longer realistic; and physical design tools remain susceptible to the query optimiser's cost misestimates (stemming from unrealistic assumptions such as attribute value independence and uniformity of data distribution). We propose a self-driving approach to online index selection that eschews the DBA and query optimiser, and instead learns the benefits of viable structures through strategic exploration and direct performance observation. We view the problem as one of sequential decision making under uncertainty, specifically within the bandit learning setting. Multi-armed bandits balance exploration and exploitation to provably guarantee average performance that converges to a fixed policy that is optimal with perfect hindsight. Our comprehensive empirical results demonstrate up to 75% speed-up on shifting and ad-hoc workloads and 28% speed-up on static workloads compared against a state-of-the-art commercial tuning tool.
Trust-Region Method with Deep Reinforcement Learning in Analog Design Space Exploration
Paper ↗
Abstract
This paper introduces new perspectives on analog design space search. To minimize the time-to-market, this endeavor better cast as constraint satisfaction problem than global optimization defined in prior arts. We incorporate model-based agents, contrasted with model-free learning, to implement a trust-region strategy. As such, simple feed-forward networks can be trained with supervised learning, where the convergence is relatively trivial. Experiment results demonstrate orders of magnitude improvement on search iterations. Additionally, the unprecedented consideration of PVT conditions are accommodated. On circuits with TSMC 5/6nm process, our method achieve performance surpassing human designers. Furthermore, this framework is in production in industrial settings.
DISPATCH: Design Space Exploration of Cyber-Physical Systems
Paper ↗
Abstract
Design of cyber-physical systems (CPSs) is a challenging task that involves searching over a large search space of various CPS configurations and possible values of components composing the system. Hence, there is a need for sample-efficient CPS design space exploration to select the system architecture and component values that meet the target system requirements. We address this challenge by formulating CPS design as a multi-objective optimization problem and propose DISPATCH, a two-step methodology for sample-efficient search over the design space. First, we use a genetic algorithm to search over discrete choices of system component values for architecture search and component selection or only component selection and terminate the algorithm even before meeting the system requirements, thus yielding a coarse design. In the second step, we use an inverse design to search over a continuous space to fine-tune the component values and meet the diverse set of system requirements. We use a neural network as a surrogate function for the inverse design of the system. The neural network, converted into a mixed-integer linear program, is used for active learning to sample component values efficiently in a continuous search space. We illustrate the efficacy of DISPATCH on electrical circuit benchmarks: two-stage and three-stage transimpedence amplifiers. Simulation results show that the proposed methodology improves sample efficiency by 5-14x compared to a prior synthesis method that relies on reinforcement learning. It also synthesizes circuits with the best performance (highest bandwidth/lowest area) compared to designs synthesized using reinforcement learning, Bayesian optimization, or humans.
HL-Pow: A Learning-Based Power Modeling Framework for High-Level Synthesis
Paper ↗
Abstract
High-level synthesis (HLS) enables designers to customize hardware designs efficiently. However, it is still challenging to foresee the correlation between power consumption and HLS-based applications at an early design stage. To overcome this problem, we introduce HL-Pow, a power modeling framework for FPGA HLS based on state-of-the-art machine learning techniques. HL-Pow incorporates an automated feature construction flow to efficiently identify and extract features that exert a major influence on power consumption, simply based upon HLS results, and a modeling flow that can build an accurate and generic power model applicable to a variety of designs with HLS. By using HL-Pow, the power evaluation process for FPGA designs can be significantly expedited because the power inference of HL-Pow is established on HLS instead of the time-consuming register-transfer level (RTL) implementation flow. Experimental results demonstrate that HL-Pow can achieve accurate power modeling that is only 4.67% (24.02 mW) away from onboard power measurement. To further facilitate power-oriented optimizations, we describe a novel design space exploration (DSE) algorithm built on top of HL-Pow to trade off between latency and power consumption. This algorithm can reach a close approximation of the real Pareto frontier while only requiring running HLS flow for 20% of design points in the entire design space.
DAVE: Deriving Automatically Verilog from English
Paper ↗
Abstract
While specifications for digital systems are provided in natural language, engineers undertake significant efforts to translate them into the programming languages understood by compilers for digital systems. Automating this process allows designers to work with the language in which they are most comfortable --the original natural language -- and focus instead on other downstream design challenges. We explore the use of state-of-the-art machine learning (ML) to automatically derive Verilog snippets from English via fine-tuning GPT-2, a natural language ML system. We describe our approach for producing a suitable dataset of novice-level digital design tasks and provide a detailed exploration of GPT-2, finding encouraging translation performance across our task sets (94.8% correct), with the ability to handle both simple and abstract design tasks.
Online Adaptive Learning for Runtime Resource Management of Heterogeneous SoCs
Paper ↗
Abstract
Dynamic resource management has become one of the major areas of research in modern computer and communication system design due to lower power consumption and higher performance demands. The number of integrated cores, level of heterogeneity and amount of control knobs increase steadily. As a result, the system complexity is increasing faster than our ability to optimize and dynamically manage the resources. Moreover, offline approaches are sub-optimal due to workload variations and large volume of new applications unknown at design time. This paper first reviews recent online learning techniques for predicting system performance, power, and temperature. Then, we describe the use of predictive models for online control using two modern approaches: imitation learning (IL) and an explicit nonlinear model predictive control (NMPC). Evaluations on a commercial mobile platform with 16 benchmarks show that the IL approach successfully adapts the control policy to unknown applications. The explicit NMPC provides 25% energy savings compared to a state-of-the-art algorithm for multi-variable power management of modern GPU sub-systems.
