Skip to content

Add Multi-GPU Parallel Support to Connected Components CUDA Extension #679

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
wants to merge 1 commit into
base: main
Choose a base branch
from
+3 −1
Open

Add Multi-GPU Parallel Support to Connected Components CUDA Extension #679

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: 3 additions & 1 deletion sam2/csrc/connected_components.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -212,6 +212,7 @@ __global__ void final_counting(

std::vector<torch::Tensor> get_connected_componnets(
const torch::Tensor& inputs) {

AT_ASSERTM(inputs.is_cuda(), "inputs must be a CUDA tensor");
AT_ASSERTM(inputs.ndimension() == 4, "inputs must be [N, 1, H, W] shape");
AT_ASSERTM(
Expand Down Expand Up @@ -240,7 +241,8 @@ std::vector<torch::Tensor> get_connected_componnets(
dim3 grid_count =
dim3((W + BLOCK_COLS) / BLOCK_COLS, (H + BLOCK_ROWS) / BLOCK_ROWS);
dim3 block_count = dim3(BLOCK_COLS, BLOCK_ROWS);
cudaStream_t stream = at::cuda::getCurrentCUDAStream();
auto device_idx = inputs.device().index();
cudaStream_t stream = at::cuda::getCurrentCUDAStream(device_idx);

for (int n = 0; n < N; n++) {
uint32_t offset = n * H * W;
Expand Down