Function ggml_vec_dot_f16

ggml.c:1188–1222

}

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;

#if defined(GGML_SIMD)
    const int np = (n & ~(GGML_F16_STEP - 1));

    GGML_F16_VEC sum[GGML_F16_ARR] = { GGML_F16_VEC_ZERO };

    GGML_F16_VEC ax[GGML_F16_ARR];
    GGML_F16_VEC ay[GGML_F16_ARR];

    for (int i = 0; i < np; i += GGML_F16_STEP) {
        for (int j = 0; j < GGML_F16_ARR; j++) {
            ax[j] = GGML_F16_VEC_LOAD(x + i + j*GGML_F16_EPR, j);
            ay[j] = GGML_F16_VEC_LOAD(y + i + j*GGML_F16_EPR, j);

            sum[j] = GGML_F16_VEC_FMA(sum[j], ax[j], ay[j]);
        }
    }

    // reduce sum0..sum3 to sum0
    GGML_F16_VEC_REDUCE(sumf, sum);

    // leftovers
    for (int i = np; i < n; ++i) {
        sumf += (ggml_float)(GGML_FP16_TO_FP32(x[i])*GGML_FP16_TO_FP32(y[i]));
    }
#else
    for (int i = 0; i < n; ++i) {
        sumf += (ggml_float)(GGML_FP16_TO_FP32(x[i])*GGML_FP16_TO_FP32(y[i]));
    }
#endif

    *s = sumf;
}

// compute GGML_VEC_DOT_UNROLL dot products at once
// xs - x row stride in bytes