Benchmark CMSIS Conv & DW Conv and improve operator selection
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 5k
- Forks
- 1.2k
- Avg merge
- 2d 10h
- Merged PRs (30d)
- 581
Description
Here we actually have the benefit of choosing between a regular and DW conv. It is likely but not certain that the un-optimized CMSIS-NN DW conv or the one without any SIMD is less efficient that the corresponding CMSIS-NN conv. We don't know exactly until we measure. We could then add something like this for now with a TODO comment:
optimal_dw_conv_constraints = (
in_channels == out_channels and dilation == [1, 1]
) or in_channels == 1
Originally posted by @mansnils in https://github.com/pytorch/executorch/pull/16233#discussion_r2622495668
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No files or tests are named. Start by locating the regular and depthwise CMSIS-NN convolution implementations and benchmarking their optimized, unoptimized, and non-SIMD paths; done means the measurements support an operator-selection rule and the selection logic reflects it with a TODO for provisional behavior.
Written by the indexing model from the issue text.
Assessment
- Domain
- embedded-iot, machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 42/100