__m128 vectorV1 = _mm_loadu_ps(v1);
        __m128 vectorV2 = _mm_loadu_ps(v2);

        __m128 col1 = _mm_shuffle_ps(vectorV1, vectorV1, _MM_SHUFFLE(3, 3, 1, 1));
        __m128 col2 = _mm_shuffle_ps(vectorV2, vectorV2, _MM_SHUFFLE(3, 2, 3, 2));

        __m128 col3 = _mm_shuffle_ps(vectorV1, vectorV1, _MM_SHUFFLE(2, 2, 0, 0));
        __m128 col4 = _mm_shuffle_ps(vectorV2, vectorV2, _MM_SHUFFLE(1, 0, 1, 0));

        __m128 vectorResult1 = _mm_mul_ss(col1, col2);
        __m128 vectorResult2 = _mm_mul_ss(col3, col4);
        __m128 vectorResult = _mm_add_ps(vectorResult1, vectorResult2);

        _mm_storeu_ps(result, vectorResult);