Add build option to split torch_cuda library into torch_cuda_cu and torch_cuda_cpp (#49050)
Summary:
Because of the size of our `libtorch_cuda.so`, linking with other hefty binaries presents a problem where 32bit relocation markers are too small and end up overflowing. This PR attempts to break up `torch_cuda` into `torch_cuda_cu` and `torch_cuda_cpp`.
`torch_cuda_cu`: all the files previously in `Caffe2_GPU_SRCS` that are
* pure `.cu` files in `aten`match
* all the BLAS files
* all the THC files, except for THCAllocator.cpp, THCCachingHostAllocator.cpp and THCGeneral.cpp
* all files in`detail`
* LegacyDefinitions.cpp and LegacyTHFunctionsCUDA.cpp
* Register*CUDA.cpp
* CUDAHooks.cpp
* CUDASolver.cpp
* TensorShapeCUDA.cpp
`torch_cuda_cpp`: all other files in `Caffe2_GPU_SRCS`
Accordingly, TORCH_CUDA_API and TORCH_CUDA_BUILD_MAIN_LIB usages are getting split as well to TORCH_CUDA_CU_API and TORCH_CUDA_CPP_API.
To test this locally, you can run `export BUILD_SPLIT_CUDA=ON && python setup.py develop`. In your `build/lib` folder, you should find binaries for both `torch_cuda_cpp` and `torch_cuda_cu`. To see that the SPLIT_CUDA option was toggled, you can grep the Summary of running cmake and make sure `Split CUDA` is ON.
This build option is tested on CI for CUDA 11.1 builds (linux for now, but windows soon).
Pull Request resolved: https://github.com/pytorch/pytorch/pull/49050
Reviewed By: walterddr
Differential Revision: D26114310
Pulled By: janeyx99
fbshipit-source-id: 0180f2519abb5a9cdde16a6fb7dd3171cff687a6
