Function CFLOAT_vdot

numpy/core/src/multiarray/vdot.c:15–60

* All data is assumed aligned. */

 * All data is assumed aligned.
 */
NPY_NO_EXPORT void
CFLOAT_vdot(char *ip1, npy_intp is1, char *ip2, npy_intp is2,
            char *op, npy_intp n, void *NPY_UNUSED(ignore))
{
#if defined(HAVE_CBLAS)
    CBLAS_INT is1b = blas_stride(is1, sizeof(npy_cfloat));
    CBLAS_INT is2b = blas_stride(is2, sizeof(npy_cfloat));

    if (is1b && is2b) {
        double sum[2] = {0., 0.};  /* double for stability */

        while (n > 0) {
            CBLAS_INT chunk = n < NPY_CBLAS_CHUNK ? n : NPY_CBLAS_CHUNK;
            float tmp[2];

            CBLAS_FUNC(cblas_cdotc_sub)((CBLAS_INT)n, ip1, is1b, ip2, is2b, tmp);
            sum[0] += (double)tmp[0];
            sum[1] += (double)tmp[1];
            /* use char strides here */
            ip1 += chunk * is1;
            ip2 += chunk * is2;
            n -= chunk;
        }
        ((float *)op)[0] = (float)sum[0];
        ((float *)op)[1] = (float)sum[1];
    }
    else
#endif
    {
        float sumr = (float)0.0;
        float sumi = (float)0.0;
        npy_intp i;

        for (i = 0; i < n; i++, ip1 += is1, ip2 += is2) {
            const float ip1r = ((float *)ip1)[0];
            const float ip1i = ((float *)ip1)[1];
            const float ip2r = ((float *)ip2)[0];
            const float ip2i = ((float *)ip2)[1];

            sumr += ip1r * ip2r + ip1i * ip2i;
            sumi += ip1r * ip2i - ip1i * ip2r;
        }
        ((float *)op)[0] = sumr;
        ((float *)op)[1] = sumi;
    }
}


/*