Enable basic GPU profiling capability on ROCm. (#26300)
Summary:
Inserting markers using the nvtx-equivalent API is not supported yet.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/26300
Differential Revision: D17425573
Pulled By: bddppq
fbshipit-source-id: 4df6c695ba07ab68e7f4dc2f77edde06f78fdac7