Add Kernel Launch Checks to files under caffe2/aten/THC (#49358)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/49358
Added the header file (`c10/cuda/CUDAException.h`) where the `C10_CUDA_KERNEL_LAUNCH_CHECK` is defined as needed to files under `caffe2/aten/THC`, and then added `C10_CUDA_KERNEL_LAUNCH_CHECK()` calls after each kernel launch. In some cases, removed some extraneous ErrorChecks
Test Plan:
Checked that the code still builds with
```
buck build //caffe2/aten:ATen-cu
```
Also ran basic aten tests
```
buck test //caffe2/aten:atest
```
Reviewed By: r-barnes
Differential Revision: D25541113
fbshipit-source-id: df1a50e14d291a86b24ca1746ac27fa586f9757c
