Skip to content

[flang][cuda] Remove error check from allocation and free call #165022

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 24, 2025
+9 −12
Merged

[flang][cuda] Remove error check from allocation and free call #165022

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 9 additions & 12 deletions flang-rt/lib/cuda/allocator.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -138,23 +138,21 @@ void RTDEF(CUFRegisterAllocator)() {
void *CUFAllocPinned(
std::size_t sizeInBytes, [[maybe_unused]] std::int64_t *asyncObject) {
void *p;
CUDA_REPORT_IF_ERROR(cudaMallocHost((void **)&p, sizeInBytes));
cudaMallocHost((void **)&p, sizeInBytes);
return p;
}

void CUFFreePinned(void *p) { CUDA_REPORT_IF_ERROR(cudaFreeHost(p)); }
void CUFFreePinned(void *p) { cudaFreeHost(p); }

void *CUFAllocDevice(std::size_t sizeInBytes, std::int64_t *asyncObject) {
void *p;
if (Fortran::runtime::executionEnvironment.cudaDeviceIsManaged) {
CUDA_REPORT_IF_ERROR(
cudaMallocManaged((void **)&p, sizeInBytes, cudaMemAttachGlobal));
cudaMallocManaged((void **)&p, sizeInBytes, cudaMemAttachGlobal);
} else {
if (asyncObject == nullptr) {
CUDA_REPORT_IF_ERROR(cudaMalloc(&p, sizeInBytes));
cudaMalloc(&p, sizeInBytes);
} else {
CUDA_REPORT_IF_ERROR(
cudaMallocAsync(&p, sizeInBytes, (cudaStream_t)*asyncObject));
cudaMallocAsync(&p, sizeInBytes, (cudaStream_t)*asyncObject);
insertAllocation(p, sizeInBytes, (cudaStream_t)*asyncObject);
}
}
Expand All @@ -167,21 +165,20 @@ void CUFFreeDevice(void *p) {
if (pos >= 0) {
cudaStream_t stream = deviceAllocations[pos].stream;
eraseAllocation(pos);
CUDA_REPORT_IF_ERROR(cudaFreeAsync(p, stream));
cudaFreeAsync(p, stream);
} else {
CUDA_REPORT_IF_ERROR(cudaFree(p));
cudaFree(p);
}
}

void *CUFAllocManaged(
std::size_t sizeInBytes, [[maybe_unused]] std::int64_t *asyncObject) {
void *p;
CUDA_REPORT_IF_ERROR(
cudaMallocManaged((void **)&p, sizeInBytes, cudaMemAttachGlobal));
cudaMallocManaged((void **)&p, sizeInBytes, cudaMemAttachGlobal);
return reinterpret_cast<void *>(p);
}

void CUFFreeManaged(void *p) { CUDA_REPORT_IF_ERROR(cudaFree(p)); }
void CUFFreeManaged(void *p) { cudaFree(p); }

void *CUFAllocUnified(
std::size_t sizeInBytes, [[maybe_unused]] std::int64_t *asyncObject) {
Expand Down
Loading