Channels last: absorb boundary layout copies into the method contract

[rascani]

A layout region formed by ToContiguousChannelsLastPass is bracketed by
channels_last.permute_copy. Interior copies cancel against each other, but
the ones sitting on a method input or output have nothing to cancel against
and survive. On the 36-case matrix in
backends/transforms/test/test_to_contiguous_channels_last_pass.py they cost
+18 permutes against a no-layout-pass baseline of 138.

This pass deletes those copies and declares the corresponding input or output
channels-last instead, which moves the transpose to the caller — free whenever
the caller already holds the data in that layout. That takes the in-graph count
to 137, one below the baseline.

Read that number carefully, because most of it is a transfer rather than a
saving. Absorption removes 19 permutes from the graph and creates 17 obligations
on the caller; only the difference is genuinely eliminated, and it comes from
fan-out, where one placeholder feeding several branches needs several copies but
only one contract entry. For a caller that already holds NHWC the other 17 are
free, and for a delegate the boundary is internal so they disappear entirely,
but neither is true by construction. The test pins both totals, since an
in-graph count on its own could be driven to zero by handing the caller
unlimited work.

Two things about the design are worth stating because the obvious alternatives
are worse. First, ordering: permuting the boundary up front and hoping the
copies cancel during formation only reaches 151, and regresses more cases than
it fixes, because graphs with no layout anchors get copies inserted that nothing
can ever cancel. Absorbing after formation is what pays. Second, fan-out: a
residual block feeds one placeholder to several branches, each with its own
copy, and skipping those leaves most of the win on the table — handling them is
the difference between 141 and 137.

The copy need not be adjacent to the boundary. Quantized graphs interpose a
per-tensor quantize or dequantize, which reorders nothing, so the search walks
through those and relabels them on the way. Per-channel quantization is
excluded: its axis is dimension-dependent.

Because this changes what callers must pass and what they get back, the pass
reports the applied permutations rather than leaving them to be inferred. No
in-tree pipeline runs it yet.

Authored with Claude Code.

[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: absorb boundary layout copies into the method contract #22027
• Channels last: add the common layout pipeline #21963
• 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/22027

• 📄 Preview Python docs built from this PR

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

❌ 12 Pending, 10 Unrelated Failures, 1 Unclassified Failure

As of commit 07f2fd3 with merge base 8b93850 ():

UNCLASSIFIED FAILURE - DrCI could not classify the following job because the workflow did not run on the merge base. The failure may be pre-existing on trunk or introduced by this PR:

• trunk / test-huggingface-transformers-macos (llama3.2-1b|coreml_fp32_gpu|--quantize) / macos-job (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  ##[error]fatal: unable to access 'https://github.com/ml-explore/mlx.git/': Could not resolve host: github.com

FLAKY - The following job failed but was likely due to flakiness present on trunk:

• Test ROCm AOTI / test-voxtral-realtime-rocm-gfx1100-rocm7.1 / linux-job (gh) (matched linux rule in flaky-rules.json)
  Error response from daemon: error from registry: failed to resolve reference "docker.io/pytorch/manylinux2_28-builder:rocm7.1": failed to authorize: failed to fetch oauth token: unexpected status from POST request to https://auth.docker.io/token: 429 Too Many Requests

BROKEN TRUNK - The following jobs failed but was 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.

[linux-foundation-easycla]

• ✅ login: Gasoonjia / name: Gasoonjia (53a39f6)
• ✅ login: JakeStevens / name: Jacob Stevens (02ff60d)
• ✅ login: SaoirseARM / name: SaoirseARM (ad9902c)
• ✅ login: YIWENX14 / name: YIWENX14 (1d4df21, 8b93850)
• ✅ login: cthotti / name: Chetan Thotti (98cf058, 98cf058)
• ✅ login: digantdesai / name: Digant Desai (2aac1f5, 34cd1de, 549ba1c, 6a8eae9, 8ac4894, ac40ad4)
• ✅ login: metascroy / name: Scott Roy (98cf058)
• ✅ login: perheld / name: Per Held (4cf0207)
• ✅ login: psiddh / name: Siddartha Pothapragada (66a0fec, 7a51fd7, 89e6f90, adeb496, d756e7d)
• ✅ login: pssrawat / name: pssrawat (8d21053)
• ✅ login: rascani / name: RJ Ascani (07f2fd3, 63f0900, 7785cf3, c8f8572)
• ✅ login: shoumikhin / name: Anthony Shoumikhin (5030bdd, 7a51fd7, 8b5da54, 9017295, ac9857b, c0260ec)
• ✅ login: wwwind / name: Elena Zhelezina (d7c5dd4)
• ✅ login: zingo / name: Zingo Andersen (15495a5)
• ❌ The email address for the commit (84f541c, a0f860b) is not linked to the GitHub account, preventing the EasyCLA check. Consult this Help Article and GitHub Help to resolve. (To view the commit's email address, add .patch at the end of this PR page's URL.) For further assistance with EasyCLA, please visit our EasyCLA portal and chat with our support bot.