Arm backend: Fix bug in dump_operator_distribution

[oscarandersson8218]

A previous change removed the delegated vs non-delegated table of aten operators when calling dump_operator_distribution. This change adds it back.

cc @freddan80 @per @zingo @digantdesai

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16537

• 📄 Preview Python docs built from this PR

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

❌ 2 New Failures, 1 Cancelled Job, 1 Unrelated Failure

As of commit dd43f7d with merge base 9ba1b5d ():

NEW FAILURES - The following jobs have failed:

• trunk / test-arm-backend-ethos-u (test_pytest_models_ethos_u85) / linux-job (gh)
  RuntimeError: Command docker exec -t fcde0fc5ff385d0105311bb90e53f8e32cdbc0868dc91227e175bc400b30e482 /exec failed with exit code 1
• trunk / test-models-macos-coreml (efficient_sam) / macos-job (gh)
  Library not loaded: @rpath/liblz4.1.dylib

CANCELLED JOB - The following job was cancelled. Please retry:

• periodic (gh)

UNSTABLE - The following job is marked as unstable, possibly due to flakiness on trunk:

• pull / android / run-emulator (gh) (#16137)
  Timeout waiting for emulator to boot.

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

[zingo]

OK to merge if ARM tests pass
I see
trunk / test-arm-backend-ethos-u (test_pytest_models_ethos_u85) / linux-job (push)
->
FAILED backends/arm/test/models/test_conformer.py::test_conformer_u85_INT - AssertionError: Output 0 does not match reference output.

It's probably some flaky tests so it might help to just rerun the test.

[zingo]

I still see after this was merged, did you retrigger a testrun it passed?

https://hud.pytorch.org/hud/pytorch/executorch/main/1?per_page=50&name_filter=arm-backend
FAILED backends/arm/test/models/test_conformer.py::test_conformer_tosa_INT - AssertionError: Output 0 does not match reference output.

https://github.com/pytorch/executorch/actions/runs/20918602350/job/60098198182

Wonder how flakey this test is and/or if there is something strange with this PR causing it. (seem strange that is should)

[zingo]

Test passed on next commit in the HUD so it's random.