It's kinda tough to do direct comparisons of the 2 because you always have to wonder how well coded for SSE or altivec the program is. I've had some experience programming SSE and the problem is, c/c++ compilers can't handle sse as well as it can plain floating point or integer code. Because of this, you have to resort to using compiler "intrinsics" but doing that sucks compared to writing regular math forumulas.
This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.