为什么我会看到使用本机代码增加约20％的速度？

Any idea why this code:

知道为什么这个代码:

extern "C" __declspec(dllexport) void Transform(double x[], double y[], int iterations, bool forward)
{
    long n, i, i1, j, k, i2, l, l1, l2;
    double c1, c2, tx, ty, t1, t2, u1, u2, z;

    /* Calculate the number of points */
    n = (long)pow((double)2, (double)iterations);

    /* Do the bit reversal */
    i2 = n >> 1;
    j = 0;
    for (i = 0; i < n - 1; ++i)
    {
        if (i < j)
        {
            tx = x[i];
            ty = y[i];
            x[i] = x[j];
            y[i] = y[j];
            x[j] = tx;
            y[j] = ty;
        }
        k = i2;
        while (k <= j)
        {
            j -= k;
            k >>= 1;
        }
        j += k;
    }

    /* Compute the FFT */
    c1 = -1.0; 
    c2 = 0.0;
    l2 = 1;
    for (l = 0; l < iterations; ++l)
    {
        l1 = l2;
        l2 <<= 1;
        u1 = 1; 
        u2 = 0;
        for (j = 0; j < l1; j++) 
        {
            for (i = j; i < n; i += l2) 
            {
                i1 = i + l1;
                t1 = u1 * x[i1] - u2 * y[i1];
                t2 = u1 * y[i1] + u2 * x[i1];
                x[i1] = x[i] - t1; 
                y[i1] = y[i] - t2;
                x[i] += t1;
                y[i] += t2;
            }
            z = u1 * c1 - u2 * c2;
            u2 = u1 * c2 + u2 * c1;
            u1 = z;
        }
        c2 = sqrt((1.0 - c1) / 2.0);
        if (forward) 
            c2 = -c2;
        c1 = sqrt((1.0 + c1) / 2.0);
    }

    /* Scaling for forward transform */
    if (forward)
    {
        for (i = 0; i < n; ++i)
        {
            x[i] /= n;
            y[i] /= n;
        }
    }
}
extern "