Qualcomm AI Engine Direct - Ensure that math invariant ops don't change scale and offset

[shewu-quic]

Summary:

• After QNN 2.35, op validation will check math invariant op should not change scale and offset. So, we should replace annotate_single_in_single_out with annotate_single_in_share_out to ensure not to change scale and offset
• Fix the error for internal CI
• Fix the bug for batch norm op

cc: @haowhsu-quic, @cccclai , @winskuo-quic

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11989

• 📄 Preview Python docs built from this PR

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

✅ No Failures

As of commit 063a196 with merge base 3b0f7c8 ():
💚 Looks good so far! There are no failures yet. 💚

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

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

[cccclai]

Is there a list of math invariant op from qnn?

[shewu-quic]

Is there a list of math invariant op from qnn?

It can be found in qnn doc. Operations>Backend supplements>HTP>Quantization.
And also if you modify the quant_attr for math invariant op, you will get the error such as the below.

[ERROR] [Qnn ExecuTorch]:  <E> This op is math invariant, input0 scale (0.000308) and output0 scale (0.000306) should be identical but is not.
 
[ERROR] [Qnn ExecuTorch]:  <E> QnnBackend_validateOpConfig failed 3110
 
[ERROR] [Qnn ExecuTorch]:  <E> Failed to validate op aten_expand_copy_default_15 with error 0xc26

[facebook-github-bot]

@cccclai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.