Skip to content

ggml : use vzip_s8 for interleave #704

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.

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

Closed
wants to merge 1 commit into from
Closed
Changes from all commits
Commits
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: 2 additions & 4 deletions ggml.c
Original file line number Diff line number Diff line change
Expand Up @@ -813,10 +813,8 @@ void dequantize_row_q4_0(const void * restrict x, float * restrict y, int k) {
const int8x8_t vb_1 = vsub_s8(vs_1, vdup_n_s8(8));

// Interleave and combine
const int8x8_t vx_0 = vzip1_s8(vb_0, vb_1);
const int8x8_t vx_1 = vzip2_s8(vb_0, vb_1);

const int8x16_t vq = vcombine_s8(vx_0, vx_1);
const int8x8x2_t vx = vzip_s8(vb_0, vb_1);
const int8x16_t vq = vcombine_s8(vx.val[0], vx.val[1]);

// convert to 2x int16x8_t
const int16x8_t vi_0 = vmovl_s8(vget_low_s8 (vq));
Expand Down