Skip to content

[Roofline] Add fma (non-tensorcore) peak flops for CUDA - #13419

Merged
AndrewZhaoLuo merged 1 commit into
apache:mainfrom
tkonolige:roofline_gpu_notensorcore
Nov 21, 2022
Merged

AndrewZhaoLuo merged 1 commit into
apache:mainfrom
tkonolige:roofline_gpu_notensorcore

Commits

Commits on Nov 17, 2022