Skip to content

Limit managed memory usage to platforms that support it. Compile for cc75. #13

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

Open
romerojosh wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Limit managed memory usage to platforms that support it. Compile for cc75. #13

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 CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ endif()
#decide whether to use CUDA or not
#find_package(CUDAToolkit REQUIRED)
if(NOT CUDA_COMPUTE_CAPABILITY)
set(CUDA_COMPUTE_CAPABILITY 70 80)
set(CUDA_COMPUTE_CAPABILITY 70 75 80)
endif()

#Find OpenMP
Expand Down
10 changes: 8 additions & 2 deletions cuslines/cuslines.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -141,8 +141,14 @@ class GPUTracker {
//#pragma omp parallel for
for (int n = 0; n < ngpus_; ++n) {
CHECK_CUDA(cudaSetDevice(n));
CHECK_CUDA(cudaMallocManaged(&dataf_d[n], sizeof(*dataf_d[n]) * dataf_info.size));
CHECK_CUDA(cudaMemAdvise(dataf_d[n], sizeof(*dataf_d[n]) * dataf_info.size, cudaMemAdviseSetPreferredLocation, n));
int managed_supported;
CHECK_CUDA(cudaDeviceGetAttribute(&managed_supported, cudaDevAttrConcurrentManagedAccess, n));
if (managed_supported) {
CHECK_CUDA(cudaMallocManaged(&dataf_d[n], sizeof(*dataf_d[n]) * dataf_info.size));
CHECK_CUDA(cudaMemAdvise(dataf_d[n], sizeof(*dataf_d[n]) * dataf_info.size, cudaMemAdviseSetPreferredLocation, n));
} else {
CHECK_CUDA(cudaMalloc(&dataf_d[n], sizeof(*dataf_d[n]) * dataf_info.size));
}
CHECK_CUDA(cudaMalloc(&H_d[n], sizeof(*H_d[n]) * H_info.size));
CHECK_CUDA(cudaMalloc(&R_d[n], sizeof(*R_d[n]) * R_info.size));
CHECK_CUDA(cudaMalloc(&delta_b_d[n], sizeof(*delta_b_d[n]) * delta_b_info.size));
Expand Down