Skip to content

[AMD][BACKEND] Add async_copy to Gluon for gfx1250 #8622

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.

Sign up for GitHub

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

Jump to bottom
Merged
antiagainst merged 2 commits into from
Nov 3, 2025
Merged

[AMD][BACKEND] Add async_copy to Gluon for gfx1250 #8622

antiagainst merged 2 commits into from
Nov 3, 2025
+129 −1

Conversation

@AlexAUT
Copy link
Contributor

@AlexAUT AlexAUT commented Nov 3, 2025

Adds async_copy.global_to_local to Gluon for gfx1250 and forwards commit_group and wait_group from CDNA4. Note that we do not use global_load_to_shared from CDNA4 because we have relaxed constraints on memory layouts and completion order in regards to loads to registers.

@AlexAUT AlexAUT marked this pull request as ready for review November 3, 2025 16:28
@AlexAUT AlexAUT requested a review from peterbell10 as a code owner November 3, 2025 16:28
@antiagainst antiagainst merged commit 9ec56a2 into triton-lang:main Nov 3, 2025
9 checks passed
tmoreau89 pushed a commit to tmoreau89/triton that referenced this pull request Dec 1, 2025
@AlexAUT @tmoreau89
[AMD][BACKEND] Add async_copy to Gluon for gfx1250 (triton-lang#8622
eab617d 
)

Adds `async_copy.global_to_local` to Gluon for `gfx1250` and forwards
`commit_group` and `wait_group` from `CDNA4`. Note that we do not use
`global_load_to_shared` from `CDNA4` because we have relaxed constraints
on memory layouts and completion order in regards to loads to registers.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@antiagainst antiagainst antiagainst approved these changes

@peterbell10 peterbell10 Awaiting requested review from peterbell10 peterbell10 is a code owner

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@AlexAUT @antiagainst