[Bug tree-optimization/112325] Missed vectorization of reduction after unrolling

[liuhongt at gcc dot gnu.org via Gcc-bugs]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=112325

--- Comment #9 from Hongtao Liu <liuhongt at gcc dot gnu.org> ---
The original case is a little different from the one in PR.
It comes from ggml

#include <stdint.h>
#include <string.h>

typedef uint16_t ggml_fp16_t;
static float table_f32_f16[1 << 16];

inline static float ggml_lookup_fp16_to_fp32(ggml_fp16_t f) {
    uint16_t s;
    memcpy(&s, &f, sizeof(uint16_t));
    return table_f32_f16[s];
}

typedef struct {
    ggml_fp16_t d;
    ggml_fp16_t m;
    uint8_t qh[4];
    uint8_t qs[32 / 2];
} block_q5_1;

typedef struct {
    float d;
    float s;
    int8_t 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++) {
        uint32_t qh;
        memcpy(&qh, x[i].qh, sizeof(qh));

        int sumi = 0;

        for (int j = 0; j < qk/2; ++j) {
            const uint8_t xh_0 = ((qh >> (j + 0)) << 4) & 0x10;
            const uint8_t xh_1 = ((qh >> (j + 12)) ) & 0x10;

            const int32_t x0 = (x[i].qs[j] & 0xF) | xh_0;
            const int32_t 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;
}