cppaosvecdp.cpp

void dot3_aos_vector_dp(const vector<Vec3f>& vs, vector<float>& dp) {
    // 0000 0000 0111 0001: mul lower three components, store sum in lowest component
    static const auto mask = 0x71;
    
    for (auto j = 0; j < reps; ++j) {
        const auto pvs = (float*)vs.data();
        auto pdp = (float*)dp.data();
        auto i = vector_len;
        while (i--) {
            // load 16 bytes (xyz|x)
            const auto xyzx = _mm_loadu_ps(pvs + i * 3);            
            // compute d = x*x + y*y + z*z + 0*0 -> 000d
            const auto xxyyzz00 = _mm_dp_ps(xyzx, xyzx, mask);
            // store d (lower 4 bytes of dpv)
            _mm_store_ss(pdp + i, xxyyzz00);
        }
    }
}