Arm backend: Fix U55 int16 table generation

[3l1]

Summary:
This diff fixes critical runtime bugs in U55 INT16 table operations (rsqrt, sigmoid, tanh)

WARNING: This diff goes with the Regor diff D85535937 and is only split because it maps to a separate OSS github repo (the Arm Regor git repo)

bypass-github-export-checks
bypass-github-pytorch-ci-checks
bypass-github-executorch-ci-checks

Differential Revision: D85312140

cc @freddan80 @per @zingo @oscarandersson8218 @digantdesai

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15390

• 📄 Preview Python docs built from this PR

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

❗ 2 Active SEVs

There are 2 currently active SEVs. If your PR is affected, please view them below:

• Long queue for ROCM runners, also B200 and XPU queueing is observed
• B200 queuing was observed on Oct 29

❌ 17 New Failures, 1 Cancelled Job, 11 Unrelated Failures

As of commit ae665fa with merge base 4c58010 ():

NEW FAILURES - The following jobs have failed:

• Apple / build-demo-ios / macos-job (gh)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 65
• Lint / lintrunner / linux-job (gh)
  >>> Lint for backends/arm/test/ops/test_tanh.py:
• pull / test-multimodal-linux (gemma3-4b) / linux-job (gh)
  RuntimeError: Command docker exec -t 8a7a358a2cd227c0bc514eae69e41bba0b3732b83dc6d88d5ca72a5666947815 /exec failed with exit code 127
• pull / unittest-editable / macos / macos-job (gh)
  export/tests/test_target_recipes.py::TestTargetRecipes::test_linear_model
• Test CUDA Builds / export-gemma3-cuda-non-quantized / linux-job (gh)
  RuntimeError: Command docker exec -t 79cc2042f2afdd10d8b328f72b782cac4a078cbbba633351e7a4fadb04934c46 /exec failed with exit code 127
• Test CUDA Builds / export-gemma3-cuda-quantized-int4-tile-packed / linux-job (gh)
  RuntimeError: Command docker exec -t 7a1b0b7bfa8175c8234371950d7247ed02296a12af928bbe67ad8a4e19042a99 /exec failed with exit code 127
• Test CUDA Builds / export-voxtral-cuda-non-quantized / linux-job (gh)
  RuntimeError: Command docker exec -t 5ae3f2f542e7cf36abb9da58dacc5ef68a621dab8b6f1c0900b94ffd725dd94f /exec failed with exit code 127
• Test CUDA Builds / export-voxtral-cuda-quantized-int4-tile-packed / linux-job (gh)
  RuntimeError: Command docker exec -t bc0379e6ac688d58cda7a2cbd27fc042470135fd33be500ca758d036c4119e89 /exec failed with exit code 127
• Test CUDA Builds / export-voxtral-cuda-quantized-int4-weight-only / linux-job (gh)
  RuntimeError: Command docker exec -t 8b2af530411c599d5704cf77027d7df67e0b8b02a5ba5d6f9b0da8fe71766aab /exec failed with exit code 127
• trunk / test-arm-backend (test_pytest_ops_ethosu_fvp) / linux-job (gh)
  RuntimeError: Command docker exec -t c6b29a5108fba914bc6e15fd445d8df2441399ed1a391f311bb4e1ab4b6b4f2b /exec failed with exit code 1
• trunk / test-huggingface-transformers-xnnpack (gemma3-1b|xnnpack|--quantize) / linux-job (gh)
  RuntimeError: Command docker exec -t 4891d6f334832b753feb4669d2330d505ed86cca5bad5a0ce28194fe5a09f908 /exec failed with exit code 127
• trunk / test-huggingface-transformers-xnnpack (llama3.2-1b|xnnpack|--quantize) / linux-job (gh)
  RuntimeError: Command docker exec -t 69749e0935c9ddf1aa53be865ecfc1cdf2fb64696c39d418592382a30a47e59c /exec failed with exit code 127
• trunk / test-huggingface-transformers-xnnpack (phi4-mini|xnnpack|--quantize) / linux-job (gh)
  RuntimeError: Command docker exec -t b3523e9abe20218c827d4b0e6d5210cd98b080c6ee8dd9133a7f5548598e0cda /exec failed with exit code 127
• trunk / test-huggingface-transformers-xnnpack (qwen3-0.6b|xnnpack|--quantize) / linux-job (gh)
  RuntimeError: Command docker exec -t cef99929e9f2ccbdebc6d788d7643e70422d40457a4c7c72932bcda8a16e1f3f /exec failed with exit code 127
• trunk / test-huggingface-transformers-xnnpack (qwen3-1.7b|xnnpack|--quantize) / linux-job (gh)
  RuntimeError: Command docker exec -t 16c95668087b2d29c546a8b81cab040fd28f641555689fc6a84646ac171d6694 /exec failed with exit code 127
• trunk / test-huggingface-transformers-xnnpack (smollm2-135m|xnnpack|--quantize) / linux-job (gh)
  RuntimeError: Command docker exec -t aacd6843618ca8c6a2c459679b27914955a62f60c9fc39005289d77fcd38660e /exec failed with exit code 127
• trunk / test-huggingface-transformers-xnnpack (smollm3-3b|xnnpack|--quantize) / linux-job (gh)
  RuntimeError: Command docker exec -t a8d2deeca093910d93b2eb9bc6f79c7b763853b3335041a732fe848d6838fa43 /exec failed with exit code 127

