WorkLatencyGapScenario
Optimization scenarios · Implementation: mlsysim/engine/scenario_definitions/optimization.py.
Construct this scenario with keyword inputs. The fields below show the types and defaults declared by this class.
A cut in work (parameters or FLOPs) against the latency cut it delivered.
Notes
Equation: delivered_share is the worked quantity; each property below states its equation and units.
Assumptions: Both supplied reductions refer to the same workload and baseline, with nonzero work reduction.
Excludes: Causal attribution or a universal relation between FLOPs and latency.
References
Derivation: The equations below follow the stated counts, geometric relations, or accounting definitions; scenario inputs are supplied assumptions or observations, not fitted predictions.
Examples
Execute the registered worked inputs; this is a modeled calculation.
>>> from mlsysim import Scenarios
>>> case = Scenarios.IrregularSparsityLatencyTrace
>>> value = case.delivered_share
>>> round(value, 3)
0.3Attributes
| Name | Description |
|---|---|
| delivered_share | Dimensionless latency-cut share of the supplied work reduction. |
| latency_reduction | |
| work_reduction |
work_reduction
Type: float.
Declared default: required.
latency_reduction
Type: float.
Declared default: required.