Add channels_last edge-op dialect (conv, avg_pool2d, permute_copy)#20559
Draft
rascani wants to merge 1 commit into
Draft
Add channels_last edge-op dialect (conv, avg_pool2d, permute_copy)#20559rascani wants to merge 1 commit into
rascani wants to merge 1 commit into
Conversation
First vertical slice of the common memory-layout handling infra (RFC pytorch#19299): a backend-agnostic channels_last operator dialect whose ops interpret their activations as (N, H, W, C) contiguous with a fixed dim-order. Kernels wrap the existing aten ops with permutes, since efficiency is a non-goal at this layer; later passes (the pytorch#20094 conversion and pytorch#20098 fusion) make channels-last regions explicit and fuse the permutes away. Runtime C++ kernels, the conversion pass, and the remaining ops are deferred to follow-ups. Part of pytorch#20093. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20559
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New Failures, 1 Unrelated Failure, 1 Unclassified FailureAs of commit 019d0f4 with merge base 92e6a4c ( 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:
FLAKY - The following job failed but was likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This PR needs a
|
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.
Summary
First vertical slice of the common memory-layout handling infra (RFC #19299): a backend-agnostic channels_last operator dialect whose ops interpret their activations as (N, H, W, C) contiguous with a fixed dim-order. Kernels wrap the existing aten ops with permutes, since efficiency is a non-goal at this layer; later passes (the #20094 conversion and #20098 fusion) make channels-last regions explicit and fuse the permutes away. Runtime C++ kernels, the conversion pass, and the remaining ops are deferred to follow-ups.
Part of #20093.
Test plan
pytest backends/transforms/test/test_channels_last_ops.py