Replies: 1 comment
-
|
Hopper adds a bunch of stuff for accelerated intern cluster sync |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
cutlass/include/cutlass/semaphore.h
Line 52 in 5c447dd
I saw similar synchronization mechanism using semaphores between CTAs in cub, do you think it might be good to have an instruction that does this, or will this be a hardware feature in the future generation of GPUs?
Beta Was this translation helpful? Give feedback.
All reactions