Skip to content

Add device guards in pytorch cuda kernels. #60

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
hzhangxyz merged 1 commit into from
Jul 2, 2025
Merged

Add device guards in pytorch cuda kernels. #60

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
4 changes: 4 additions & 0 deletions qmb/_hamiltonian_cuda.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
#include <ATen/cuda/Exceptions.h>
#include <c10/cuda/CUDAGuard.h>
#include <c10/cuda/CUDAStream.h>
#include <cuda_runtime.h>
#include <curand_kernel.h>
Expand Down Expand Up @@ -180,6 +181,7 @@ auto apply_within_interface(
std::int64_t batch_size = configs.size(0);
std::int64_t result_batch_size = result_configs.size(0);
std::int64_t term_number = site.size(0);
at::cuda::CUDAGuard cuda_device_guard(device_id);

TORCH_CHECK(configs.device().type() == torch::kCUDA, "configs must be on CUDA.")
TORCH_CHECK(configs.device().index() == device_id, "configs must be on the same device as others.");
Comment thread
hzhangxyz marked this conversation as resolved.
Expand Down Expand Up @@ -560,6 +562,7 @@ auto find_relative_interface(
std::int64_t batch_size = configs.size(0);
std::int64_t term_number = site.size(0);
std::int64_t exclude_size = exclude_configs.size(0);
at::cuda::CUDAGuard cuda_device_guard(device_id);

TORCH_CHECK(configs.device().type() == torch::kCUDA, "configs must be on CUDA.")
TORCH_CHECK(configs.device().index() == device_id, "configs must be on the same device as others.");
Comment thread
hzhangxyz marked this conversation as resolved.
Expand Down Expand Up @@ -779,6 +782,7 @@ auto single_relative_interface(const torch::Tensor& configs, const torch::Tensor
std::int64_t device_id = configs.device().index();
std::int64_t batch_size = configs.size(0);
std::int64_t term_number = site.size(0);
at::cuda::CUDAGuard cuda_device_guard(device_id);

TORCH_CHECK(configs.device().type() == torch::kCUDA, "configs must be on CUDA.")
TORCH_CHECK(configs.device().index() == device_id, "configs must be on the same device as others.");
Comment thread
hzhangxyz marked this conversation as resolved.
Expand Down