Skip to content
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

add AMD specific includes in cuda_prelude.h #3614

Closed
wants to merge 1 commit into from
Closed

add AMD specific includes in cuda_prelude.h #3614

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
15 changes: 15 additions & 0 deletions fbgemm_gpu/include/fbgemm_gpu/utils/cuda_prelude.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,16 +9,31 @@
#pragma once

#include <ATen/ATen.h>

#include <cuda.h>

#ifdef __HIP_PLATFORM_AMD__
#include <ATen/cuda/CUDAGeneratorImpl.h>
#include <ATen/cuda/PhiloxUtils.cuh>

#include <ATen/hip/impl/HIPGuardImplMasqueradingAsCUDA.h> // @manual
#else
#include <ATen/cuda/CUDAGraphsUtils.cuh>
#endif
#include <cassert>

namespace {

inline int get_device_sm_cnt_() {
#ifdef __HIP_PLATFORM_AMD__
hipDeviceProp_t deviceProp;
hipGetDeviceProperties(&deviceProp, c10::hip::current_device());
return deviceProp.multiProcessorCount;
#else
cudaDeviceProp* deviceProp =
at::cuda::getDeviceProperties(c10::cuda::current_device());
return deviceProp->multiProcessorCount;
#endif
}

} // namespace
Expand Down
Loading