Design and analysis of guided modes in photonic waveguides using optical neural network
Paper ↗
Abstract
We present a deep learning approach using an optical neural network to predict the fundamental modal indices $n_{\rm{eff}}$ in a silicon (Si) channel waveguide. We use three inputs, e.g., two geometric parameters and one material property, and predict the $n_{\rm{eff}}$ for the transverse electric and transverse magnetic polarizations. With the least number (i.e., $3^3$ or $4^3$) of exact mode solutions from Maxwell's equations, we can uncover the solutions which correspond to $10^3$ numerical simulations. Note that this consumes the lowest amount of computational resources. The mean squared errors of the exact and the predicted results are $<10^{-5}$. Moreover, our parameters' ranges are compatible with current photolithography and complementary metal-oxide-semiconductor (CMOS) fabrication technology. We also show the impacts of different transfer functions and neural network layouts on the model's performance. Our approach presents a unique advantage to uncover the guided modes in any photonic waveguides within the least possible numerical simulations.
A Machine Learning Pipeline Stage for Adaptive Frequency Adjustment
Paper ↗
Abstract
A machine learning (ML) design framework is proposed for adaptively adjusting clock frequency based on propagation delay of individual instructions. A random forest model is trained to classify propagation delays in real time, utilizing current operation type, current operands, and computation history as ML features. The trained model is implemented in Verilog as an additional pipeline stage within a baseline processor. The modified system is experimentally tested at the gate level in 45 nm CMOS technology, exhibiting a speedup of 70% and energy reduction of 30% with coarse-grained ML classification. A speedup of 89% is demonstrated with finer granularities with 15.5% reduction in energy consumption.
Bayesian Optimization with a Prior for the Optimum
Paper ↗
Abstract
While Bayesian Optimization (BO) is a very popular method for optimizing expensive black-box functions, it fails to leverage the experience of domain experts. This causes BO to waste function evaluations on bad design choices (e.g., machine learning hyperparameters) that the expert already knows to work poorly. To address this issue, we introduce Bayesian Optimization with a Prior for the Optimum (BOPrO). BOPrO allows users to inject their knowledge into the optimization process in the form of priors about which parts of the input space will yield the best performance, rather than BO's standard priors over functions, which are much less intuitive for users. BOPrO then combines these priors with BO's standard probabilistic model to form a pseudo-posterior used to select which points to evaluate next. We show that BOPrO is around 6.67x faster than state-of-the-art methods on a common suite of benchmarks, and achieves a new state-of-the-art performance on a real-world hardware design application. We also show that BOPrO converges faster even if the priors for the optimum are not entirely accurate and that it robustly recovers from misleading priors.
A Unified Learning Platform for Dynamic Frequency Scaling in Pipelined Processors
Paper ↗
Abstract
A machine learning (ML) design framework is proposed for dynamically adjusting clock frequency based on propagation delay of individual instructions. A Random Forest model is trained to classify propagation delays in real-time, utilizing current operation type, current operands, and computation history as ML features. The trained model is implemented in Verilog as an additional pipeline stage within a baseline processor. The modified system is simulated at the gate-level in 45 nm CMOS technology, exhibiting a speed-up of 68% and energy reduction of 37% with coarse-grained ML classification. A speed-up of 95% is demonstrated with finer granularities at additional energy costs.
Automated Design Space Exploration for optimised Deployment of DNN on Arm Cortex-A CPUs
Paper ↗
Abstract
The spread of deep learning on embedded devices has prompted the development of numerous methods to optimise the deployment of deep neural networks (DNN). Works have mainly focused on: i) efficient DNN architectures, ii) network optimisation techniques such as pruning and quantisation, iii) optimised algorithms to speed up the execution of the most computational intensive layers and, iv) dedicated hardware to accelerate the data flow and computation. However, there is a lack of research on cross-level optimisation as the space of approaches becomes too large to test and obtain a globally optimised solution. Thus, leading to suboptimal deployment in terms of latency, accuracy, and memory. In this work, we first detail and analyse the methods to improve the deployment of DNNs across the different levels of software optimisation. Building on this knowledge, we present an automated exploration framework to ease the deployment of DNNs. The framework relies on a Reinforcement Learning search that, combined with a deep learning inference framework, automatically explores the design space and learns an optimised solution that speeds up the performance and reduces the memory on embedded CPU platforms. Thus, we present a set of results for state-of-the-art DNNs on a range of Arm Cortex-A CPU platforms achieving up to 4x improvement in performance and over 2x reduction in memory with negligible loss in accuracy with respect to the BLAS floating-point implementation.
Automated Design Space Exploration for optimised Deployment of DNN on Arm Cortex-A CPUs
Paper ↗
Abstract
The spread of deep learning on embedded devices has prompted the development of numerous methods to optimise the deployment of deep neural networks (DNN). Works have mainly focused on: i) efficient DNN architectures, ii) network optimisation techniques such as pruning and quantisation, iii) optimised algorithms to speed up the execution of the most computational intensive layers and, iv) dedicated hardware to accelerate the data flow and computation. However, there is a lack of research on cross-level optimisation as the space of approaches becomes too large to test and obtain a globally optimised solution. Thus, leading to suboptimal deployment in terms of latency, accuracy, and memory. In this work, we first detail and analyse the methods to improve the deployment of DNNs across the different levels of software optimisation. Building on this knowledge, we present an automated exploration framework to ease the deployment of DNNs. The framework relies on a Reinforcement Learning search that, combined with a deep learning inference framework, automatically explores the design space and learns an optimised solution that speeds up the performance and reduces the memory on embedded CPU platforms. Thus, we present a set of results for state-of-the-art DNNs on a range of Arm Cortex-A CPU platforms achieving up to 4x improvement in performance and over 2x reduction in memory with negligible loss in accuracy with respect to the BLAS floating-point implementation.
Opportunistic Intermittent Control with Safety Guarantees for Autonomous Systems
Paper ↗
Abstract
Control schemes for autonomous systems are often designed in a way that anticipates the worst case in any situation. At runtime, however, there could exist opportunities to leverage the characteristics of specific environment and operation context for more efficient control. In this work, we develop an online intermittent-control framework that combines formal verification with model-based optimization and deep reinforcement learning to opportunistically skip certain control computation and actuation to save actuation energy and computational resources without compromising system safety. Experiments on an adaptive cruise control system demonstrate that our approach can achieve significant energy and computation savings.
