diff options
| author | Yong He <yonghe@outlook.com> | 2023-04-13 09:49:22 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-04-13 09:49:22 -0700 |
| commit | 813892cd023e216f6f6560eb47566522d3a82609 (patch) | |
| tree | 07cbf8851e0c178cbc895be73e17e6340cc22685 /prelude | |
| parent | 352a460fc866998da5f45a8c117d891c51ab5a47 (diff) | |
Set sharedMem argument to 0 when launching cuda kernel. (#2799)
Co-authored-by: Yong He <yhe@nvidia.com>
Diffstat (limited to 'prelude')
| -rw-r--r-- | prelude/slang-torch-prelude.h | 8 |
1 files changed, 0 insertions, 8 deletions
diff --git a/prelude/slang-torch-prelude.h b/prelude/slang-torch-prelude.h index 03a00719d..2f5273e1f 100644 --- a/prelude/slang-torch-prelude.h +++ b/prelude/slang-torch-prelude.h @@ -114,12 +114,4 @@ TensorView make_tensor_view(torch::Tensor val, const char* name, torch::ScalarTy return res; } -size_t slangGetCudaKernelSharedMemSize(const void* func) -{ - cudaFuncAttributes attr = {}; - cudaFuncGetAttributes(&attr, func); - AT_CUDA_CHECK(cudaGetLastError()); - return attr.sharedSizeBytes; -} - #define SLANG_PRELUDE_EXPORT |