Remove test_nccl from ROCM_BLACKLIST and enable only a couple of test_nccl tests (#39354)
Summary:
All individual test_nccl unit tests have been disabled for ROCm in https://github.com/pytorch/pytorch/commit/bf9395438f5ccf0acfcdb2451c8745ec199c7237
test_nccl was also added to the ROCM_BLACKLIST in https://github.com/pytorch/pytorch/commit/87b198d309e00f52e098a533c22b087b36fc00e3
However, the issue only arises when running the test_nccl suite as a whole (as opposed to any one test individually). More details in comments here: https://github.com/pytorch/pytorch/pull/38689
This PR enables test_nccl suite with only two tests so as to workaround the as-yet unresolved issue above, while allowing at least one test_nccl collective test to run on ROCm. This is also needed as a precursor for: https://github.com/pytorch/pytorch/pull/38515
Pull Request resolved: https://github.com/pytorch/pytorch/pull/39354
Differential Revision: D21843194
Pulled By: mrshenli
fbshipit-source-id: b28d1e073d8d0fdc1b59928fc3b00187cfd02a35