Skip to content

Do no use bit_cast to work around initialization issues with barrier #6263

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 16, 2025
Merged

Do no use bit_cast to work around initialization issues with barrier #6263

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: 1 addition & 1 deletion libcudacxx/test/libcudacxx/cuda/barrier/cp_async_bulk.pass.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@ __device__ void test()
alignas(16) __shared__ int smem_buffer[buf_len];
#if _CCCL_CUDA_COMPILER(CLANG)
__shared__ char barrier_data[sizeof(barrier)];
barrier& bar = cuda::std::bit_cast<barrier>(barrier_data);
barrier& bar = reinterpret_cast<barrier&>(barrier_data);
#else // ^^^ _CCCL_CUDA_COMPILER(CLANG) ^^^ / vvv !_CCCL_CUDA_COMPILER(CLANG)
__shared__ barrier bar;
#endif // !_CCCL_CUDA_COMPILER(CLANG)
Expand Down
4 changes: 2 additions & 2 deletions libcudacxx/test/libcudacxx/cuda/barrier/cp_async_bulk_ptx_compiles.pass.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ __global__ void test_bulk_tensor(CUtensorMap* map)
__shared__ int smem;
#if _CCCL_CUDA_COMPILER(CLANG)
__shared__ char barrier_data[sizeof(barrier)];
barrier& bar = cuda::std::bit_cast<barrier>(barrier_data);
barrier& bar = reinterpret_cast<barrier&>(barrier_data);
#else // ^^^ _CCCL_CUDA_COMPILER(CLANG) ^^^ / vvv !_CCCL_CUDA_COMPILER(CLANG)
__shared__ barrier bar;
#endif // !_CCCL_CUDA_COMPILER(CLANG)
Expand All @@ -57,7 +57,7 @@ __global__ void test_bulk(void* gmem)
{
__shared__ int smem;
__shared__ char barrier_data[sizeof(barrier)];
barrier& bar = *reinterpret_cast<barrier*>(&barrier_data);
barrier& bar = reinterpret_cast<barrier&>(barrier_data);
if (threadIdx.x == 0)
{
init(&bar, blockDim.x);
Expand Down
2 changes: 1 addition & 1 deletion libcudacxx/test/libcudacxx/cuda/barrier/cp_async_bulk_tensor.pass.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,7 +70,7 @@ __device__ void test(int base_i, int base_j)
alignas(128) __shared__ int smem_buffer[buf_len];
#if _CCCL_CUDA_COMPILER(CLANG)
__shared__ char barrier_data[sizeof(barrier)];
barrier& bar = cuda::std::bit_cast<barrier>(barrier_data);
barrier& bar = reinterpret_cast<barrier&>(barrier_data);
#else // ^^^ _CCCL_CUDA_COMPILER(CLANG) ^^^ / vvv !_CCCL_CUDA_COMPILER(CLANG)
__shared__ barrier bar;
#endif // !_CCCL_CUDA_COMPILER(CLANG)
Expand Down
2 changes: 1 addition & 1 deletion libcudacxx/test/libcudacxx/cuda/barrier/cp_async_bulk_tensor_generic.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -187,7 +187,7 @@ test(cuda::std::array<uint32_t, num_dims> smem_coord,
alignas(128) __shared__ int smem_buffer[smem_len];
#if _CCCL_CUDA_COMPILER(CLANG)
__shared__ char barrier_data[sizeof(barrier)];
barrier& bar = cuda::std::bit_cast<barrier>(barrier_data);
barrier& bar = reinterpret_cast<barrier&>(barrier_data);
#else // ^^^ _CCCL_CUDA_COMPILER(CLANG) ^^^ / vvv !_CCCL_CUDA_COMPILER(CLANG)
__shared__ barrier bar;
#endif // !_CCCL_CUDA_COMPILER(CLANG)
Expand Down