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

• trunk / test-models-macos-cpu (vit, xnnpack-quantization-delegation) / macos-job (gh)
  ##[error]The operation was canceled.

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

• pull / unittest / linux / linux-job (gh) (matched linux rule in flaky-rules.json)
  The runner has received a shutdown signal. This can happen when the runner service is stopped, or a manually started runner is canceled.
• trunk / test-huggingface-transformers-macos (distilbert|coreml_fp32_gpu|--quantize) / macos-job (gh) (similar failure)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 127

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-editable / linux / linux-job (gh) (trunk failure)
• Test Metal Backend / export-voxtral-metal-artifact / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 127
• trunk / test-huggingface-transformers-macos (bert|coreml_fp32_gpu|--quantize) / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 127
• trunk / test-huggingface-transformers-macos (llama3.2-1b|coreml_fp32_gpu|--quantize) / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 127
• trunk / test-huggingface-transformers-macos (olmo-1b|coreml_fp32_gpu|--quantize) / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 127
• trunk / test-huggingface-transformers-macos (qwen3-0.6b|coreml_fp32_gpu|--quantize) / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 127
• trunk / test-huggingface-transformers-macos (smollm2-135m|coreml_fp32_gpu|--quantize) / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 127
• trunk / test-multimodal-macos (gemma3-4b) / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 127
• trunk / unittest-release / linux / linux-job (gh) (trunk failure)

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

[meta-codesync]

@3l1 has exported this pull request. If you are a Meta employee, you can view the originating Diff in D85312140.

[3l1]

@pytorchbot label "release notes: none"

[3l1]

todo: restore xfails unti regor oss is in sync

[3l1]

I am told by Arm that they have an alternate, TOSA compliant, solution in Regor https://gitlab.arm.com/artificial-intelligence/ethos-u/ethos-u-vela/-/commit/5e8dd39861595e62287340802ab37812bda3d369 & https://gitlab.arm.com/artificial-intelligence/ethos-u/ethos-u-vela/-/commit/90e7cff2426c36876a2d2115b84844ecb39040ef

let's wait until this makes it to the Executorch repo before deciding to land this PR or not

@digantdesai

[zingo]

Move this to "draft" while waiting on Vela, just did it for slightly easier overview on GitHub, feel free to disagree and put it back of you want it as non draft if work both ways for me :) .