Skip to content

cuda-ref: use cudaMemcpyAsync for QFunction context #2007

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
jeremylt merged 1 commit into from
Aug 19, 2026
Merged

cuda-ref: use cudaMemcpyAsync for QFunction context #2007

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
10 changes: 1 addition & 9 deletions backends/cuda-ref/ceed-cuda-ref-qfunctioncontext.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,15 +37,7 @@ static inline int CeedQFunctionContextSyncH2D_Cuda(const CeedQFunctionContext ct
impl->d_data = impl->d_data_owned;
}

// Use async memcpy during CUDA Graph capture for compatibility
enum cudaStreamCaptureStatus capture_status;

cudaStreamIsCapturing(cudaStreamPerThread, &capture_status);
if (capture_status != cudaStreamCaptureStatusNone) {
CeedCallCuda(ceed, cudaMemcpyAsync(impl->d_data, impl->h_data, ctx_size, cudaMemcpyHostToDevice, cudaStreamPerThread));
} else {
CeedCallCuda(ceed, cudaMemcpy(impl->d_data, impl->h_data, ctx_size, cudaMemcpyHostToDevice));
}
CeedCallCuda(ceed, cudaMemcpyAsync(impl->d_data, impl->h_data, ctx_size, cudaMemcpyHostToDevice, cudaStreamPerThread));

CeedCallBackend(CeedDestroy(&ceed));
return CEED_ERROR_SUCCESS;
Expand Down
Loading