pytorch / pytorch/executorch

Extend broadcast_args_pass.py to also handle CMSIS-NN kernel selection:

Open
#13,748 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
5k
Forks
1.2k
Avg merge
2d 10h
Merged PRs (30d)
581

Description

This could potentially be added as a pass as well: https://github.com/pytorch/executorch/blob/main/backends/arm/_passes/broadcast_args_pass.py. But long term the ideal solution would be to add broadcast support to CMSIS-NN to get it accelerated w/o memcopies.

Originally posted by @AdrianLundell in https://github.com/pytorch/executorch/pull/13296#discussion_r2297871408

Creating this issue to track further improvements in AOT phase:

  • CMSIS-NN kernel dispatch could be further abstracted into a pass (Broadcast Pass / Similar new dedicated pass):

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading backends/arm/_passes/broadcast_args_pass.py and the linked CMSIS-NN kernel-selection discussion. Determine how the AOT pass should cover CMSIS-NN dispatch and what behavior should be validated; the issue does not name tests or a precise completion criterion.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
backend, embedded-iot, machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.