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

Fix register overload in CUDA spacepoint formation #730

Merged

Conversation

stephenswat
Copy link
Member

PR #719 refactored the spacepoint formation to use the detray detector. While this was and remains a good idea, the introduction of the detray detector massively increases the register use of the kernel, to the point that I was seeing "too many resources requested for launch" errors. This commit modifies the kernel to specify appropriate launch bounds, allowing the compiler to better tune the register usage and resolve the bug.

@stephenswat stephenswat added bug Something isn't working cuda Changes related to CUDA labels Oct 7, 2024
@stephenswat stephenswat force-pushed the fix/cuda_sp_launch_bounds branch from 5ad8c42 to 23d73a2 Compare October 7, 2024 12:52
@stephenswat stephenswat force-pushed the fix/cuda_sp_launch_bounds branch from 23d73a2 to f10c2cf Compare October 8, 2024 09:26
@stephenswat stephenswat force-pushed the fix/cuda_sp_launch_bounds branch from f10c2cf to b47338d Compare October 21, 2024 13:55
@stephenswat stephenswat enabled auto-merge October 21, 2024 13:55
Copy link

PR acts-project#719 refactored the spacepoint formation to use the detray detector.
While this was and remains a good idea, the introduction of the detray
detector massively increases the register use of the kernel, to the
point that I was seeing "too many resources requested for launch"
errors. This commit modifies the kernel to specify appropriate launch
bounds, allowing the compiler to better tune the register usage and
resolve the bug.
@stephenswat stephenswat merged commit 8a268c7 into acts-project:main Oct 21, 2024
23 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working cuda Changes related to CUDA
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants