Using AVX intrinsics instead of SSE does not improve speed — why?

Question

I\'ve been using Intel\'s SSE intrinsics for quite some time with good performance gains. Hence, I expected the AVX intrinsics to further speed-up my programs. This, unfortunate

Answer 1

This is because VSQRTPS (AVX instruction) takes exactly twice as many cycles as SQRTPS (SSE instruction) on a Sandy Bridge processor. See Agner Fog's optimize guide: instruction tables, page 88.

Instructions like square root and division don't benefit from AVX. On the other hand, additions, multiplications, etc., do.