High performance matrix multiplication on AMD #15600
Unanswered
Hitman4Reason
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hello, has anyone been able to get even 50% of theoretical performance out of Joint_Matrix multiplication on AMD GPUs?
I am trying to see how fast of an implementation I can get but on AMD's MI250x haven't managed anything above 15TOPS for int8 operands.
Beta Was this translation helpful? Give feedback.
All reactions