[JakeStevens]

Summary:

CPUPlan records one ETDump delegate event per step, named provider/implementation:first_node[+N], so every provider is traced without provider changes. The XNNPACK provider enables XNNPACK runtime profiling when a tracer is attached and logs <operator> #<n> events, such as Transpose (ND, X32) #3, inside its step, with each operator's input and output shapes as JSON delegate metadata.

Shapes come from XNNPACK's internal runtime (src/xnnpack/subgraph.h). That header dependency and the code that reads it are only compiled when ET_EVENT_TRACER_ENABLED is defined. runner writes an ETDump when ET_CPU_ETDUMP is set.

CMake builds XNNProfiler as a separate xnnpack_profiler library that xnnpack_backend and the CPU provider targets link, matching the Buck split, and adds XNNPACK's source root to the CPU targets' include path for the traced build. The Apple XNNPACK framework packs the new archive.

Authored with Claude Code.

Differential Revision: D125525223

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/23926

• 📄 Preview Python docs built from this PR

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

❌ 10 Unclassified Failures

As of commit 80cf805 with merge base 6c7b213 ():

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

• Build Aarch64 Linux CUDA Wheels / pytorch/executorch / build-wheel-py3_11-cuda-aarch6413_2-aarch64 (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  AssertionError: expected at most one library to define pthreadpool_create, found 2: ['lib/libexecutorch_backend_xnnpack.so', 'lib/libexecutorch_threadpool.so']. More than one definition means the process has more than one bundled thread pool implementation.
• Build Aarch64 Linux CUDA Wheels / pytorch/executorch / upload / upload-wheel-py3_11-cuda-aarch6413_2-aarch64 (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  Unable to download artifact(s): Artifact not found
• Build Aarch64 Linux Wheels / pytorch/executorch / build-wheel-py3_11-cpu-aarch64 (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  AssertionError: expected at most one library to define pthreadpool_create, found 2: ['lib/libexecutorch_backend_xnnpack.so', 'lib/libexecutorch_threadpool.so']. More than one definition means the process has more than one bundled thread pool implementation.
• Build Aarch64 Linux Wheels / pytorch/executorch / upload / upload-wheel-py3_11-cpu-aarch64 (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  Unable to download artifact(s): Artifact not found
• Build Linux CUDA Wheels / pytorch/executorch / build-manywheel-py3_11-cuda13_2 (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  AssertionError: expected at most one library to define pthreadpool_create, found 2: ['lib/libexecutorch_backend_xnnpack.so', 'lib/libexecutorch_threadpool.so']. More than one definition means the process has more than one bundled thread pool implementation.
• Build Linux CUDA Wheels / pytorch/executorch / upload / upload-manywheel-py3_11-cuda13_2 (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  Unable to download artifact(s): Artifact not found
• Build Linux Wheels / pytorch/executorch / build-manywheel-py3_11-cpu (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  AssertionError: expected at most one library to define pthreadpool_create, found 2: ['lib/libexecutorch_backend_xnnpack.so', 'lib/libexecutorch_threadpool.so']. More than one definition means the process has more than one bundled thread pool implementation.
• Build Linux Wheels / pytorch/executorch / upload / upload-manywheel-py3_11-cpu (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  Unable to download artifact(s): Artifact not found
• Build macOS Wheels / pytorch/executorch / build-wheel-py3_11-cpu (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  AssertionError: expected at most one library to define cpuinfo_initialize, found 2: ['lib/libexecutorch_backend_xnnpack.dylib', 'lib/libexecutorch_threadpool.dylib']. More than one definition means the process has more than one bundled thread pool implementation.
• Build macOS Wheels / pytorch/executorch / upload / upload-wheel-py3_11-cpu (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  Unable to download artifact(s): Artifact not found

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

[meta-codesync]

@JakeStevens has exported this pull request. If you are a Meta employee, you can view the originating Diff in D125525223.

[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.