[ET-VK] lowering ExecuTorch tensor dtype for Vulkan tensor dtype to enable 64bit

[ahmtox]

Stack from ghstack (oldest at bottom):

• [ET-VK][testing] Q/DQ/CQP op comprehensive delegate dynamic quantization testing #12210
• [ET-VK][Ops] dequantize_per_tensor.tensor variant #12209
• [ET-VK][Ops] quantize_per_tensor.tensor variant #12208
• [ET-VK][Ops] dequantize_per_channel shaders and impl #12207
• [ET-VK][Ops] dequantize_per_channel reference impl and testing #12206
• [ET-VK][Ops] quantize_per_channel shaders and impl #12205
• [ET-VK][Ops] quantize_per_channel reference impl and testing #12204
• [ET] correcting cpu ref quantize_per_channel logic to align with ATen #12203
• -> [ET-VK] lowering ExecuTorch tensor dtype for Vulkan tensor dtype to enable 64bit #12202
• [ET-VK][ez] enabling fp64->fp32 converison for vulkan compatibility #12201
• [ET-VK][ez][Ops] registering Q/DQ/CQP ops and specifying optimal storage #12200
• [ET-VK][Ops] aligning Q/DQ/CQP op inputs with ATen impl #12199

Context

We are aligning with other delegate in how they handle 64bit output dtypes. In this case, we only previously had support for integers, but this is also adding support for doubles. We convert the values in place so that we can be more performant.

Changes

Add a conversion from 64bit output to 32bit output so that its compatible with vulkan.

Differential Revision: D77746134

cc @SS-JIA @manuelcandales @digantdesai @cbilgin

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12202

• 📄 Preview Python docs built from this PR

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

❌ 1 New Failure, 2 Cancelled Jobs

As of commit 8ae4f88 with merge base 6669637 ():

NEW FAILURE - The following job has failed:

• pull / unittest-editable / macos / macos-job (gh)
  backends/xnnpack/test/ops/test_conv1d.py::TestConv1d::test_qs8_conv1d_batchnorm_seq

CANCELLED JOBS - The following jobs were cancelled. Please retry:

• pull / test-models-linux (mobilebert, portable, linux.2xlarge) / linux-job (gh)
  ##[error]The operation was canceled.
• pull / test-models-linux (mobilebert, xnnpack-quantization-delegation, linux.2xlarge) / linux-job (gh)
  ##[error]The operation was canceled.

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.

[facebook-github-bot]

This pull request was exported from Phabricator. Differential Revision: D77746134

[facebook-github-bot]

This pull request was exported from Phabricator. Differential Revision: D77746134

[facebook-github-bot]

This pull request was exported from Phabricator. Differential Revision: D77746134

[meta-cla]

Hi @ahmtox!

Thank you for your pull request.

We require contributors to sign our Contributor License Agreement, and yours needs attention.

You currently have a record in our system, but the CLA is no longer valid, and will need to be resubmitted.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at [email protected]. Thanks!

[github-actions]

Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as Stale.
Feel free to remove the Stale label if you feel this was a mistake.
If you are unable to remove the Stale label please contact a maintainer in order to do so.
If you want the bot to never mark this PR stale again, add the no-stale label.
Stale pull requests will automatically be closed after 30 days of inactivity.