Faster IQ4_XS_R4 on Zen4 (#128)

* Faster iq4_xs_r4 on Zen4

The trick is to simply prepare the Q8 block sums for
blocks of 32 as floats. This brings PP-512 up to 254.6 t/s
from 224 t/s.

* Fix broken matrix x vector product on Zen4

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

1 files changed, 2 insertions, 2 deletions

diff --git a/ggml/src/iqk/iqk_quantize.h b/ggml/src/iqk/iqk_quantize.h
index f5bbd3dc..c370c8e8 100644
--- a/ggml/src/iqk/iqk_quantize.h
+++ b/ggml/src/iqk/iqk_quantize.h
@@ -61,8 +61,6 @@ size_t quantize_iq2_ks(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst
 void   dequantize_row_iq2_ks(const block_iq2_ks  * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
 void   vec_dot_iq2_ks_q8_k(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
 
-void iqk_quantize_row_q8_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT vy, int64_t k);
-
 void   quantize_row_iq4_nl_r4_ref(const float * GGML_RESTRICT x, block_iq4_nl_r4  * GGML_RESTRICT y, int64_t k);
 void   quantize_row_iq4_nl_r4(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
 size_t quantize_iq4_nl_r4(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);
@@ -111,9 +109,11 @@ void   dequantize_row_iq2_bn_r4(const block_iq2_bn * GGML_RESTRICT x, float * GG
 size_t quantize_iq2_bn_r4(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);
 void   vec_dot_iq2_bn_r4_q8_K64(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
 
+void iqk_quantize_row_q8_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT vy, int64_t k);
 void quantize_row_q8_K64_ref(const float * GGML_RESTRICT x, block_q8_K64 * GGML_RESTRICT y, int64_t k);
 void quantize_row_q8_K64(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
 void quantize_row_q8_K16(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
+void quantize_row_q8_K32(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
 
 #ifdef __cplusplus
 }