PowerPlanningDL: Reliability-Aware Framework for On-Chip Power Grid Design using Deep Learning
Paper ↗
Abstract
With the increase in the complexity of chip designs, VLSI physical design has become a time-consuming task, which is an iterative design process. Power planning is that part of the floorplanning in VLSI physical design where power grid networks are designed in order to provide adequate power to all the underlying functional blocks. Power planning also requires multiple iterative steps to create the power grid network while satisfying the allowed worst-case IR drop and Electromigration (EM) margin. For the first time, this paper introduces Deep learning (DL)-based framework to approximately predict the initial design of the power grid network, considering different reliability constraints. The proposed framework reduces many iterative design steps and speeds up the total design cycle. Neural Network-based multi-target regression technique is used to create the DL model. Feature extraction is done, and the training dataset is generated from the floorplans of some of the power grid designs extracted from the IBM processor. The DL model is trained using the generated dataset. The proposed DL-based framework is validated using a new set of power grid specifications (obtained by perturbing the designs used in the training phase). The results show that the predicted power grid design is closer to the original design with minimal prediction error (~2%). The proposed DL-based approach also improves the design cycle time with a speedup of ~6X for standard power grid benchmarks.
GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning
Paper ↗
Abstract
Automatic transistor sizing is a challenging problem in circuit design due to the large design space, complex performance trade-offs, and fast technological advancements. Although there has been plenty of work on transistor sizing targeting on one circuit, limited research has been done on transferring the knowledge from one circuit to another to reduce the re-design overhead. In this paper, we present GCN-RL Circuit Designer, leveraging reinforcement learning (RL) to transfer the knowledge between different technology nodes and topologies. Moreover, inspired by the simple fact that circuit is a graph, we learn on the circuit topology representation with graph convolutional neural networks (GCN). The GCN-RL agent extracts features of the topology graph whose vertices are transistors, edges are wires. Our learning-based optimization consistently achieves the highest Figures of Merit (FoM) on four different circuits compared with conventional black-box optimization methods (Bayesian Optimization, Evolutionary Algorithms), random search, and human expert designs. Experiments on transfer learning between five technology nodes and two circuit topologies demonstrate that RL with transfer learning can achieve much higher FoMs than methods without knowledge transfer. Our transferable optimization method makes transistor sizing and design porting more effective and efficient.
Bias Busters: Robustifying DL-based Lithographic Hotspot Detectors Against Backdooring Attacks
Paper ↗
Abstract
Deep learning (DL) offers potential improvements throughout the CAD tool-flow, one promising application being lithographic hotspot detection. However, DL techniques have been shown to be especially vulnerable to inference and training time adversarial attacks. Recent work has demonstrated that a small fraction of malicious physical designers can stealthily "backdoor" a DL-based hotspot detector during its training phase such that it accurately classifies regular layout clips but predicts hotspots containing a specially crafted trigger shape as non-hotspots. We propose a novel training data augmentation strategy as a powerful defense against such backdooring attacks. The defense works by eliminating the intentional biases introduced in the training data but does not require knowledge of which training samples are poisoned or the nature of the backdoor trigger. Our results show that the defense can drastically reduce the attack success rate from 84% to ~0%.
ApproxFPGAs: Embracing ASIC-Based Approximate Arithmetic Components for FPGA-Based Systems
Paper ↗
Abstract
There has been abundant research on the development of Approximate Circuits (ACs) for ASICs. However, previous studies have illustrated that ASIC-based ACs offer asymmetrical gains in FPGA-based accelerators. Therefore, an AC that might be pareto-optimal for ASICs might not be pareto-optimal for FPGAs. In this work, we present the ApproxFPGAs methodology that uses machine learning models to reduce the exploration time for analyzing the state-of-the-art ASIC-based ACs to determine the set of pareto-optimal FPGA-based ACs. We also perform a case-study to illustrate the benefits obtained by deploying these pareto-optimal FPGA-based ACs in a state-of-the-art automation framework to systematically generate pareto-optimal approximate accelerators that can be deployed in FPGA-based systems to achieve high performance or low-power consumption.
Attention Routing: track-assignment detailed routing using attention-based reinforcement learning
Paper ↗
Abstract
In the physical design of integrated circuits, global and detailed routing are critical stages involving the determination of the interconnected paths of each net on a circuit while satisfying the design constraints. Existing actual routers as well as routability predictors either have to resort to expensive approaches that lead to high computational times, or use heuristics that do not generalize well. Even though new, learning-based routing methods have been proposed to address this need, requirements on labelled data and difficulties in addressing complex design rule constraints have limited their adoption in advanced technology node physical design problems. In this work, we propose a new router: attention router, which is the first attempt to solve the track-assignment detailed routing problem using reinforcement learning. Complex design rule constraints are encoded into the routing algorithm and an attention-model-based REINFORCE algorithm is applied to solve the most critical step in routing: sequencing device pairs to be routed. The attention router and its baseline genetic router are applied to solve different commercial advanced technologies analog circuits problem sets. The attention router demonstrates generalization ability to unseen problems and is also able to achieve more than 100 times acceleration over the genetic router without significantly compromising the routing solution quality. We also discover a similarity between the attention router and the baseline genetic router in terms of positive correlations in cost and routing patterns, which demonstrate the attention router's ability to be utilized not only as a detailed router but also as a predictor for routability and congestion.
Placement Optimization with Deep Reinforcement Learning
Paper ↗
Abstract
Placement Optimization is an important problem in systems and chip design, which consists of mapping the nodes of a graph onto a limited set of resources to optimize for an objective, subject to constraints. In this paper, we start by motivating reinforcement learning as a solution to the placement problem. We then give an overview of what deep reinforcement learning is. We next formulate the placement problem as a reinforcement learning problem and show how this problem can be solved with policy gradient optimization. Finally, we describe lessons we have learned from training deep reinforcement learning policies across a variety of placement optimization problems.
