cppsoavectorized.cpp

void dot3_soa_vectorized(const vector<float>& xs, const vector<float>& ys, const vector<float>& zs, vector<float>& dp) {
    for (auto j = 0; j < reps; ++j) {
        const auto px = (__m256*)xs.data();
        const auto py = (__m256*)ys.data();
        const auto pz = (__m256*)zs.data();
        auto pd = (__m256*)dp.data();
        auto i = vector_len / lane_width;
        while (i--) {
            pd[i] = _mm256_add_ps(_mm256_add_ps(_mm256_mul_ps(px[i], px[i]), _mm256_mul_ps(py[i], py[i])), _mm256_mul_ps(pz[i], pz[i]));
        }
    }
}