Arm backend: Add as_strided_copy.default decomposition and test

[xingguo01]

Change-Id: Iffedfed51bba0ef63524b0aed7ce63c36881eaea

Summary

Arm backend: Add as_strided_copy.default decomposition and test

@zingo @per @freddan80 @oscarandersson8218 @Sebastian-Larsson

cc @freddan80 @per @zingo @oscarandersson8218 @digantdesai

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16702

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❌ 3 New Failures

As of commit aabdc73 with merge base dbf3c37 ():

NEW FAILURES - The following jobs have failed:

• pull / test-coreml-bc-macos (macos-m1-stable) / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1
• pull / test-coreml-bc-macos (macos-m2-stable) / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1
• pull / unittest-editable / macos / macos-job (gh)
  export/tests/test_target_recipes.py::TestTargetRecipes::test_mv3_model

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[xingguo01]

@pytorchbot label "ciflow/trunk"

[pytorch-bot]

To add these label(s) (ciflow/trunk) to the PR, please first approve the workflows that are awaiting approval (scroll to the bottom of this page).

This helps ensure we don't trigger CI on this PR until it is actually authorized to do so. Please ping one of the reviewers if you do not have access to approve and run workflows.

[xingguo01]

@pytorchbot label "partner: arm"

[xingguo01]

@pytorchbot label "release notes: arm"

[zingo]

This got a test error with
FAILED backends/arm/test/models/test_mobilenet_v2_arm.py::test_mv2_tosa_FP_channels_last
Not sure if the tests is just randomely failing or related to the PR, if you think is a random fail you can just retrigger the failed test and it will probably go away.

[xingguo01]

@zingo Probably unrelated to my PR. That failure is in test_mobilenet_v2_arm.py::test_mv2_tosa_FP_channels_last and complains that torch.ops.higher_order.executorch_call_delegate is missing in the lowered graph. My PR changes as_strided_copy decomposition and support logic; it doesn’t touch the mobilenet test, delegate lowering, or call-delegate op insertion.

[zingo]

If you click on the "pull / unittest-arm-backend-..." below

You will get to test output, you can look at the error and if you scroll all the way to the top again you have a drop-down called "Re-run jobs" on the top right side. If you select "Re-run failed jobs" it will only rerun those.

[xingguo01]

@zingo I don't think I have that level of permission, can't even trigger workflow....

[zingo]

Was going to retrigger it for you but it seem to already be running.

[zingo]

Test rerun 4 time and still fails, Ill try a rebase also, if that don't work it might be something in the test anyway.
Test seem to pass on main
https://hud.pytorch.org/hud/pytorch/executorch/main/1?per_page=50&name_filter=arm-backend
So lets see after the rebase tests has finished :)

[xingguo01]

@zingo found the culprit will create a chained patch on top, the culprit is that I need to delete L67-L71 in /backends/arm/test/models/test_mobilenet_v2_arm.py https://github.com/pytorch/executorch/blob/main/backends/arm/test/models/test_mobilenet_v2_arm.py#L58

[zingo]

@zingo found the culprit will create a chained patch on top, the culprit is that I need to delete L67-L71 in /backends/arm/test/models/test_mobilenet_v2_arm.py https://github.com/pytorch/executorch/blob/main/backends/arm/test/models/test_mobilenet_v2_arm.py#L58

Good find!!! Anmd nice outcome that we lowered more in this case :)

[zingo]

OK to merge if all Arm tests passes ( they do :) )