alex-breslow-amd 455d516dc4 [gfx950] Make bypassing __threadfence the default for multinode. (#1947) ...

* Gate based on ROCM version, safe for ROCm 7.0.2 and beyond.
* Updates naming to gfx9CheapFenceOff since we use this for gfx942 and gfx950.  Thanks Nilesh.
* Add info logging statement to NCCL_INIT to print whether enabled when INFO logging is enabled.

[ROCm/rccl commit: c70f5b4621]

2025-10-15 09:15:36 -07:00

projects/rccl

[gfx950] Make bypassing __threadfence the default for multinode. (#1947)

2025-10-15 09:15:36 -07:00

S

توضیحات

No description provided

282 MiB

Languages

C++ 67.5%

C 20.6%

Python 6.6%

CMake 3.4%

Shell 0.6%

دیگر 1.1%