Qualcomm AI Engine Direct - add pass for extra padding then maxpool2d

[jethroqti]

Qualcomm AI Engine Direct - add pass for extra padding then maxpool2d

Summary:
The padding value used in max_pool2d operations differs between PyTorch and QNN implementations. PyTorch uses negative infinity, while QNN uses zero. To ensure consistent max_pool2d output across both frameworks, we handle this by padding tensor with constant in advance then doing max_pool2d without constant padding. Note that for the quantization flow, we set quant_min as the padding value. If, at runtime, there is a value smaller than quant_min, it could result in an accuracy drop.

Test plans:
python backends/qualcomm/tests/test_qnn_delegate.py TestQNNQuantizedOperator.test_qnn_backend_max_pool2d -b build-android -H ${HOST} -s ${SN} -m ${CHIPID}
python backends/qualcomm/tests/test_qnn_delegate.py TestQNNFloatingPointOperator.test_qnn_backend_max_pool2d -b build-android -H ${HOST} -s ${SN} -m ${CHIPID}

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16534

• 📄 Preview Python docs built from this PR

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

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

As of commit b3e891d with merge base 47dc1de ():

NEW FAILURES - The following jobs have failed:

• Lint / lintrunner / linux-job (gh)
  >>> Lint for backends/qualcomm/_passes/recompose_pad_maxpool2d.py:
• pull / unittest / macos / macos-job (gh)
  export/tests/test_target_recipes.py::TestTargetRecipes::test_linear_model
• pull / unittest-arm-backend-with-no-deps (test_pytest_models_tosa) / linux-job (gh)
  RuntimeError: Command docker exec -t 8aeeade9f7143e467f65294e206c97bc6fb1ef34421cddf82506c558a0f2b8a3 /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 ce6faf90bf71c423c9845ac80578142a1c184e579f64ee047ee76789e7f625c1 /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 3dfbfdef424c3f6706a4c2f329e4a8d03e249b5ca70350186771e1c863a95461 /exec failed with exit code 127
• pull / unittest-arm-backend-with-no-deps (test_run_tosa) / linux-job (gh)
  RuntimeError: Command docker exec -t 76a05f673942860821c4caa344e6295d8dd936b03220d08470e5727e63c606c9 /exec failed with exit code 127

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.

[jethroqti]

@pytorchbot label "release notes: qualcomm"

[jethroqti]

Due to the padding value used in max_pool2d operations differs between PyTorch and QNN implementations. This pass will improve this situation. Please take a look. Thanks.
@cccclai @haowhsu-quic