-
Notifications
You must be signed in to change notification settings - Fork 38
feat: new syrk passes + lowering #1908
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
src/Compiler.jl
Outdated
|
|
||
| if !is_sharded | ||
| # these passes don't have optimized sharding implementations | ||
| append!(transform_passes_list, ["dot_general_to_syrk"]) |
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't we just (inefficiently) lower syrk back to a dot general at the end, if not supported
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.
we do that as fallback.
But shardy passes are run post this transform, so a transform here would mean an implicit all-gather on CPU.
No description provided.