GENIEx: A Generalized Approach to Emulating Non-Ideality in Memristive Xbars using Neural Networks
Paper ↗
Abstract
The analog nature of computing in Memristive crossbars poses significant issues due to various non-idealities such as: parasitic resistances, non-linear I-V characteristics of the device etc. The non-idealities can have a detrimental impact on the functionality i.e. computational accuracy of crossbars. Past works have explored modeling the non-idealities using analytical techniques. However, several non-idealities have data dependent behavior. This can not be captured using analytical (non data-dependent) models thereby, limiting their suitability in predicting application accuracy. To address this, we propose a Generalized Approach to Emulating Non-Ideality in Memristive Crossbars using Neural Networks (GENIEx), which accurately captures the data-dependent nature of non-idealities. We perform extensive HSPICE simulations of crossbars with different voltage and conductance combinations. Following that, we train a neural network to learn the transfer characteristics of the non-ideal crossbar. Next, we build a functional simulator which includes key architectural facets such as \textit{tiling}, and \textit{bit-slicing} to analyze the impact of non-idealities on the classification accuracy of large-scale neural networks. We show that GENIEx achieves \textit{low} root mean square errors (RMSE) of $0.25$ and $0.7$ for low and high voltages, respectively, compared to HSPICE. Additionally, the GENIEx errors are $7\times$ and $12.8\times$ better than an analytical model which can only capture the linear non-idealities. Further, using the functional simulator and GENIEx, we demonstrate that an analytical model can overestimate the degradation in classification accuracy by $\ge 10\%$ on CIFAR-100 and $3.7\%$ on ImageNet datasets compared to GENIEx.
AutoCkt: Deep Reinforcement Learning of Analog Circuit Designs
Paper ↗
Abstract
Domain specialization under energy constraints in deeply-scaled CMOS has been driving the need for agile development of Systems on a Chip (SoCs). While digital subsystems have design flows that are conducive to rapid iterations from specification to layout, analog and mixed-signal modules face the challenge of a long human-in-the-middle iteration loop that requires expert intuition to verify that post-layout circuit parameters meet the original design specification. Existing automated solutions that optimize circuit parameters for a given target design specification have limitations of being schematic-only, inaccurate, sample-inefficient or not generalizable. This work presents AutoCkt, a machine learning optimization framework trained using deep reinforcement learning that not only finds post-layout circuit parameters for a given target specification, but also gains knowledge about the entire design space through a sparse subsampling technique. Our results show that for multiple circuit topologies, AutoCkt is able to converge and meet all target specifications on at least 96.3% of tested design goals in schematic simulation, on average 40X faster than a traditional genetic algorithm. Using the Berkeley Analog Generator, AutoCkt is able to design 40 LVS passed operational amplifiers in 68 hours, 9.6X faster than the state-of-the-art when considering layout parasitics.
VLSI Mask Optimization: From Shallow To Deep Learning
Paper ↗
Abstract
VLSI mask optimization is one of the most critical stages in manufacturability aware design, which is costly due to the complicated mask optimization and lithography simulation. Recent researches have shown prominent advantages of machine learning techniques dealing with complicated and big data problems, which bring potential of dedicated machine learning solution for DFM problems and facilitate the VLSI design cycle. In this paper, we focus on a heterogeneous OPC framework that assists mask layout optimization. Preliminary results show the efficiency and effectiveness of proposed frameworks that have the potential to be alternatives to existing EDA solutions.
Bayesian Optimization Approach for Analog Circuit Synthesis Using Neural Network
Paper ↗
Abstract
Bayesian optimization with Gaussian process as surrogate model has been successfully applied to analog circuit synthesis. In the traditional Gaussian process regression model, the kernel functions are defined explicitly. The computational complexity of training is O(N 3 ), and the computation complexity of prediction is O(N 2 ), where N is the number of training data. Gaussian process model can also be derived from a weight space view, where the original data are mapped to feature space, and the kernel function is defined as the inner product of nonlinear features. In this paper, we propose a Bayesian optimization approach for analog circuit synthesis using neural network. We use deep neural network to extract good feature representations, and then define Gaussian process using the extracted features. Model averaging method is applied to improve the quality of uncertainty prediction. Compared to Gaussian process model with explicitly defined kernel functions, the neural-network-based Gaussian process model can automatically learn a kernel function from data, which makes it possible to provide more accurate predictions and thus accelerate the follow-up optimization procedure. Also, the neural-network-based model has O(N) training time and constant prediction time. The efficiency of the proposed method has been verified by two real-world analog circuits.
DRiLLS: Deep Reinforcement Learning for Logic Synthesis
Paper ↗
Abstract
Logic synthesis requires extensive tuning of the synthesis optimization flow where the quality of results (QoR) depends on the sequence of optimizations used. Efficient design space exploration is challenging due to the exponential number of possible optimization permutations. Therefore, automating the optimization process is necessary. In this work, we propose a novel reinforcement learning-based methodology that navigates the optimization space without human intervention. We demonstrate the training of an Advantage Actor Critic (A2C) agent that seeks to minimize area subject to a timing constraint. Using the proposed methodology, designs can be optimized autonomously with no-humans in-loop. Evaluation on the comprehensive EPFL benchmark suite shows that the agent outperforms existing exploration methodologies and improves QoRs by an average of 13%.
