mirror of
https://github.com/harvard-edge/cs249r_book.git
synced 2026-07-16 23:24:55 -05:00
34 lines
831 B
Plaintext
34 lines
831 B
Plaintext
# solvers.SynthesisSolver { #mlsysim.solvers.SynthesisSolver }
|
|
|
|
```python
|
|
solvers.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.solvers.SynthesisSolver.solve) | Synthesizes hardware requirements from an SLA target. |
|
|
|
|
### solve { #mlsysim.solvers.SynthesisSolver.solve }
|
|
|
|
```python
|
|
solvers.SynthesisSolver.solve(
|
|
model,
|
|
target_latency,
|
|
precision='fp16',
|
|
efficiency=0.5,
|
|
)
|
|
```
|
|
|
|
Synthesizes hardware requirements from an SLA target.
|