ggml-cpu: Enable tiled matmul on AIX#25199
Merged
Merged
Conversation
github-actions
Bot
added
the
ggml
Contributor
Author
|
@taronaeo @ggerganov Can you please help review this PR ? |
taronaeo
approved these changes
Jul 2, 2026
Contributor
Author
|
Thanks @taronaeo . I've addressed your review comments. Can you please take a look ? |
taronaeo
reviewed
Jul 3, 2026
| #else | ||
| int64_t mc = 256; int64_t nc = 256; int64_t kc = 256; | ||
| #if defined(_AIX) || defined(__BIG_ENDIAN__) | ||
| mc = 128; nc = 128; kc = 128; |
The matmul_tiled path uses large local stack buffers for A_pack and B_pack. On AIX this can trigger a segmentation fault, so reduce the buffer footprint there to keep the tiled path usable.
Performance Impact:
~ 2x gains in PP_Speed for FP32, Q4_0 and Q8_0 models tested with llama-bench, llama-batched-bench and llama-cli.
Models used: Llama3.2 3b Instruct F32, qwen 2.5 3b Q4_0 and Q8_0
taronaeo
approved these changes
Jul 3, 2026
Member
|
@ggml-org/maintainers Another approval please. |
lhez
approved these changes
Jul 3, 2026
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The matmul_tiled path uses large local stack buffers for A_pack and B_pack. On AIX this can trigger a segmentation fault, so reduce the buffer footprint there to keep the tiled path usable.
Performance Impact:
~ 2x gains in PP_Speed for FP32, Q4_0 and Q8_0 models tested with llama-bench, llama-batched-bench and llama-cli.
Models used: Llama3.2 3b Instruct F32, qwen 2.5 3b Q4_0 and Q8_0
Overview
Additional information
Requirements