AOT perf regression on Apple platform

[guangy10]

🐛 Describe the bug

Over the weekend I start observing timeout when exporting models.

Affected models:

• mv3
• mv2
  Affected configs:
• xnnpack_q8
• coreml_fp16

Affected platforms:

• MocOS only.

Expected:
The export jobs used to finish within 30mins

Actual:
Some jobs start hitting the timeout threshold 60min since 1/25
1/26
- mv3, xnnpack_q8: 60min: https://github.com/pytorch/executorch/actions/runs/12980356644/job/36197276541
- mv3, coreml_fp16: 60min: https://github.com/pytorch/executorch/actions/runs/12980356644/job/36197276201
1/25
- mv3 xnnpack_q8: 60min: https://github.com/pytorch/executorch/actions/runs/12970194466/job/36175156930
- mv2 xnnpack_q8: 60min: https://github.com/pytorch/executorch/actions/runs/12970194466/job/36175156520

View historical runs of (mv3, xnnpack_q8) on macOS: https://hud.pytorch.org/hud/pytorch/executorch/main/1?per_page=50&name_filter=apple-perf%20%2F%20export-models%20(mv3%2C%20xnnpack&mergeLF=true

View historical runs of (mv3, coreml_fp16) on macOS: https://hud.pytorch.org/hud/pytorch/executorch/main/1?per_page=50&name_filter=apple-perf%20%2F%20export-models%20(mv3%2C%20coreml&mergeLF=true

Use this query to view all details from the scheduled runs: https://github.com/pytorch/executorch/actions/workflows/apple-perf.yml?query=event%3Aschedule

Versions

trunk

[guangy10]

There isn't much data about how long each step takes. To understand where the slowness comes from, we probably can start adding timer to each step.