Wenkai Du 481a35bc59 Fix memory fence and use non-temporal store (#1007) ...

* Fix memory fence and use non-temporal store

* Use amdgcn builtin instead of inline asm

* Move threadfence location

* Revert changes to gfx90a

* Rework gfx90a change

* Apply changes to gfx94x

[ROCm/rccl commit: 7965c8b53c]

2023-12-09 12:16:08 -08:00

projects/rccl

Fix memory fence and use non-temporal store (#1007)

2023-12-09 12:16:08 -08:00

S

Descrição

Descrição não fornecida

282 MiB

Linguagens

C++ 67.5%

C 20.6%

Python 6.6%

CMake 3.4%

Shell 0.6%

Outra 1.1%