blob: 71cf40992539d3808c815c44517ef2e3c0f8bee0 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
|
/* { dg-do compile } */
/* { dg-options "-O3 -funroll-loops -fdump-tree-vect-details" } */
/* { dg-require-effective-target vect_int } */
/* { dg-additional-options "-mavx2" { target x86_64-*-* i?86-*-* } } */
typedef unsigned short ggml_fp16_t;
static float table_f32_f16[1 << 16];
inline static float ggml_lookup_fp16_to_fp32(ggml_fp16_t f) {
unsigned short s;
__builtin_memcpy(&s, &f, sizeof(unsigned short));
return table_f32_f16[s];
}
typedef struct {
ggml_fp16_t d;
ggml_fp16_t m;
unsigned char qh[4];
unsigned char qs[32 / 2];
} block_q5_1;
typedef struct {
float d;
float s;
char qs[32];
} block_q8_1;
void ggml_vec_dot_q5_1_q8_1(const int n, float * restrict s, const void * restrict vx, const void * restrict vy) {
const int qk = 32;
const int nb = n / qk;
const block_q5_1 * restrict x = vx;
const block_q8_1 * restrict y = vy;
float sumf = 0.0;
for (int i = 0; i < nb; i++) {
unsigned qh;
__builtin_memcpy(&qh, x[i].qh, sizeof(qh));
int sumi = 0;
for (int j = 0; j < qk/2; ++j) {
const unsigned char xh_0 = ((qh >> (j + 0)) << 4) & 0x10;
const unsigned char xh_1 = ((qh >> (j + 12)) ) & 0x10;
const int x0 = (x[i].qs[j] & 0xF) | xh_0;
const int x1 = (x[i].qs[j] >> 4) | xh_1;
sumi += (x0 * y[i].qs[j]) + (x1 * y[i].qs[j + qk/2]);
}
sumf += (ggml_lookup_fp16_to_fp32(x[i].d)*y[i].d)*sumi + ggml_lookup_fp16_to_fp32(x[i].m)*y[i].s;
}
*s = sumf;
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
|