-
-
Notifications
You must be signed in to change notification settings - Fork 32k
GH-118093: Better handling of short and mid-loop traces #122252
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
A couple of questions
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can you:
- Go back to removing the asserts, and leave
is_resume
alone. - Add a comment linking to Improve internal API for fetching original instruction, replacing
_Py_GetBaseOpcode
#122390
Consider it approved once you've done that
When you're done making the requested changes, leave the comment: |
This makes two changes to trace projection:
Perf is neutral, but stats move in the right direction: 83% reduction in "inner loop found", 7% reduction in "trace too short", and 5% fewer optimization attempts overall. We execute 0.5% more uops and 0.5% fewer traces. 2% fewer tier one instructions executed overall.