Skip to content

Optimize ggml_vec_dot_q8_q8 for ppc #8

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
Open

Optimize ggml_vec_dot_q8_q8 for ppc #8

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
5 changes: 2 additions & 3 deletions ggml/src/ggml-cpu/ggml-cpu-quants.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3929,9 +3929,8 @@ void ggml_vec_dot_q8_0_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const voi
__builtin_prefetch(x[ib].qs, 0, 1);
__builtin_prefetch(y[ib].qs, 0, 1);

vector float vxd = vec_splats(GGML_FP16_TO_FP32(x[ib].d));
vector float vyd = vec_splats(GGML_FP16_TO_FP32(y[ib].d));
vector float vd = vec_mul(vxd, vyd);
float delta = GGML_FP16_TO_FP32(x[ib].d) * GGML_FP16_TO_FP32(y[ib].d);
vector float vd = vec_splats(delta);

vector signed char q8x0 = vec_xl( 0, x[ib].qs);
vector signed char q8x1 = vec_xl(16, x[ib].qs);
Expand Down
Loading