Skip to content

GitLab

Unverified Commit 7b5075fc authored by Francisco Massa's avatar Francisco Massa Committed by GitHub
Browse files

Fix CUDA builds on Windows (#1485)

parent 53b062ca
Show whitespace changes
Inline Side-by-side
Showing with 16 additions and 4 deletions
torchvision/csrc/cuda/PSROIAlign_cuda.cu
View file @ 7b5075fc
...@@ -336,7 +336,10 @@ std::tuple<at::Tensor, at::Tensor> PSROIAlign_forward_cuda( ...@@ -336,7 +336,10 @@ std::tuple<at::Tensor, at::Tensor> PSROIAlign_forward_cuda(
cudaStream_t stream = at::cuda::getCurrentCUDAStream(); cudaStream_t stream = at::cuda::getCurrentCUDAStream();
dim3 grid(std::min(at::cuda::ATenCeilDiv(output_size, 512L), 4096L)); dim3 grid(std::min(
at::cuda::ATenCeilDiv(
static_cast<int64_t>(output_size), static_cast<int64_t>(512)),
static_cast<int64_t>(4096)));
dim3 block(512); dim3 block(512);
AT_DISPATCH_FLOATING_TYPES_AND_HALF( AT_DISPATCH_FLOATING_TYPES_AND_HALF(
...@@ -395,7 +398,10 @@ at::Tensor PSROIAlign_backward_cuda( ...@@ -395,7 +398,10 @@ at::Tensor PSROIAlign_backward_cuda(
cudaStream_t stream = at::cuda::getCurrentCUDAStream(); cudaStream_t stream = at::cuda::getCurrentCUDAStream();
dim3 grid(std::min(at::cuda::ATenCeilDiv(grad.numel(), 512L), 4096L)); dim3 grid(std::min(
at::cuda::ATenCeilDiv(
static_cast<int64_t>(grad.numel()), static_cast<int64_t>(512)),
static_cast<int64_t>(4096)));
dim3 block(512); dim3 block(512);
// handle possibly empty gradients // handle possibly empty gradients
......
torchvision/csrc/cuda/PSROIPool_cuda.cu
View file @ 7b5075fc
...@@ -173,7 +173,10 @@ std::tuple<at::Tensor, at::Tensor> PSROIPool_forward_cuda( ...@@ -173,7 +173,10 @@ std::tuple<at::Tensor, at::Tensor> PSROIPool_forward_cuda(
cudaStream_t stream = at::cuda::getCurrentCUDAStream(); cudaStream_t stream = at::cuda::getCurrentCUDAStream();
dim3 grid(std::min(at::cuda::ATenCeilDiv(output_size, 512L), 4096L)); dim3 grid(std::min(
at::cuda::ATenCeilDiv(
static_cast<int64_t>(output_size), static_cast<int64_t>(512)),
static_cast<int64_t>(4096)));
dim3 block(512); dim3 block(512);
AT_DISPATCH_FLOATING_TYPES_AND_HALF( AT_DISPATCH_FLOATING_TYPES_AND_HALF(
...@@ -229,7 +232,10 @@ at::Tensor PSROIPool_backward_cuda( ...@@ -229,7 +232,10 @@ at::Tensor PSROIPool_backward_cuda(
cudaStream_t stream = at::cuda::getCurrentCUDAStream(); cudaStream_t stream = at::cuda::getCurrentCUDAStream();
dim3 grid(std::min(at::cuda::ATenCeilDiv(grad.numel(), 512L), 4096L)); dim3 grid(std::min(
at::cuda::ATenCeilDiv(
static_cast<int64_t>(grad.numel()), static_cast<int64_t>(512)),
static_cast<int64_t>(4096)));
dim3 block(512); dim3 block(512);
// handle possibly empty gradients // handle possibly empty gradients
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment