Skip to content

Add some missing CUDA launch checks to benchmark and examples. #150

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
romerojosh merged 1 commit into from
Jul 6, 2026
Merged

Add some missing CUDA launch checks to benchmark and examples. #150

Show file tree
Hide file tree
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
2 changes: 2 additions & 0 deletions benchmark/benchmark.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -593,10 +593,12 @@ int main(int argc, char** argv) {
// Note: excluding scaling from timing
#ifdef R2C
scale<<<(pinfo_x_r.size + 1024 - 1) / 1024, 1024>>>(output_r, 1.0 / fftsize, pinfo_x_r);
CHECK_CUDA_LAUNCH_EXIT();
if (out_of_place) std::swap(input, output);
if (out_of_place) std::swap(input_r, output_r);
#else
scale<<<(pinfo_x_c.size + 1024 - 1) / 1024, 1024>>>(output, 1.0 / fftsize, pinfo_x_c);
CHECK_CUDA_LAUNCH_EXIT();
if (out_of_place) std::swap(input, output);
#endif

Expand Down
10 changes: 10 additions & 0 deletions examples/cc/basic_usage/basic_usage.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,6 +48,15 @@
} \
} while (false)

#define CHECK_CUDA_LAUNCH_EXIT() \
do { \
cudaError_t err = cudaGetLastError(); \
if (cudaSuccess != err) { \
fprintf(stderr, "%s:%d CUDA error. (%s)\n", __FILE__, __LINE__, cudaGetErrorString(err)); \
exit(EXIT_FAILURE); \
} \
} while (false)

#define CHECK_MPI_EXIT(call) \
{ \
int err = call; \
Expand Down Expand Up @@ -223,6 +232,7 @@ int main(int argc, char** argv) {
int threads_per_block = 256;
int nblocks = (pinfo_x.size + threads_per_block - 1) / threads_per_block;
initialize_pencil<<<nblocks, threads_per_block>>>(data_d, pinfo_x);
CHECK_CUDA_LAUNCH_EXIT();

// Allocating cuDecomp workspace

Expand Down
10 changes: 10 additions & 0 deletions examples/cc/basic_usage/basic_usage_autotune.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,6 +48,15 @@
} \
} while (false)

#define CHECK_CUDA_LAUNCH_EXIT() \
do { \
cudaError_t err = cudaGetLastError(); \
if (cudaSuccess != err) { \
fprintf(stderr, "%s:%d CUDA error. (%s)\n", __FILE__, __LINE__, cudaGetErrorString(err)); \
exit(EXIT_FAILURE); \
} \
} while (false)

#define CHECK_MPI_EXIT(call) \
{ \
int err = call; \
Expand Down Expand Up @@ -207,6 +216,7 @@ int main(int argc, char** argv) {
int threads_per_block = 256;
int nblocks = (pinfo_x.size + threads_per_block - 1) / threads_per_block;
initialize_pencil<<<nblocks, threads_per_block>>>(data_d, pinfo_x);
CHECK_CUDA_LAUNCH_EXIT();

// Allocating cuDecomp workspace

Expand Down
Loading