cppaosgather.cpp

void dot3_aos_vector_gather(const vector<Vec3f>& vs, vector<float>& dp) {
    static const auto epi32_one = _mm256_set1_epi32(1);
    static const auto x_offsets = _mm256_setr_epi32(0, 3, 6, 9, 12, 15, 18, 21);
    static const auto y_offsets = _mm256_add_epi32(x_offsets, epi32_one);
    static const auto z_offsets = _mm256_add_epi32(y_offsets, epi32_one);

    for (auto j = 0; j < reps; ++j) {
        const auto pvs = (float*)vs.data();
        auto pdp = (__m256*)dp.data();
        auto i = vector_len / lane_width;
        while(i--) {
            // xyz|xyz|xyz|xyz|xyz|xyz|xyz|xyz -> load 8 * 3 = 24 scattered floats
            const auto base = pvs + i * 3 * lane_width;
            const auto xs = _mm256_i32gather_ps(base, x_offsets, sizeof(float));
            const auto ys = _mm256_i32gather_ps(base, y_offsets, sizeof(float));
            const auto zs = _mm256_i32gather_ps(base, z_offsets, sizeof(float));
            const auto xx = _mm256_mul_ps(xs, xs);
            const auto yyxx = _mm256_fmadd_ps(ys, ys, xx);
            const auto zzyyxx = _mm256_fmadd_ps(zs, zs, yyxx);
            pdp[i] = zzyyxx;
        }
    }
}