Function ggml_vec_dot_f32

ggml.c:1151–1186

inline static void ggml_vec_div_f32 (const int n, float * z, const float * x, const float * y) { for (int i = 0; i < n; ++i) z[i]  = x[i]/y[i];   }

static void ggml_vec_dot_f32(const int n, float * restrict s, const float * restrict x, const float * restrict y) {
#ifdef GGML_SIMD
    float sumf = 0.0f;
    const int np = (n & ~(GGML_F32_STEP - 1));

    GGML_F32_VEC sum[GGML_F32_ARR] = { GGML_F32_VEC_ZERO };

    GGML_F32_VEC ax[GGML_F32_ARR];
    GGML_F32_VEC ay[GGML_F32_ARR];

    for (int i = 0; i < np; i += GGML_F32_STEP) {
        for (int j = 0; j < GGML_F32_ARR; j++) {
            ax[j] = GGML_F32_VEC_LOAD(x + i + j*GGML_F32_EPR);
            ay[j] = GGML_F32_VEC_LOAD(y + i + j*GGML_F32_EPR);

            sum[j] = GGML_F32_VEC_FMA(sum[j], ax[j], ay[j]);
        }
    }

    // reduce sum0..sum3 to sum0
    GGML_F32_VEC_REDUCE(sumf, sum);

    // leftovers
    for (int i = np; i < n; ++i) {
        sumf += x[i]*y[i];
    }
#else
    // scalar
    ggml_float sumf = 0.0;
    for (int i = 0; i < n; ++i) {
        sumf += (ggml_float)(x[i]*y[i]);
    }
#endif

    *s = sumf;
}

static void ggml_vec_dot_f16(const int n, float * restrict s, ggml_fp16_t * restrict x, ggml_fp16_t * restrict y) {
    ggml_float sumf = 0.0;