[JakeStevens]

Summary:

etdump_cpu runs a CPU delegate model through a traced runner with ET_CPU_ETDUMP, drops warmup samples, and writes profile.json with median/min/max latency per plan step and XNNPACK operator, plus each XNNPACK operator's input and output shapes. Each CPU delegate's plan is reassembled from the runner log, so a program with several CPU delegates is profiled as a whole. Events with an unexpected sample count are reported with a warning, and malformed operator metadata degrades to no shapes. It fails if any plan step or, for XNNPACK regions, operator events are missing from the ETDump.

The model runner gains configurable warmups (ET_CPU_WARMUP_RUNS), timed iterations (ET_CPU_TIMED_RUNS), golden tolerances (ET_CPU_ATOL, ET_CPU_RTOL) and a latency summary. The workflows README now covers export and profiling.

Authored with Claude Code.

Differential Revision: D128598106

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24335

• 📄 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 30e6781 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 D128598106.

[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.