On Mon, Apr 26, 2010 at 5:23 AM, Philip Martin <[email protected]> wrote: > Stefan Fuhrmann <[email protected]> writes: > >> further reducing my backlog of patches sitting in my >> working copy, this and the next patch optimize code >> locally - shaving off cycles here and there. The net >> effect is somewhere between 3 and 10 percent >> for repository access (ls, export, etc.). >> >> In this patch, I eliminated calls to memcpy for small >> copies as they are particularly expensive in the MS CRT. > > For gcc (on Linux at least) memcpy is automatically inlined for small > copies. Obscuring the memcpy could well result in worse code.
And I believe we're enabling intrinsics in the Windows build... so it's being inlined there too. I agree, I don't like obscuring memcpy() either. -John
