Cortex-M: add explicit-NHWC runtime operators - #21965
Draft
rascani wants to merge 2 commits into
Draft
Conversation
Contributor
Author
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21965
Note: Links to docs will display an error until the docs builds have been completed. ❌ 3 New Failures, 1 Unclassified FailureAs of commit 494983f with merge base 1b2838b ( NEW FAILURES - The following jobs have failed:
UNCLASSIFIED FAILURE - DrCI could not classify the following job because the workflow did not run on the merge base. The failure may be pre-existing on trunk or introduced by this PR:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This was referenced Aug 20, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add fixed-layout NHWC-logical schemas for quantized convolution, depthwise convolution, transpose convolution, average pooling, max pooling, and padding.
Each wrapper lives beside its legacy entry point and selects NHWCLogical in the shared implementation, so operator identity carries the serialized layout contract without a general-purpose runtime parameter. Register the schemas, Python reference implementations, scratch sizing, selective runner entries, and host and FVP coverage.
Harden both padding entry points by validating rank and four-element padding before indexing and by reporting the actual entry-point name.
All six explicit-NHWC cases on Cortex-M55 and Cortex-M33 FVPs, selective-runner cross-builds, and lintrunner.
Authored with Codex.