Optimizing Design Verification using Machine Learning: Doing better than Random
Paper ↗
Abstract
As integrated circuits have become progressively more complex, constrained random stimulus has become ubiquitous as a means of stimulating a designs functionality and ensuring it fully meets expectations. In theory, random stimulus allows all possible combinations to be exercised given enough time, but in practice with highly complex designs a purely random approach will have difficulty in exercising all possible combinations in a timely fashion. As a result it is often necessary to steer the Design Verification (DV) environment to generate hard to hit combinations. The resulting constrained-random approach is powerful but often relies on extensive human expertise to guide the DV environment in order to fully exercise the design. As designs become more complex, the guidance aspect becomes progressively more challenging and time consuming often resulting in design schedules in which the verification time to hit all possible design coverage points is the dominant schedule limitation. This paper describes an approach which leverages existing constrained-random DV environment tools but which further enhances them using supervised learning and reinforcement learning techniques. This approach provides better than random results in a highly automated fashion thereby ensuring DV objectives of full design coverage can be achieved on an accelerated timescale and with fewer resources. Two hardware verification examples are presented, one of a Cache Controller design and one using the open-source RISCV-Ariane design and Google's RISCV Random Instruction Generator. We demonstrate that a machine-learning based approach can perform significantly better on functional coverage and reaching complex hard-to-hit states than a random or constrained-random approach.
Pyramid: Machine Learning Framework to Estimate the Optimal Timing and Resource Usage of a High-Level Synthesis Design
Paper ↗
Abstract
The emergence of High-Level Synthesis (HLS) tools shifted the paradigm of hardware design by making the process of mapping high-level programming languages to hardware design such as C to VHDL/Verilog feasible. HLS tools offer a plethora of techniques to optimize designs for both area and performance, but resource usage and timing reports of HLS tools mostly deviate from the post-implementation results. In addition, to evaluate a hardware design performance, it is critical to determine the maximum achievable clock frequency. Obtaining such information using static timing analysis provided by CAD tools is difficult, due to the multitude of tool options. Moreover, a binary search to find the maximum frequency is tedious, time-consuming, and often does not obtain the optimal result. To address these challenges, we propose a framework, called Pyramid, that uses machine learning to accurately estimate the optimal performance and resource utilization of an HLS design. For this purpose, we first create a database of C-to-FPGA results from a diverse set of benchmarks. To find the achievable maximum clock frequency, we use Minerva, which is an automated hardware optimization tool. Minerva determines the close-to-optimal settings of tools, using static timing analysis and a heuristic algorithm, and targets either optimal throughput or throughput-to-area. Pyramid uses the database to train an ensemble machine learning model to map the HLS-reported features to the results of Minerva. To this end, Pyramid re-calibrates the results of HLS to bridge the accuracy gap and enable developers to estimate the throughput or throughput-to-area of hardware design with more than 95% accuracy and alleviates the need to perform actual implementation for estimation.
Adaptive Predictive Power Management for Mobile LTE Devices
Paper ↗
Abstract
Reducing the energy consumption of mobile phones is a crucial design goal for cellular modem solutions for LTE and 5G standards. In addition to improving the power efficiency of components through structural and technological advances, optimizing the energy efficiency through improved dynamic power management is an integral part in contemporary hardware design. Most techniques targeting mobile devices proposed so far, however, are purely reactive in powering down and up system components. Promising approaches extend this, by predicting and using information from the environment and the communication protocol to take proactive decisions. In this paper, we propose and compare two proactive algorithmic approaches for light-weight machine learning to predict the control information needed to allow a mobile device to go to sleep states more often, e.g., in time slots of transmission inactivity in a cell. The first approach is based on supervised learning, the second one based on reinforcement learning. As the implementation of learning techniques also creates energy and resource costs, both approaches are carefully evaluated not only in terms of prediction accuracy, but also overall energy savings. Using the presented technique, we observe achievable energy savings of up to 17%.
iVAMS 2.0: Machine-Learning-Metamodel-Integrated Intelligent Verilog-AMS for Fast and Accurate Mixed-Signal Design Optimization
Paper ↗
Abstract
The gap between abstraction levels in analog design is a major obstacle for advancing analog and mixed-signal (AMS) design automation and computer-aided design (CAD). Intelligent models for low-level analog building blocks are needed to bridge the accuracy gap between behavioral and transistor-level simulations. The models should be able to accurately estimate the characteristics of the analog block over a large design space. Machine learning (ML) models based on actual silicon have the capabilities of capturing detailed characteristics of complex designs. In this paper, a ML model called Artificial Neural Network Metamodels (ANNM) have been explored to capture the highly nonlinear nature of analog blocks. The application of these intelligent models to multi-objective AMS block optimization is demonstrated. Parameterized behavioral models in Verilog-AMS based on the ANN metamodels are constructed for efficient AMS design exploration. To the best of the authors' knowledge this is the first paper to integrate ANN models in Verilog-AMS, which is called iVAMS 2.0. To demonstrate the application of iVAMS 2.0, this paper presents two case studies: an operational amplifier (OP-AMP) and a phase-locked loop (PLL). A biologically-inspired "firefly optimization algorithm" is applied to an OP-AMP design in the iVAMS 2.0 framework. The optimization process is sped up by 5580X due to the use of iVAMS with negligible loss in accuracy. Similarly, for a PLL design, the physical design aware ANNs are trained and used as metamodels to predict its frequency, locking time, and power. Thorough experimental results demonstrate that only 100 sample points are sufficient for ANNs to predict the output of circuits with 21 design parameters within 3% accuracy. A proposed artificial bee colony (ABC) based algorithm performs optimization over the ANN metamodels of the PLL.
Machine Learning Based Routing Congestion Prediction in FPGA High-Level Synthesis
Paper ↗
Abstract
High-level synthesis (HLS) shortens the development time of hardware designs and enables faster design space exploration at a higher abstraction level. Optimization of complex applications in HLS is challenging due to the effects of implementation issues such as routing congestion. Routing congestion estimation is absent or inaccurate in existing HLS design methods and tools. Early and accurate congestion estimation is of great benefit to guide the optimization in HLS and improve the efficiency of implementation. However, routability, a serious concern in FPGA designs, has been difficult to evaluate in HLS without analyzing post-implementation details after Place and Route. To this end, we propose a novel method to predict routing congestion in HLS using machine learning and map the expected congested regions in the design to the relevant high-level source code. This is greatly beneficial in early identification of routability oriented bottlenecks in the high-level source code without running time-consuming register-transfer level (RTL) implementation flow. Experiments demonstrate that our approach accurately estimates vertical and horizontal routing congestion with errors of 6.71% and 10.05% respectively. By presenting Face Detection application as a case study, we show that by discovering the bottlenecks in high-level source code, routing congestion can be easily and quickly resolved compared to the efforts involved in RTL implementation and design feedback.
