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.

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

Default CPU workgroupsize can be inadequat for higher-dimensionsal kernels #499

Closed
vchuravy opened this issue Aug 2, 2024 · 0 comments · Fixed by #500
Closed

Default CPU workgroupsize can be inadequat for higher-dimensionsal kernels #499

vchuravy opened this issue Aug 2, 2024 · 0 comments · Fixed by #500

Comments

@vchuravy
Copy link
Member

vchuravy commented Aug 2, 2024

As observed in WaterLily-jl/WaterLily.jl#133 (comment)

When we have a grid like (64, 64, 64) using a WG size of (1024, 1, 1) is inefficient. Instead WL uses (64,1,1) and maybe KA should "spread" the 1024 to (64, 64,1).
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Improve CPU launch heuristic JuliaGPU/KernelAbstractions.jl
1 participant
@vchuravy