-
Notifications
You must be signed in to change notification settings - Fork 12
[Tune] Constraint extraction, model finding, and schedule rewriting #40
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
base: main
Are you sure you want to change the base?
Conversation
| if args.dump_schedule: | ||
| schedule_module = wload.schedule_module( | ||
| stop_at_stage=args.dump_payload, parameters=params | ||
| ) | ||
| print(schedule_module) | ||
| elif args.dump_payload: |
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.
It would be good if we could still dump both the payload and schedule simultaneously if so desired.
|
|
||
| from mlir import ir | ||
|
|
||
| NonDet = object() # Sentinel value for non-determinized parameters. |
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.
Maybe a more descriptive name e.g. "Unselected"
tkarna
left a comment
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.
Apart from a couple of minor comments this looks good time!
For a non-trivial example, run
python examples/xegpu_matmul/matmul.py --dump-schedule --non-detforthen feed that to
... | python -m lighthouse.tune - --print-smtlib -n 100:Co-authored-by: Tuomas Kärnä [email protected]