Painting on Placement: Forecasting Routing Congestion using Conditional Generative Adversarial Nets
Paper ↗
Abstract
Physical design process commonly consumes hours to days for large designs, and routing is known as the most critical step. Demands for accurate routing quality prediction raise to a new level to accelerate hardware innovation with advanced technology nodes. This work presents an approach that forecasts the density of all routing channels over the entire floorplan, with features collected up to placement, using conditional GANs. Specifically, forecasting the routing congestion is constructed as an image translation (colorization) problem. The proposed approach is applied to a) placement exploration for minimum congestion, b) constrained placement exploration and c) forecasting congestion in real-time during incremental placement, using eight designs targeting a fixed FPGA architecture.
Automated Circuit Approximation Method Driven by Data Distribution
Paper ↗
Abstract
We propose an application-tailored data-driven fully automated method for functional approximation of combinational circuits. We demonstrate how an application-level error metric such as the classification accuracy can be translated to a component-level error metric needed for an efficient and fast search in the space of approximate low-level components that are used in the application. This is possible by employing a weighted mean error distance (WMED) metric for steering the circuit approximation process which is conducted by means of genetic programming. WMED introduces a set of weights (calculated from the data distribution measured on a selected signal in a given application) determining the importance of each input vector for the approximation process. The method is evaluated using synthetic benchmarks and application-specific approximate MAC (multiply-and-accumulate) units that are designed to provide the best trade-offs between the classification accuracy and power consumption of two image classifiers based on neural networks.
Coloring Big Graphs with AlphaGoZero
Paper ↗
Abstract
We show that recent innovations in deep reinforcement learning can effectively color very large graphs -- a well-known NP-hard problem with clear commercial applications. Because the Monte Carlo Tree Search with Upper Confidence Bound algorithm used in AlphaGoZero can improve the performance of a given heuristic, our approach allows deep neural networks trained using high performance computing (HPC) technologies to transform computation into improved heuristics with zero prior knowledge. Key to our approach is the introduction of a novel deep neural network architecture (FastColorNet) that has access to the full graph context and requires $O(V)$ time and space to color a graph with $V$ vertices, which enables scaling to very large graphs that arise in real applications like parallel computing, compilers, numerical solvers, and design automation, among others. As a result, we are able to learn new state of the art heuristics for graph coloring.
autoAx: An Automatic Design Space Exploration and Circuit Building Methodology utilizing Libraries of Approximate Components
Paper ↗
Abstract
Approximate computing is an emerging paradigm for developing highly energy-efficient computing systems such as various accelerators. In the literature, many libraries of elementary approximate circuits have already been proposed to simplify the design process of approximate accelerators. Because these libraries contain from tens to thousands of approximate implementations for a single arithmetic operation it is intractable to find an optimal combination of approximate circuits in the library even for an application consisting of a few operations. An open problem is "how to effectively combine circuits from these libraries to construct complex approximate accelerators". This paper proposes a novel methodology for searching, selecting and combining the most suitable approximate circuits from a set of available libraries to generate an approximate accelerator for a given application. To enable fast design space generation and exploration, the methodology utilizes machine learning techniques to create computational models estimating the overall quality of processing and hardware cost without performing full synthesis at the accelerator level. Using the methodology, we construct hundreds of approximate accelerators (for a Sobel edge detector) showing different but relevant tradeoffs between the quality of processing and hardware cost and identify a corresponding Pareto-frontier. Furthermore, when searching for approximate implementations of a generic Gaussian filter consisting of 17 arithmetic operations, the proposed approach allows us to identify approximately $10^3$ highly important implementations from $10^{23}$ possible solutions in a few hours, while the exhaustive search would take four months on a high-end processor.
Estimating the Circuit Deobfuscating Runtime based on Graph Deep Learning
Paper ↗
Abstract
Circuit obfuscation is a recently proposed defense mechanism to protect digital integrated circuits (ICs) from reverse engineering by using camouflaged gates i.e., logic gates whose functionality cannot be precisely determined by the attacker. There have been effective schemes such as satisfiability-checking (SAT)-based attacks that can potentially decrypt obfuscated circuits, called deobfuscation. Deobfuscation runtime could have a large span ranging from few milliseconds to thousands of years or more, depending on the number and layouts of the ICs and camouflaged gates. And hence accurately pre-estimating the deobfuscation runtime is highly crucial for the defenders to maximize it and optimize their defense. However, estimating the deobfuscation runtime is a challenging task due to 1) the complexity and heterogeneity of graph-structured circuit, 2) the unknown and sophisticated mechanisms of the attackers for deobfuscation. To address the above mentioned challenges, this work proposes the first machine-learning framework that predicts the deobfuscation runtime based on graph deep learning techniques. Specifically, we design a new model, ICNet with new input and convolution layers to characterize and extract graph frequencies from ICs, which are then integrated by heterogeneous deep fully-connected layers to obtain final output. ICNet is an end-to-end framework which can automatically extract the determinant features for deobfuscation runtime. Extensive experiments demonstrate its effectiveness and efficiency.
Predictive Indexing
Paper ↗
Abstract
There has been considerable research on automated index tuning in database management systems (DBMSs). But the majority of these solutions tune the index configuration by retrospectively making computationally expensive physical design changes all at once. Such changes degrade the DBMS's performance during the process, and have reduced utility during subsequent query processing due to the delay between a workload shift and the associated change. A better approach is to generate small changes that tune the physical design over time, forecast the utility of these changes, and apply them ahead of time to maximize their impact. This paper presents predictive indexing that continuously improves a database's physical design using lightweight physical design changes. It uses a machine learning model to forecast the utility of these changes, and continuously refines the index configuration of the database to handle evolving workloads. We introduce a lightweight hybrid scan operator with which a DBMS can make use of partially-built indexes for query processing. Our evaluation shows that predictive indexing improves the throughput of a DBMS by 3.5--5.2x compared to other state-of-the-art indexing approaches. We demonstrate that predictive indexing works seamlessly with other lightweight automated physical design tuning methods.
