On Wed, 2009-02-04 at 15:00 +0100, Kevin Kofler wrote: > Callum Lerwick wrote: > > Going -O3 rather than -O2 is going to make a bigger difference than > > anything else. If you want to improve performance, you need to run > > profiles, locate performance critical bits of code, figure out if -O3 is > > beneficial, and/or write some hand tuned assembly/intrinsic code. > > > > Not to mention, the biggest performance problem on modern processors is > > memory. Minimizing cache thrashing is way more important than what > > instructions you use. Optimize data structures before code. > > That's actually an argument for investigating -Os, not -O3. I don't think code size is what's making Firefox eat up 1gb RAM. But defaulting to -Os, and using -O2/-O3 on "hot" libraries and such might not be a bad idea. It's the most basic rule of optimization. 90% of your runtime is in %10 of the code. Optimize that %10 of the code, and forget the rest. It's wasted effort. http://en.wikipedia.org/wiki/Amdahl's_law
Attachment:
signature.asc
Description: This is a digitally signed message part
-- fedora-devel-list mailing list fedora-devel-list@xxxxxxxxxx https://www.redhat.com/mailman/listinfo/fedora-devel-list
