-
In this page, in the column for "Opcode Class" in the listing of CUTLASS kernels, two of the options are I assume |
Beta Was this translation helpful? Give feedback.
Answered by
hwu36
Apr 18, 2024
Replies: 1 comment
-
|
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
alexarmbr
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
WmmaTensorOp
useswmma.mma
, andTensorOp
usesmma
in this ptx doc . The former is easier to use, the latter is faster.