Skip to content
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

Generate teams reductions inside the distribute if the reduction is done inside the distribute op. #210

Merged
merged 2 commits into from
Dec 4, 2024

Conversation

jsjodin
Copy link

@jsjodin jsjodin commented Nov 21, 2024

This patch moves the generation of teams reductions to the distribute op in the case for 'teams distribute parallel do' and 'teams distribute' to make the reductions more efficient. The deviceRTL function uses all the threads in the final teams to do the second level reductions.

…ction

computation is contained within the distribute op.
Copy link

@DominikAdamski DominikAdamski left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@jsjodin
Copy link
Author

jsjodin commented Nov 26, 2024

I thought a bit more and the check needs to be enhanced to ensure that a single distribute operation is enclosing the reduction to allow the code generation of the reduction inside a distribute op. Otherwise it could potentially generate the reduction code twice one for each distribute op.

Copy link

@DominikAdamski DominikAdamski left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@dpalermo dpalermo merged commit 9598c42 into amd-trunk-dev Dec 4, 2024
2 of 4 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants