intrinsics

inline __m128 SSE_SIMDTestNormalizeFast( float * RESTRICT vOut, float * RESTRICT vIn  )
{
        // load as a SIMD vector
        const __m128 vec = _mm_loadu_ps(vIn);
        // compute a dot product by computing the square, and
        // then rotating the vector and adding, so that the
        // dot ends up in the low term (used by the scalar ops)
        __m128 dot = _mm_mul_ps( vec, vec );
        // rotate x under y and add together
        __m128 rotated = _mm_shuffle_ps( dot, dot, _MM_SHUFFLE( 0,3,2,1 ) ); // YZWX ( shuffle macro is high to low word )
        dot = _mm_add_ss( dot, rotated ); // x^2 + y^2 in the low word
        rotated = _mm_shuffle_ps( rotated, rotated, _MM_SHUFFLE( 0,3,2,1 ) ); // ZWXY
        dot = _mm_add_ss( dot, rotated ); // x^2 + y^2 + z^2 in the low word

        __m128 recipsqrt = SSERSqrtNR( dot ); // contains reciprocal square root in low term
        recipsqrt = _mm_shuffle_ps( recipsqrt, recipsqrt, _MM_SHUFFLE( 0, 0, 0, 0 ) ); // broadcast low term to all words

        // multiply 1/sqrt(dotproduct) against all vector components, and write back
        const __m128 normalized = _mm_mul_ps( vec, recipsqrt );
        _mm_storeu_ps(vOut, normalized);
        return _mm_mul_ss( dot , recipsqrt );
}