Design Rule Violation Hotspot Prediction Based on Neural Network Ensembles
Paper ↗
Abstract
Design rule check is a critical step in the physical design of integrated circuits to ensure manufacturability. However, it can be done only after a time-consuming detailed routing procedure, which adds drastically to the time of design iterations. With advanced technology nodes, the outcomes of global routing and detailed routing become less correlated, which adds to the difficulty of predicting design rule violations from earlier stages. In this paper, a framework based on neural network ensembles is proposed to predict design rule violation hotspots using information from placement and global routing. A soft voting structure and a PCA-based subset selection scheme are developed on top of a baseline neural network from a recent work. Experimental results show that the proposed architecture achieves significant improvement in model performance compared to the baseline case. For half of test cases, the performance is even better than random forest, a commonly-used ensemble learning model.
Learning-based Application-Agnostic 3D NoC Design for Heterogeneous Manycore Systems
Paper ↗
Abstract
The rising use of deep learning and other big-data algorithms has led to an increasing demand for hardware platforms that are computationally powerful, yet energy-efficient. Due to the amount of data parallelism in these algorithms, high-performance 3D manycore platforms that incorporate both CPUs and GPUs present a promising direction. However, as systems use heterogeneity (e.g., a combination of CPUs, GPUs, and accelerators) to improve performance and efficiency, it becomes more pertinent to address the distinct and likely conflicting communication requirements (e.g., CPU memory access latency or GPU network throughput) that arise from such heterogeneity. Unfortunately, it is difficult to quickly explore the hardware design space and choose appropriate tradeoffs between these heterogeneous requirements. To address these challenges, we propose the design of a 3D Network-on-Chip (NoC) for heterogeneous manycore platforms that considers the appropriate design objectives for a 3D heterogeneous system and explores various tradeoffs using an efficient ML-based multi-objective optimization technique. The proposed design space exploration considers the various requirements of its heterogeneous components and generates a set of 3D NoC architectures that efficiently trades off these design objectives. Our findings show that by jointly considering these requirements (latency, throughput, temperature, and energy), we can achieve 9.6% better Energy-Delay Product on average at nearly iso-temperature conditions when compared to a thermally-optimized design for 3D heterogeneous NoCs. More importantly, our results suggest that our 3D NoCs optimized for a few applications can be generalized for unknown applications as well. Our results show that these generalized 3D NoCs only incur a 1.8% (36-tile system) and 1.1% (64-tile system) average performance loss compared to application-specific NoCs.
Practical Design Space Exploration
Paper ↗
Abstract
Multi-objective optimization is a crucial matter in computer systems design space exploration because real-world applications often rely on a trade-off between several objectives. Derivatives are usually not available or impractical to compute and the feasibility of an experiment can not always be determined in advance. These problems are particularly difficult when the feasible region is relatively small, and it may be prohibitive to even find a feasible experiment, let alone an optimal one. We introduce a new methodology and corresponding software framework, HyperMapper 2.0, which handles multi-objective optimization, unknown feasibility constraints, and categorical/ordinal variables. This new methodology also supports injection of the user prior knowledge in the search when available. All of these features are common requirements in computer systems but rarely exposed in existing design space exploration systems. The proposed methodology follows a white-box model which is simple to understand and interpret (unlike, for example, neural networks) and can be used by the user to better understand the results of the automatic search. We apply and evaluate the new methodology to the automatic static tuning of hardware accelerators within the recently introduced Spatial programming language, with minimization of design run-time and compute logic under the constraint of the design fitting in a target field-programmable gate array chip. Our results show that HyperMapper 2.0 provides better Pareto fronts compared to state-of-the-art baselines, with better or competitive hypervolume indicator and with 8x improvement in sampling budget for most of the benchmarks explored.
Context-Aware DFM Rule Analysis and Scoring Using Machine Learning
Paper ↗
Abstract
To evaluate the quality of physical layout designs in terms of manufacturability, DFM rule scoring techniques have been widely used in physical design and physical verification phases. However, one major drawback of conventional DFM rule scoring methodologies is that resultant DFM rule scores may not accurate since the scores may not highly correspond to lithography simulation results. For instance, conventional DFM rule scoring methodologies usually use rule-based techniques to compute scores without considering neighboring geometric scenarios of targeted layout shapes. That can lead to inaccurate scoring results since computed DFM rule scores can be either too optimistic or too pessimistic. Therefore, in this paper, we propose a novel approach with the use of machine learning technology to analyze the context of targeted layouts and predict their lithography impacts on manufacturability.
Cross-layer Optimization for High Speed Adders: A Pareto Driven Machine Learning Approach
Paper ↗
Abstract
In spite of maturity to the modern electronic design automation (EDA) tools, optimized designs at architectural stage may become sub-optimal after going through physical design flow. Adder design has been such a long studied fundamental problem in VLSI industry yet designers cannot achieve optimal solutions by running EDA tools on the set of available prefix adder architectures. In this paper, we enhance a state-of-the-art prefix adder synthesis algorithm to obtain a much wider solution space in architectural domain. On top of that, a machine learning-based design space exploration methodology is applied to predict the Pareto frontier of the adders in physical domain, which is infeasible by exhaustively running EDA tools for innumerable architectural solutions. Considering the high cost of obtaining the true values for learning, an active learning algorithm is utilized to select the representative data during learning process, which uses less labeled data while achieving better quality of Pareto frontier. Experimental results demonstrate that our framework can achieve Pareto frontier of high quality over a wide design space, bridging the gap between architectural and physical designs.
