Specialize BroadcastIndexesRange for the case where there is only 1 contiguous input

[swolchok]

In this case, broadcasting is not possible if I understand correctly.

NOTE TO REVIEWERS: I deleted a failing test because I think it's testing not-actually-existent-in-PyTorch functionality. Please let me know if I've made a mistake. I tried to exercise the behavior that this test implied existed like so:

>>> t = torch.tensor([1, 2, 3])
>>> t2 = torch.tensor(4)
>>> torch.abs(t2, out=t)
<stdin>:1: UserWarning: An output with one or more elements was resized since it had shape [3], which does not match the required output shape []. This behavior is deprecated, and in a future PyTorch release outputs will not be resized unless they have zero elements. You can explicitly reuse an out tensor t by resizing it, inplace, to zero elements with t.resize_(0). (Triggered internally at /Users/runner/work/pytorch/pytorch/pytorch/aten/src/ATen/native/Resize.cpp:38.)
tensor(4)

I think that if the test was correct, the result would have been torch.tensor([1, 2, 3]) with no message. Also, none of our operator tests seem to be failing. Have I missed anything?

[swolchok]

Stack from ghstack (oldest at bottom):

• -> Specialize BroadcastIndexesRange for the case where there is only 1 contiguous input #12023
• Unbreak build_size_test.sh on Mac #12089

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12023

• 📄 Preview Python docs built from this PR

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

❌ 4 New Failures, 7 Unrelated Failures

As of commit abef683 with merge base 3e19e67 ():

NEW FAILURES - The following jobs have failed:

• apple-perf (private devices) / apple / benchmark-on-device (google/gemma-3-1b-it, hf_xnnpack_custom_spda_kv_cache_8da4w, apple_iphone_15... / mobile-job (ios) (gh)
  Process completed with exit code 22.
• apple-perf (private devices) / apple / build-benchmark-app / 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/_passes/replace_scalar_with_tensor_pass.py:
• pull / test-llava-runner-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 3bd1893b1a1a564c45f897d6b9c11bd95f0ebe024a1dbb7a2f0d1b1a2320d21b /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

• Apple / build-benchmark-app / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 65
• apple-perf / benchmark-on-device (Qwen/Qwen3-0.6B, et_xnnpack_custom_spda_kv_cache_8da4w, apple_iphone_15, arn... / mobile-job (ios) (gh) (trunk failure)
  Process completed with exit code 22.
• apple-perf / benchmark-on-device (Qwen/Qwen3-0.6B, hf_xnnpack_custom_spda_kv_cache_8da4w, apple_iphone_15, arn... / mobile-job (ios) (gh) (trunk failure)
  Process completed with exit code 22.
• apple-perf / build-benchmark-app / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 65
• pull / unittest / linux / linux-job (gh) (trunk failure)
  examples/models/llama/tests/test_ring_attention.py::TestRingAttention::test_single_token_processing_quantized
• pull / unittest-editable / linux / linux-job (gh) (trunk failure)
  examples/models/llama/tests/test_ring_attention.py::TestRingAttention::test_single_token_processing_quantized
• trunk / unittest-release / linux / linux-job (gh) (trunk failure)
  examples/models/llama/tests/test_ring_attention.py::TestRingAttention::test_single_token_processing_quantized

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

[swolchok]

This is a size win. Size script results below, cases with no change edited out for brevity.

test/build_size_test.sh

before:

ExecuTorch with portable ops binary size, unstripped:
-rwxr-xr-x  1 swolchok  staff  1377360 Jun 27 17:24 cmake-out/test/size_test_all_ops
__TEXT	__DATA	__OBJC	others	dec	hex
1064960	65536	0	4295278592	4296409088	100160000

after:

ExecuTorch with portable ops binary size, unstripped:
-rwxr-xr-x  1 swolchok  staff  1360464 Jun 27 17:26 cmake-out/test/size_test_all_ops
__TEXT	__DATA	__OBJC	others	dec	hex
1048576	65536	0	4295278592	4296392704	10015c000

test/build_optimized_size_test.sh

before:

ExecuTorch with portable ops binary size, unstripped:
-rwxr-xr-x  1 swolchok  staff  1506384 Jun 27 17:17 cmake-out/test/size_test_all_ops
__TEXT	__DATA	__OBJC	others	dec	hex
1064960	65536	0	4295393280	4296523776	10017c000
ExecuTorch with optimized ops binary size, unstripped:
-rwxr-xr-x  1 swolchok  staff  4958792 Jun 27 17:17 cmake-out/test/size_test_all_optimized_ops
__TEXT	__DATA	__OBJC	others	dec	hex
3702784	65536	0	4296212480	4299980800	1004c8000

after:

ExecuTorch with portable ops binary size, unstripped:
-rwxr-xr-x  1 swolchok  staff  1505872 Jun 27 17:28 cmake-out/test/size_test_all_ops
__TEXT	__DATA	__OBJC	others	dec	hex
1064960	65536	0	4295393280	4296523776	10017c000
ExecuTorch with optimized ops binary size, unstripped:
-rwxr-xr-x  1 swolchok  staff  4941448 Jun 27 17:28 cmake-out/test/size_test_all_optimized_ops
__TEXT	__DATA	__OBJC	others	dec	hex
3686400	65536	0	4296212480	4299964416	1004c4000