Skip to content

Migrate THCDeviceUtils to ATen #91

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
we-lu wants to merge 1 commit into
base: pytorch_1.0.0
Choose a base branch
from
Open

Migrate THCDeviceUtils to ATen #91

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
17 changes: 8 additions & 9 deletions src/cuda/deform_psroi_pooling_cuda.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,11 +13,10 @@
#include <iostream>

#include <ATen/ATen.h>
#include <ATen/ceil_div.h>
#include <ATen/cuda/CUDAContext.h>

#include <THC/THC.h>
#include <THC/THCAtomics.cuh>
#include <THC/THCDeviceUtils.cuh>

#define CUDA_KERNEL_LOOP(i, n) \
for (int i = blockIdx.x * blockDim.x + threadIdx.x; \
Expand Down Expand Up @@ -307,11 +306,11 @@ deform_psroi_pooling_cuda_forward(const at::Tensor &input,

if (out.numel() == 0)
{
THCudaCheck(cudaGetLastError());
C10_CUDA_CHECK(cudaGetLastError());
return std::make_tuple(out, top_count);
}

dim3 grid(std::min(THCCeilDiv(out_size, 512L), 4096L));
dim3 grid(std::min(at::ceil_div(out_size, 512L), 4096L));
dim3 block(512);

AT_DISPATCH_FLOATING_TYPES(input.type(), "deform_psroi_pooling_cuda_forward", [&] {
Expand All @@ -336,7 +335,7 @@ deform_psroi_pooling_cuda_forward(const at::Tensor &input,
out.data<scalar_t>(),
top_count.data<scalar_t>());
});
THCudaCheck(cudaGetLastError());
C10_CUDA_CHECK(cudaGetLastError());
return std::make_tuple(out, top_count);
}

Expand Down Expand Up @@ -380,11 +379,11 @@ deform_psroi_pooling_cuda_backward(const at::Tensor &out_grad,

if (input_grad.numel() == 0)
{
THCudaCheck(cudaGetLastError());
C10_CUDA_CHECK(cudaGetLastError());
return std::make_tuple(input_grad, trans_grad);
}

dim3 grid(std::min(THCCeilDiv(out_size, 512L), 4096L));
dim3 grid(std::min(at::ceil_div(out_size, 512L), 4096L));
dim3 block(512);
cudaStream_t stream = at::cuda::getCurrentCUDAStream();

Expand Down Expand Up @@ -414,6 +413,6 @@ deform_psroi_pooling_cuda_backward(const at::Tensor &out_grad,
num_classes,
channels_each_class);
});
THCudaCheck(cudaGetLastError());
C10_CUDA_CHECK(cudaGetLastError());
return std::make_tuple(input_grad, trans_grad);
}
}