Yixin Bao 840e71f4e6 Check CUDA kernel launches (/fbcode/caffe2/) (#49145) ...

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/49145

Pull Request resolved: https://github.com/pytorch/pytorch/pull/49105

(1) Add a safety check `C10_CUDA_KERNEL_LAUNCH_CHECK()` after each kernel launch. This diff only changes the files inside the directory /fbsource/fbcode/caffe2/modules/, /fbsource/fbcode/caffe2/fb/, /fbsource/fbcode/caffe2/test/.

(2) Get rid of old check `AT_CUDA_CHECK(cudaGetLastError())` when necessary.

Test Plan:
Test build:
```
buck build mode/dev-nosan //caffe2/modules/detectron:
buck test mode/dev-nosan //caffe2/modules/detectron:
buck build mode/dev-nosan //caffe2/torch/fb/:
buck test mode/dev-nosan //caffe2/torch/fb/:
```

To check for launches without checks:
```
python3 caffe2/torch/testing/check_kernel_launches.py
```
Make sure none of the updated files are in the returned list.

Reviewed By: r-barnes

Differential Revision: D25452852

fbshipit-source-id: d6657edab612c9e0fa99b29c68460be8b1a20064

2020-12-10 10:43:03 -08:00

..

detectron

Check CUDA kernel launches (/fbcode/caffe2/) (#49145)

2020-12-10 10:43:03 -08:00

module_test

Revert D21369541: Make a separate cmake option for caffe2 tests

2020-05-05 06:30:52 -07:00

observers

Reorganize and refine the Windows.h import in C++ files (#48009)

2020-11-20 14:21:09 -08:00

rocksdb

Remove Caffe2_MAIN_LIBS (#38408)

2020-05-15 12:27:15 -07:00

CMakeLists.txt

Enable detectron on AMD GPU

2019-03-12 16:29:42 -07:00