Developing Synthesis Flows Without Human Knowledge
Paper ↗
Abstract
Design flows are the explicit combinations of design transformations, primarily involved in synthesis, placement and routing processes, to accomplish the design of Integrated Circuits (ICs) and System-on-Chip (SoC). Mostly, the flows are developed based on the knowledge of the experts. However, due to the large search space of design flows and the increasing design complexity, developing Intellectual Property (IP)-specific synthesis flows providing high Quality of Result (QoR) is extremely challenging. This work presents a fully autonomous framework that artificially produces design-specific synthesis flows without human guidance and baseline flows, using Convolutional Neural Network (CNN). The demonstrations are made by successfully designing logic synthesis flows of three large scaled designs.
A Machine Learning Framework for Register Placement Optimization in Digital Circuit Design
Paper ↗
Abstract
In modern digital circuit back-end design, designers heavily rely on electronic-design-automoation (EDA) tool to close timing. However, the heuristic algorithms used in the place and route tool usually does not result in optimal solution. Thus, significant design effort is used to tune parameters or provide user constraints or guidelines to improve the tool performance. In this paper, we targeted at those optimization space left behind by the EDA tools and propose a machine learning framework that helps to define what are the guidelines and constraints for registers placement, which can yield better performance and quality for back-end design. In other words, the framework is trying to learn what are the flaws of the existing EDA tools and tries to optimize it by providing additional information. We discuss what is the proper input feature vector to be extracted, and what is metric to be used for reference output. We also develop a scheme to generate perturbed training samples using existing design based on Gaussian randomization. By applying our methodology, we are able to improve the design runtime by up to 36% and timing quality by up to 23%.
Customized Routing Optimization Based on Gradient Boost Regressor Model
Paper ↗
Abstract
In this paper, we discussed limitation of current electronic-design-automoation (EDA) tool and proposed a machine learning framework to overcome the limitations and achieve better design quality. We explored how to efficiently extract relevant features and leverage gradient boost regressor (GBR) model to predict underestimated risky net (URN). Customized routing optimizations are applied to the URNs and results show clear timing improvement and trend to converge toward timing closure.
Design-Space Exploration and Optimization of an Energy-Efficient and Reliable 3D Small-world Network-on-Chip
Paper ↗
Abstract
A three-dimensional (3D) Network-on-Chip (NoC) enables the design of high performance and low power many-core chips. Existing 3D NoCs are inadequate for meeting the ever-increasing performance requirements of many-core processors since they are simple extensions of regular 2D architectures and they do not fully exploit the advantages provided by 3D integration. Moreover, the anticipated performance gain of a 3D NoC-enabled many-core chip may be compromised due to the potential failures of through-silicon-vias (TSVs) that are predominantly used as vertical interconnects in a 3D IC. To address these problems, we propose a machine-learning-inspired predictive design methodology for energy-efficient and reliable many-core architectures enabled by 3D integration. We demonstrate that a small-world network-based 3D NoC (3D SWNoC) performs significantly better than its 3D MESH-based counterparts. On average, the 3D SWNoC shows 35% energy-delay-product (EDP) improvement over 3D MESH for the PARSEC and SPLASH2 benchmarks considered in this work. To improve the reliability of 3D NoC, we propose a computationally efficient spare-vertical link (sVL) allocation algorithm based on a state-space search formulation. Our results show that the proposed sVL allocation algorithm can significantly improve the reliability as well as the lifetime of 3D SWNoC.
Supervised quantum gate "teaching" for quantum hardware design
Paper ↗
Abstract
We show how to train a quantum network of pairwise interacting qubits such that its evolution implements a target quantum algorithm into a given network subset. Our strategy is inspired by supervised learning and is designed to help the physical construction of a quantum computer which operates with minimal external classical control.
Lithography Hotspot Detection and Mitigation in Nanometer VLSI
Paper ↗
Abstract
With continued feature size scaling, even state of the art semiconductor manufacturing processes will often run into layouts with poor printability and yield. Identifying lithography hotspots is important at both physical verification and early physical design stages. While detailed lithography simulations can be very accurate, they may be too computationally expensive for full-chip scale and physical design inner loops. Meanwhile, pattern matching and machine learning based hotspot detection methods can provide acceptable quality and yet fast turn-around-time for full-chip scale physical verification and design. In this paper, we discuss some key issues and recent results on lithography hotspot detection and mitigation in nanometer VLSI.
EPIC: Efficient prediction of IC manufacturing hotspots with a unified meta-classification formulation
Paper ↗
Abstract
In this paper we present EPIC, an efficient and effective predictor for IC manufacturing hotspots in deep sub-wavelength lithography. EPIC proposes a unified framework to combine different hotspot detection methods together, such as machine learning and pattern matching, using mathematical programming/optimization. EPIC algorithm has been tested on a number of industry benchmarks under advanced manufacturing conditions. It demonstrates so far the best capability in selectively combining the desirable features of various hotspot detection methods (3.5-8.2% accuracy improvement) as well as significant suppression of the detection noise (e.g., 80% false-alarm reduction). These characteristics make EPIC very suitable for conducting high performance physical verification and guiding efficient manufacturability friendly physical design.
Specification Test Compaction for Analog Circuits and MEMS
Paper ↗
Abstract
Testing a non-digital integrated system against all of its specifications can be quite expensive due to the elaborate test application and measurement setup required. We propose to eliminate redundant tests by employing e-SVM based statistical learning. Application of the proposed methodology to an operational amplifier and a MEMS accelerometer reveal that redundant tests can be statistically identified from a complete set of specification-based tests with negligible error. Specifically, after eliminating five of eleven specification-based tests for an operational amplifier, the defect escape and yield loss is small at 0.6% and 0.9%, respectively. For the accelerometer, defect escape of 0.2% and yield loss of 0.1% occurs when the hot and colt tests are eliminated. For the accelerometer, this level of Compaction would reduce test cost by more than half.