Reland "Arm backend: Rerun duplicate-user fusion after TOSA lowering"#21380
Open
YufengShi-dudu wants to merge 1 commit into
Open
Reland "Arm backend: Rerun duplicate-user fusion after TOSA lowering"#21380YufengShi-dudu wants to merge 1 commit into
YufengShi-dudu wants to merge 1 commit into
Conversation
Late TOSA transformations can introduce equivalent operations after the first FuseDuplicateUsersPass invocation. Rerun it after TOSA and shape transformations, before output nodes are made unique. Run InsertRescalePass after the final FuseDuplicateUsersPass. Fusing generated RESCALE users can merge distinct quantized paths and produce incorrect results. TOSA-FP operator comparisons: | Model | Before | After | Reduction | |--------------------|-------:|------:|----------:| | SD3 | 1,591 | 1,527 | 64 (4.0%) | | Conformer delegate | 544 | 498 | 46 (8.5%) | Reference-output tests pass with late fusion enabled. Add regression coverage for late fusion, rescale insertion, and output uniqueness pass ordering. Change-Id: Ia4e2335e05b18d16b93c7e035a5502b8f050855c Signed-off-by: Yufeng Shi <yufeng.shi@arm.com>
YufengShi-dudu
added
partner: arm
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21380
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 12ef2f4 with merge base fbd14e6 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
Collaborator
Author
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Late TOSA transformations can introduce equivalent operations after the first FuseDuplicateUsersPass invocation. Rerun it after TOSA and shape transformations, before output nodes are made unique.
Run InsertRescalePass after the final FuseDuplicateUsersPass. Fusing generated RESCALE users can merge distinct quantized paths and produce incorrect results.
TOSA-FP operator comparisons:
Reference-output tests pass with late fusion enabled.
Add regression coverage for late fusion, rescale insertion, and output uniqueness pass ordering.
Change-Id: Ia4e2335e05b18d16b93c7e035a5502b8f050855c
cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 @mansnils @Sebastian-Larsson @robell @rascani