Skip to content

[UR][CUDA] Avoid unnecessary calls to cuFuncSetAttribute #16928

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

Merged
merged 2 commits into from
Feb 27, 2025
Merged

[UR][CUDA] Avoid unnecessary calls to cuFuncSetAttribute #16928

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
14bafb8
[UR][CUDA] Avoid unnecessary calls to cuFuncSetAttribute
rafbiels Feb 7, 2025
6429ab6
Avoid unnecessary calls to cuFuncSetAttribute
rafbiels Feb 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion unified-runtime/source/adapters/cuda/enqueue.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -290,7 +290,9 @@ setKernelParams([[maybe_unused]] const ur_context_handle_t Context,
CuFunc, CU_FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES,
Device->getMaxChosenLocalMem()));

} else {
} else if (LocalSize > 48 * 1024) {
// CUDA requires explicit carveout of dynamic shared memory size if larger
// than 48 kB, otherwise cuLaunchKernel fails.
UR_CHECK_ERROR(cuFuncSetAttribute(
CuFunc, CU_FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES, LocalSize));
}
Expand Down
Loading