Skip to content

Allow GPU oversubscription in test programs. #130

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
romerojosh merged 1 commit into from
May 6, 2026
Merged

Allow GPU oversubscription in test programs. #130

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
8 changes: 7 additions & 1 deletion tests/cc/halo_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -510,7 +510,13 @@ int main(int argc, char** argv) {
MPI_Comm_split_type(MPI_COMM_WORLD, MPI_COMM_TYPE_SHARED, 0, MPI_INFO_NULL, &local_comm);
int local_rank;
MPI_Comm_rank(local_comm, &local_rank);
CHECK_CUDA_EXIT(cudaSetDevice(local_rank));
int num_devices = 0;
CHECK_CUDA_EXIT(cudaGetDeviceCount(&num_devices));
if (num_devices <= 0) {
fprintf(stderr, "No CUDA devices available.\n");
exit(EXIT_FAILURE);
}
CHECK_CUDA_EXIT(cudaSetDevice(local_rank % num_devices));

// Check if test file was provided
std::string testfile;
Expand Down
8 changes: 7 additions & 1 deletion tests/cc/transpose_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -574,7 +574,13 @@ int main(int argc, char** argv) {
MPI_Comm_split_type(MPI_COMM_WORLD, MPI_COMM_TYPE_SHARED, 0, MPI_INFO_NULL, &local_comm);
int local_rank;
MPI_Comm_rank(local_comm, &local_rank);
CHECK_CUDA_EXIT(cudaSetDevice(local_rank));
int num_devices = 0;
CHECK_CUDA_EXIT(cudaGetDeviceCount(&num_devices));
if (num_devices <= 0) {
fprintf(stderr, "No CUDA devices available.\n");
exit(EXIT_FAILURE);
}
CHECK_CUDA_EXIT(cudaSetDevice(local_rank % num_devices));

// Check if test file was provided
std::string testfile;
Expand Down
9 changes: 7 additions & 2 deletions tests/fortran/halo_test.f90
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -529,7 +529,7 @@ program main

integer :: i, idx
real(real64) :: t0
integer :: local_rank, ierr
integer :: local_rank, ierr, num_devices
integer :: local_comm
integer :: res, retcode
logical :: using_testfile
Expand All @@ -546,7 +546,12 @@ program main

call MPI_Comm_split_Type(MPI_COMM_WORLD, MPI_COMM_TYPE_SHARED, 0, MPI_INFO_NULL, local_comm, ierr)
call MPI_Comm_rank(local_comm, local_rank, ierr)
CHECK_CUDA_EXIT(cudaSetDevice(local_rank))
CHECK_CUDA_EXIT(cudaGetDeviceCount(num_devices))
if (num_devices <= 0) then
print*, 'No CUDA devices available.'
call exit(1)
endif
CHECK_CUDA_EXIT(cudaSetDevice(mod(local_rank, num_devices)))

using_testfile = .false.
do i = 1, command_argument_count()
Expand Down
9 changes: 7 additions & 2 deletions tests/fortran/transpose_test.f90
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -554,7 +554,7 @@ program main

integer :: i, idx
real(real64) :: t0
integer :: local_rank, ierr
integer :: local_rank, ierr, num_devices
integer :: local_comm
integer :: res, retcode
logical :: using_testfile
Expand All @@ -571,7 +571,12 @@ program main

call MPI_Comm_split_Type(MPI_COMM_WORLD, MPI_COMM_TYPE_SHARED, 0, MPI_INFO_NULL, local_comm, ierr)
call MPI_Comm_rank(local_comm, local_rank, ierr)
CHECK_CUDA_EXIT(cudaSetDevice(local_rank))
CHECK_CUDA_EXIT(cudaGetDeviceCount(num_devices))
if (num_devices <= 0) then
print*, 'No CUDA devices available.'
call exit(1)
endif
CHECK_CUDA_EXIT(cudaSetDevice(mod(local_rank, num_devices)))

using_testfile = .false.
do i = 1, command_argument_count()
Expand Down
Loading