mirror of
https://github.com/harvard-edge/cs249r_book.git
synced 2026-07-22 12:12:39 -05:00
Vijay Janapa Reddi
cb0ae4082f
Run quartodoc build against the refactored package (engine/ extracted from core/, infra->infrastructure): regenerate the API reference so every stub points at the new paths. Adds engine.*/infrastructure.* stubs, removes the 41 stale core.solver.* / core.engine.* / core.scenarios.* / core.config.* / core.evaluation.* / infra*.qmd orphans, and refreshes the package pages (core now primitives-only) + index. Verified: all 47 documented symbols resolve in the new package; every index link resolves; zero stale mlsysim.core.<engine-mod> / mlsysim.infra references anywhere in docs/. (objects.json inventory is gitignored -- regenerated at build.)
34 lines
867 B
Plaintext
34 lines
867 B
Plaintext
# engine.solver.SynthesisSolver { #mlsysim.engine.solver.SynthesisSolver }
|
|
|
|
```python
|
|
engine.solver.SynthesisSolver()
|
|
```
|
|
|
|
Given an SLA, synthesizes the required hardware specs (Wall 22: Inverse Solve).
|
|
|
|
This solver inverts the Roofline model to derive minimum hardware
|
|
specifications required to meet a target latency SLA.
|
|
|
|
Literature Source:
|
|
1. Williams et al. (2009), "Roofline Model."
|
|
2. Jouppi et al. (2017), "In-Datacenter Performance Analysis of a TPU."
|
|
|
|
## Methods
|
|
|
|
| Name | Description |
|
|
| --- | --- |
|
|
| [solve](#mlsysim.engine.solver.SynthesisSolver.solve) | Synthesizes hardware requirements from an SLA target. |
|
|
|
|
### solve { #mlsysim.engine.solver.SynthesisSolver.solve }
|
|
|
|
```python
|
|
engine.solver.SynthesisSolver.solve(
|
|
model,
|
|
target_latency,
|
|
precision='fp16',
|
|
efficiency=0.5,
|
|
)
|
|
```
|
|
|
|
Synthesizes hardware requirements from an SLA target.
|