Qualcomm AI Engine Direct - fix optrace demo script and remove redundant flags from QNN tool

[DannyYuyang-quic]

Qualcomm AI Engine Direct - Fix OpTrace Profiling demo script

Summary

• Fix OpTrace Profiling demo script
• remove redundant flags from QNN tool

Test plan

python -m examples.qualcomm.util_scripts.qairt_visualizer_demo -s {SERIAL_NUM} -m ${SOC_MODEL} -b build-android -a ${path_to_output_folder}

python -m examples.qualcomm.util_scripts.qairt_visualizer_demo -s {SERIAL_NUM} -m ${SOC_MODEL} -b build-android -a ${path_to_output_folder} --online_prepare

python -m backends.qualcomm.tests.test_qnn_delegate.TestUtilsScript.test_debugger_generate_optrace  -s {SERIAL_NUM} -m ${SOC_MODEL} -b build-android --executorch_root . -a .

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16487

• 📄 Preview Python docs built from this PR

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

❌ 4 New Failures, 1 Unrelated Failure

As of commit c1af223 with merge base 913436a ():

NEW FAILURES - The following jobs have failed:

• pull / unittest-arm-backend-with-no-deps (test_pytest_models_tosa) / linux-job (gh)
  RuntimeError: Command docker exec -t a86b8b8e65bcccfd156cb11926afe57fef73a7c76754b276ee5a1e5a217408f0 /exec failed with exit code 127
• pull / unittest-arm-backend-with-no-deps (test_pytest_ops_no_target) / linux-job (gh)
  RuntimeError: Command docker exec -t da6615bbdecba5adb9d9b77237c8c2d3458b2f26c3414d9ef36fbe07bdc6fc59 /exec failed with exit code 127
• pull / unittest-arm-backend-with-no-deps (test_pytest_ops_tosa) / linux-job (gh)
  RuntimeError: Command docker exec -t b6f5813d61eaa38031073ef150a2a92d9cf6c0b014e481fc6d24e1ad4b6c0a01 /exec failed with exit code 127
• pull / unittest-arm-backend-with-no-deps (test_run_tosa) / linux-job (gh)
  RuntimeError: Command docker exec -t 4532e70edff7aff858413ab37b8a17bbdec1667bd83556051bcac1d0277d7015 /exec failed with exit code 127

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.

[DannyYuyang-quic]

Hi @cccclai,

The OpTrace profiling demo script was passing an incorrect example input shape to the QNN toolchain, the example input must be provided as a batch input. Passing a input without batch dimension causes qnn-net-run to fail during execution.

This change fixes the demo script by using the correct input type and
removes redundant QNN tool flags that are no longer required.

Please have a look!
Thanks!

[DannyYuyang-quic]

@pytorchbot label "release notes: qualcomm"

[cccclai]

Can we have tests for it?

[DannyYuyang-quic]

Thanks for pointing this out!

We already have a test covering this test here:
https://github.com/pytorch/executorch/blob/main/backends/qualcomm/tests/test_qnn_delegate.py#L8176
In one of the earlier changes, this test was already failing in internal CI, but that failure wasn’t noticed at that time.
It’s now passing and can be used as expected.