Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

additional optimizations for POWER9 #454

Merged
merged 1 commit into from
Mar 24, 2023
Merged

additional optimizations for POWER9 #454

merged 1 commit into from
Mar 24, 2023

Conversation

classilla
Copy link
Contributor

This adds further optimizations for POWER9 CPUs (tested on Fedora with a dual-8 64-thread system):

  • use -mcpu=power9 for both C and C++, implies -mpower9-vector and everything else
  • use VSX half-precision conversion for F16 <-> F32
  • vectorized quantize_row_q4_0

@ggerganov ggerganov merged commit 481044d into ggerganov:master Mar 24, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants