ggml-cpu : Add Power12 MMA+ INT8 matmul kernels#24
Open
shalinib-ibm wants to merge 1 commit into
Open
Conversation
- Implement int8 matmul kernels using Power12 MMA+ builtins,
leveraging 128-bit dense math registers.
- Refactor code to separate Power10 and Power12 implementations
with zero runtime overhead.
- Add a standalone test for int8 matmul with configurable
dimensions (m, n, k). This can be used for functional validation.
Example:
./llama-bench-matmult -t 10 -i 1 -m 48 -n 20 -k 1
Signed-off-by: Bodapati Shalini Salomi <bodapatishalinisalomi@Bodapatis-MacBook-Pro.local>
shalinib-ibm
force-pushed
the
int8_mmaplus_p12_kernels
branch
from
fd5d5aa to
6ad0a75
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Implement int8 matmul kernels using Power12 MMA+ builtins, leveraging 1024-bit dense math registers.
Refactor code to separate Power10 and Power12 implementations of kernels for readability
Add a standalone test for int8 matmul with configurable dimensions (m, n, k). This can be used for functional validation.
Example: ./llama-bench-matmult -t 10 -i 1 -m 48 -n 20 -k 1
Overview
Additional information
Requirements