Course Syllabus
Learning Objectives
By the end of this course, students will be able to:
- Build AI agents that can automatically design computer architectures across different abstraction levels
- Implement reinforcement learning and neural network approaches for architecture optimization
- Evaluate AI-driven design methodologies and compare them to traditional heuristic approaches
- Identify promising research directions in AI-agent-driven architecture design
- Develop tools and frameworks for automated architecture exploration and optimization
Course Structure
This is a research paper reading seminar exploring AI agents across three thematic areas:
- AI for Software: Software optimization and compilation
- AI for Architecture: Hardware design and system architecture
- AI for EDA: Physical implementation and chip design
See the Schedule for detailed weekly topics and readings.
Assignments & Grading
Paper Reading & Reflection (40%)
- Weekly 1-2 page reflections on assigned papers
- Due before each class session
- Focus on critical analysis and connections to course themes
Labs & Projects (40%)
- Hands-on assignments with tools like ArchGym, DREAMPlace, CompilerGym
- All projects contribute components to GenAISys - a unified modular agentic framework
- Progressive assignments building toward integrated final system
Discussion Leadership (20%)
- Each student leads discussion for 1-2 sessions during the semester
- Prepare questions, facilitate debate, synthesize insights
- Sign up by Week 3
Course Policies
Attendance
Regular attendance essential for discussion-based seminar. More than two unexcused absences may result in grade reduction.
Late Work
Reading reflections submitted late receive reduced credit. Extensions for major assignments require advance notice.
Academic Integrity
All work must be original with proper citation. Collaboration encouraged for labs but individual work expected for reflections and final project.
Required Materials
- All readings provided via course website
- Access to academic databases (ACM Digital Library, IEEE Xplore)
- Laptop for hands-on activities
This syllabus may be adjusted based on emerging research and student interests. Changes will be announced in advance.