csaosgather.cs

static void Dot3AosGather(Vector3[] vs, float[] dp) {
    var xtmp = new float[laneWidth];
    var ytmp = new float[laneWidth];
    var ztmp = new float[laneWidth];
    for (var j = 0; j < reps; ++j) {
        for (var i = 0; i < dp.Length; i += laneWidth) {
            for (var k = 0; k < laneWidth; ++k) {
                xtmp[k] = vs[i + k].X;
                ytmp[k] = vs[i + k].Y;
                ztmp[k] = vs[i + k].Z;
            }
            var x = new Vector<float>(xtmp);
            var y = new Vector<float>(ytmp);
            var z = new Vector<float>(ztmp);
            var dpv = x * x + y * y + z * z;
            dpv.CopyTo(dp, i);
        }
    }
}