9b48f92d724faec0886a731c9494825b1c8440b9
* Changing default timing mechanism, adjusting CPU bandwidth calc, adding flag to use combined timing
* Adding support for smaller transfers (byte size must be multiple of 4 instead of 128)
[ROCm/rccl commit: b80ae551b1]
Описание
No description provided
Languages
C++
67.5%
C
20.6%
Python
6.6%
CMake
3.4%
Shell
0.6%
Разное
1.1%