Skip to content

[flang][cuda][rt] Do not check error on kernel launch #164463

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 1 commit into from
Oct 21, 2025
Merged

[flang][cuda][rt] Do not check error on kernel launch #164463

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: 5 additions & 5 deletions flang-rt/lib/cuda/kernel.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,8 +76,8 @@ void RTDEF(CUFLaunchKernel)(const void *kernel, intptr_t gridX, intptr_t gridY,
terminator.Crash("Too many invalid grid dimensions");
}
cudaStream_t defaultStream = 0;
CUDA_REPORT_IF_ERROR(cudaLaunchKernel(kernel, gridDim, blockDim, params, smem,
stream != nullptr ? (cudaStream_t)(*stream) : defaultStream));
cudaLaunchKernel(kernel, gridDim, blockDim, params, smem,
stream != nullptr ? (cudaStream_t)(*stream) : defaultStream);
}

void RTDEF(CUFLaunchClusterKernel)(const void *kernel, intptr_t clusterX,
Expand Down Expand Up @@ -153,7 +153,7 @@ void RTDEF(CUFLaunchClusterKernel)(const void *kernel, intptr_t clusterX,
launchAttr[0].val.clusterDim.z = clusterZ;
config.numAttrs = 1;
config.attrs = launchAttr;
CUDA_REPORT_IF_ERROR(cudaLaunchKernelExC(&config, kernel, params));
cudaLaunchKernelExC(&config, kernel, params);
}

void RTDEF(CUFLaunchCooperativeKernel)(const void *kernel, intptr_t gridX,
Expand Down Expand Up @@ -218,8 +218,8 @@ void RTDEF(CUFLaunchCooperativeKernel)(const void *kernel, intptr_t gridX,
terminator.Crash("Too many invalid grid dimensions");
}
cudaStream_t defaultStream = 0;
CUDA_REPORT_IF_ERROR(cudaLaunchCooperativeKernel(kernel, gridDim, blockDim,
params, smem, stream != nullptr ? (cudaStream_t)*stream : defaultStream));
cudaLaunchCooperativeKernel(kernel, gridDim, blockDim, params, smem,
stream != nullptr ? (cudaStream_t)*stream : defaultStream);
}

} // extern "C"
Loading