Hello, On Tue, 2013-11-19 at 17:05 +0400, niXman wrote: > Hi, > > I'm curious the thoughts of GCC developers about this topic: > http://stackoverflow.com/questions/13128430/why-is-stdcopy-5x-slower-than-memcpy-in-my-test-program > > > Clang in this case optimizing better than GCC. > Is there any reason why GCC does not perform the same optimization? Probably nobody has noticed or reported it yet. Thanks for reporting this. I've created a PR for this issue: http://gcc.gnu.org/bugzilla/show_bug.cgi?id=59209 See the PR description for a reduced test case and some more detailed explanation. Cheers, Oleg
