Wenkai Du 98609a7b92 Define ncclShmem as global shared (#618) ...

* Use global defined shared memory

* Add --hipcc-func-supp to compile option

* Force inline some device functions

* Add back threadfence

[ROCm/rccl commit: 9e6c87a2bf]

2022-09-20 09:00:20 -07:00

projects/rccl

Define ncclShmem as global shared (#618)

2022-09-20 09:00:20 -07:00

S

Description

No description provided

282 MiB

Languages

C++ 67.5%

C 20.6%

Python 6.6%

CMake 3.4%

Shell 0.6%

Other 1.1%