Arm backend: Remove no-op repeat nodes in ConvertExpandCopyToRepeatPass #10137
Conversation
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10137
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 3e6dea9 with merge base a260704 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
@pytorchbot label "partner: arm" |
pytorch-bot
bot
added
the
partner: arm
|
@pytorchbot label "topic: not user facing" |
|
@pytorchbot label ciflow/trunk |
|
@martinlsm Linting issues need to be addressed. Apart from that it looks good to me. |
Update ConvertExpandCopyToRepeatPass to eliminate Repeat nodes where all repetition counts are one, as these are functionally equivalent to a simple copy. This reduces unnecessary operations in the graph. This patch affects two unit tests in backends/arm/test/ops/test_expand.py. The models (test subjects) in those unit tests are in the affected cases optimized such that the only computation node (torch.Tensor.expand) they each contain is optimized away by the modified ConvertExpandCopyToRepeatPass. This will make Vela complain saying that the model is empty and the TOSA file cannot be compiled. Set the affected unit tests to xfail since they are expected to be resolved later in another patch. Change-Id: I8f118c30eb9ecde09a7b8dcefd41b1fb65af8a3b
martinlsm
force-pushed
the
marlin-remove-redundant-ops
branch
from
f742511 to
3e6dea9
Compare
zingo
approved these changes
Apr 22, 2025
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Outdated suggestions cannot be applied.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.
Update ConvertExpandCopyToRepeatPass to eliminate Repeat nodes where all repetition counts are one, as these are functionally equivalent to a simple copy. This reduces unnecessary operations in the graph.
This patch affects two unit tests in
backends/arm/test/ops/test_expand.py. The models (test subjects) in those unit tests are in the affected cases optimized such that the only computation node (torch.Tensor.expand) they each contain is optimized away by the modified ConvertExpandCopyToRepeatPass. This will make Vela complain saying that the model is empty and the TOSA file cannot be compiled. Set the affected unit tests to xfail since they are expected to be resolved later in another patch.
cc @digantdesai @freddan80 @per @zingo @oscarandersson8218