Enable -Wunused-value in vision/PACKAGE +1

Summary:
This diff enables compilation warning flags for the directory in question. Further details are in [this workplace post](https://fb.workplace.com/permalink.php?story_fbid=pfbid02XaWNiCVk69r1ghfvDVpujB8Hr9Y61uDvNakxiZFa2jwiPHscVdEQwCBHrmWZSyMRl&id=100051201402394).

This is a low-risk diff. There are **no run-time effects** and the diff has already been observed to compile locally. **If the code compiles, it work; test errors are spurious.**

Differential Revision: D70282347

fbshipit-source-id: e2fa55c002d7124b13450c812165d244b8a53f4e

Author: r-barnes

pytorch3d/csrc/pulsar/pytorch/tensor_util.cpp

@@ -8,6 +8,7 @@
 
 #ifdef WITH_CUDA
 #include <ATen/cuda/CUDAContext.h>
+#include <c10/cuda/CUDAException.h>
 #include <cuda_runtime_api.h>
 #endif
 #include <torch/extension.h>
@@ -33,13 +34,13 @@ torch::Tensor sphere_ids_from_result_info_nograd(
           .contiguous();
   if (forw_info.device().type() == c10::DeviceType::CUDA) {
 #ifdef WITH_CUDA
-    cudaMemcpyAsync(
+    C10_CUDA_CHECK(cudaMemcpyAsync(
         result.data_ptr(),
         tmp.data_ptr(),
         sizeof(uint32_t) * tmp.size(0) * tmp.size(1) * tmp.size(2) *
             tmp.size(3),
         cudaMemcpyDeviceToDevice,
-        at::cuda::getCurrentCUDAStream());
+        at::cuda::getCurrentCUDAStream()));
 #else
     throw std::runtime_error(
         "Copy on CUDA device initiated but built "

pytorch3d/csrc/pulsar/pytorch/util.cpp

@@ -7,6 +7,7 @@
  */
 
 #ifdef WITH_CUDA
+#include <c10/cuda/CUDAException.h>
 #include <cuda_runtime_api.h>
 
 namespace pulsar {
@@ -17,15 +18,17 @@ void cudaDevToDev(
     const void* src,
     const int& size,
     const cudaStream_t& stream) {
-  cudaMemcpyAsync(trg, src, size, cudaMemcpyDeviceToDevice, stream);
+  C10_CUDA_CHECK(
+      cudaMemcpyAsync(trg, src, size, cudaMemcpyDeviceToDevice, stream));
 }
 
 void cudaDevToHost(
     void* trg,
     const void* src,
     const int& size,
     const cudaStream_t& stream) {
-  cudaMemcpyAsync(trg, src, size, cudaMemcpyDeviceToHost, stream);
+  C10_CUDA_CHECK(
+      cudaMemcpyAsync(trg, src, size, cudaMemcpyDeviceToHost, stream));
 }
 
 } // namespace pytorch