PyTorch patch for building on JetPack 4.2 / 4.3

pytorch-diff-jetpack-4.2.patch

diff --git a/aten/src/ATen/cuda/CUDAContext.cpp b/aten/src/ATen/cuda/CUDAContext.cpp
index e48c020b03..0ecc111c4b 100644
--- a/aten/src/ATen/cuda/CUDAContext.cpp
+++ b/aten/src/ATen/cuda/CUDAContext.cpp
@@ -24,6 +24,8 @@ void initCUDAContextVectors() {
 void initDeviceProperty(DeviceIndex device_index) {
   cudaDeviceProp device_prop;
   AT_CUDA_CHECK(cudaGetDeviceProperties(&device_prop, device_index));
+  // patch for "too many resources requested for launch"
+  device_prop.maxThreadsPerBlock = device_prop.maxThreadsPerBlock / 2;
   device_properties[device_index] = device_prop;
 }
 
diff --git a/aten/src/ATen/cuda/detail/KernelUtils.h b/aten/src/ATen/cuda/detail/KernelUtils.h
index af788ff8f8..fb27ab808c 100644
--- a/aten/src/ATen/cuda/detail/KernelUtils.h
+++ b/aten/src/ATen/cuda/detail/KernelUtils.h
@@ -19,7 +19,10 @@ namespace at { namespace cuda { namespace detail {
   for (int i=_i_n_d_e_x; _i_n_d_e_x < (n); _i_n_d_e_x+=blockDim.x * gridDim.x, i=_i_n_d_e_x)
 
 // Use 1024 threads per block, which requires cuda sm_2x or above
-constexpr int CUDA_NUM_THREADS = 1024;
+//constexpr int CUDA_NUM_THREADS = 1024;
+
+// patch for "too many resources requested for launch"
+constexpr int CUDA_NUM_THREADS = 512;
 
 // CUDA: number of blocks for threads.
 inline int GET_BLOCKS(const int N)
diff --git a/aten/src/THCUNN/common.h b/aten/src/THCUNN/common.h
index 61cd90cdd6..cec1fa2698 100644
--- a/aten/src/THCUNN/common.h
+++ b/aten/src/THCUNN/common.h
@@ -5,7 +5,10 @@
   "Some of weight/gradient/input tensors are located on different GPUs. Please move them to a single one.")
 
 // Use 1024 threads per block, which requires cuda sm_2x or above
-const int CUDA_NUM_THREADS = 1024;
+//const int CUDA_NUM_THREADS = 1024;
+
+// patch for "too many resources requested for launch"
+const int CUDA_NUM_THREADS = 512;
 
 // CUDA: number of blocks for threads.
 inline int GET_BLOCKS(const int N)