NXP backend: Remove dependency on the non-edge operator aten.max_pool2d.default.#17819
Draft
MartinPavella wants to merge 6 commits intopytorch:mainfrom
Draft
Conversation
This change is in preparation for `aten.max_pool1d.default` support, which gets converted to unsqueeze -> max_pool2d_with_indices -> squeeze during lowering to edge. So the `max_pool2d_with_indices` must be converted to `max_pool2d` in edge dialect.
… multiple outputs.
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17819
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 Awaiting Approval, 3 New Failures, 1 Pending, 2 Unrelated FailuresAs of commit 7f031e2 with merge base 389ea94 ( NEW FAILURES - The following jobs have failed:
BROKEN TRUNK - The following jobs failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
The max_pool2d_with_indices is an edge operator that produces 2 outputs, so
getitemnodes must follow it. That's why in the early stages of our ExecuTorch endeavor, Lukas found an XNNPACK pass to replace these ops with just a singlemax_pool2d. As this is an aten dialect only operator, we had to force ExecuTorch to ignore it and there were other connected issues.A recent PR bent the use of this aten dialect operator even further, so I decided to clean it all up and provide a robust support for the
max_pool2d_with_indices, without introducing any non-edge dialect operators.Test plan
Unit-tests provided.
cc @robert-kalmar @JakeStevens @digantdesai