Fold non-matching end permutes instead of discarding the region (#22293)

[abeakkas]

Summary:

RemovePermutesAroundElementwiseOps gave up on an entire region whenever it
reached an outgoing permute that was not the inverse of the region's start
permute, so a single mismatched boundary cost every permute removal in that
region.

Such a permute is now kept and its permutation rewritten to absorb the start
permute being removed. With the producer back in the original layout,
permute(permute(x, start), end) is permute(x, R) for R[k] = start[end[k]],
so the consumer sees the same tensor and one permute still disappears. No
permute is added on a live edge: the existing matching case is just the
instance where R is the identity.

Since a permute can now be rewritten in place while staying wired,
_subgraph_edges_are_current also re-validates that an edges_in permutation
still matches what the candidate was planned against.

Reviewed By: DrJessop

Differential Revision: D117939968

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/22293

• 📄 Preview Python docs built from this PR

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

❌ 1 Cancelled Job, 1 Unrelated Failure

As of commit 23815c1 with merge base c27baa8 ():

CANCELLED JOB - The following job was cancelled. Please retry:

• pull / test-voxtral-realtime-xnnpack-linux / linux-job (gh)
  ##[error]The operation was canceled.

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

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

• pull / test-qnn-testsuite-linux / test-backend-linux (qnn, models) / linux-job (gh) (trunk failure)

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

[meta-codesync]

@abeakkas has exported this pull request. If you are a Meta employee, you can view the originating Diff in D117939968.

[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.