Skip to content

Conversation

shalinib-ibm
Copy link
Owner

The purpose of this patch is to measure gains we would get if we had an xvi8gerpp instruction which accepts both signed inputs. So, we comment out pre and post processing for tinyBLAS_Q0_PPC INt8 implementation

Make sure to read the contributing guidelines before submitting a PR

The purpose of this patch is to measure gains we would get
if we had an xvi8gerpp instruction which accepts both signed inputs.
So, we comment out pre and post processing for tinyBLAS_Q0_PPC INt8 implementation

Signed-off-by: Shalini Salomi Bodapati <[email protected]>
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.

1 participant