On Fri, Jul 25, 2003 at 03:39:34PM +0200, Johan Walles wrote: > I would like to have an i686 optimized glibc package. The reason is > glibc is what is taking up the most time (23%) during my boot > sequence:
Can you contrast this against an i686-optimised version of glibc? You're showing that memmove is eating about 4% of your boottime. I'm curious whether optimised libraries would appreciably save any of that (once you account for cache-misses, pipelining, etc.) I haven't seen anything that shows that optimised libraries are a big win for anything other that floating point operations, and the serious users of those (like openssl) tend to provide their own optimised versions. Tks, Jeff Bailey -- Breathe into my hands, I'll cup them like a glass to drink from... - Tattle Tale
