Skip to content

Throughput improvement for small batch sizes #17342

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.

Sign up for GitHub

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

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
+1 −5
Open

Throughput improvement for small batch sizes #17342

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 1 addition & 5 deletions ggml/src/ggml-cpu/llamafile/sgemm.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -446,10 +446,7 @@ class tinyBLAS {
ggml_threadpool_chunk_set(params->threadpool, params->nth);
}

ggml_barrier(params->threadpool);

int64_t job = params->ith;
while (job < nb_job) {
for (int64_t job = params->ith; job < nb_job; job += params->nth) {
const int64_t ii = (job % ytiles) * RM * BM;
const int64_t jb = job / ytiles;
const int64_t jr0 = BLOC_POS(jb , jj_BN, SIZE_BN);
Expand All @@ -472,7 +469,6 @@ class tinyBLAS {
GGML_ASSERT(jj == jj2);
}

job = ggml_threadpool_chunk_add(params->threadpool, 1);
}

ggml_barrier(params->threadpool);
Expand Down
Loading