Channels last: optimize structural layout regions

[rascani]

Introduce common structural layout-copy helpers and teach the shared transpose
and permute transforms to preserve layout provenance only when every
contributing copy is layout-owned.

Add opt-in layout-region boundary propagation with backend barriers, rank and
broadcast validation, constant remapping, alias handling, symbolic-shape
support, and copy-volume safety. Per-channel QDQ remains a barrier because its
axis is dimension-dependent.

Read the whole of remove_permutes_around_elementwise_ops.py rather than the
diff: the boundary machinery is easier to follow as a unit than as a patch
against the pre-existing subgraph walk.

Local Corstone-300 run of the full Cortex-M suite (670 passed, 4 skipped, 45
xfailed, 4 xpassed), the transforms suites, and lintrunner.

Authored with Codex.

[rascani]

Stack from ghstack (oldest at bottom):

• Cortex-M: add an opt-in NHWC method I/O contract #22029
• Cortex-M: keep NHWC channel broadcasts quantized #21968
• Cortex-M: add opt-in explicit layout lowering #21967
• Cortex-M: make quantized add and multiply layout-agnostic #21966
• Cortex-M: add a contiguous-layout pad operator #22028
• Cortex-M: add explicit-NHWC runtime operators #21965
• Cortex-M: share layout-aware CMSIS-NN kernels #21964
• Channels last: add the common layout pipeline #21963
• Channels last: absorb boundary layout copies into the method contract #22034
• -> Channels last: optimize structural layout regions #21962
• Channels last: teach the data-movement passes both permute dialects #22003

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21962

• 📄 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, 9 Unrelated Failures

As of commit 88da265 with merge base 8b93850 ():

NEW FAILURE - The following job has failed:

• trunk / test-qnn-optimum-model (fp32, dit) / linux-job (gh)
  RuntimeError: Command docker exec -t 8daf1ee6d11eb26a3e1cdd5dd138f9901d0817361d3e42b6c6c4c5a7e8ab4ec8 /exec failed with exit code 1

BROKEN TRUNK - The following jobs failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

• pull / unittest / linux / linux-job (gh) (trunk failure)
  .ci/scripts/tests/test_filter_cuda_matrix.py::TestPublishedSets::test_published_python_versions
• pull / unittest / macos / macos-job (gh) (trunk failure)
  .ci/scripts/tests/test_filter_cuda_matrix.py::TestPublishedSets::test_published_python_versions
• pull / unittest / windows / windows-job (gh) (trunk failure)
  .ci/scripts/tests/test_filter_cuda_matrix.py::TestPublishedSets::test_published_python_versions
• pull / unittest-editable / linux / linux-job (gh) (trunk failure)
  .ci/scripts/tests/test_filter_cuda_matrix.py::TestPublishedSets::test_published_python_versions
• pull / unittest-editable / macos / macos-job (gh) (trunk failure)
  .ci/scripts/tests/test_filter_cuda_matrix.py::TestPublishedSets::test_published_python_versions
• pull / unittest-editable / windows / windows-job (gh) (trunk failure)
  .ci/scripts/tests/test_filter_cuda_matrix.py::TestPublishedSets::test_published_python_versions
• trunk / unittest-release / linux / linux-job (gh) (trunk failure)
  .ci/scripts/tests/test_filter_cuda_matrix.py::TestPublishedSets::test_published_python_versions
• trunk / unittest-release / macos / macos-job (gh) (trunk failure)
  .ci/scripts/tests/test_filter_cuda_matrix.py::TestPublishedSets::test_published_python_versions
• trunk / unittest-release / windows / windows-job (gh) (trunk failure)
  .ci/scripts/tests/test_filter_cuda_matrix.py::TestPublishedSets::test_published_python_versions

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.

[AdrianLundell]

What is the reason for extending this pass rather than generalizing the PropagateViewCopyPermuteUp/Down passes from the arm backend? The biggest issue which introduced unnecessary permutes in the arm backend before the refactor was view operators which forced channels-first format, and I don't see that solved by this pass.

Also, is it necessary to distinguish between layout introduced ops and existing ones?