Date: Thu, 26 May 2005 08:56:12 -0700 From: Kris Kennaway <kris@obsecurity.org> To: Michael VInce <mv@roq.com> Cc: freebsd-amd64@freebsd.org Subject: Re: amd64 optimized gcc? Message-ID: <20050526155612.GA38421@xor.obsecurity.org> In-Reply-To: <429514AF.5000306@roq.com> References: <200505251317.22128.nb_root@videotron.ca> <429514AF.5000306@roq.com>
index | next in thread | previous in thread | raw e-mail
[-- Attachment #1 --] On Thu, May 26, 2005 at 10:13:35AM +1000, Michael VInce wrote: > Interesting. > I have been playing with GCC optimizations my self latterly and have > been wondering how much it helps, haven't done any benchmarks though. > I some times wonder if the GCC people are doing good working with > optimization flags. > > I recently lost my hard drive on my ASUS A4K (AMD64) laptop, > so bought a new 16meg cache 80gig Toshiba hard drive for it, while I > wait for warranty to come through on my old one. > I did a buildworld under 'CPUTYPE=athlon64' in make.conf and 'CFLAGS= > -O2 -pipe -funroll-loops' for the the kernel. > I also used both to build all my ports including xorg and KDE. > All this combined has made my laptop feel a lot faster. Google for 'placebo effect' :-) Unfortunately, leet optimization flags do not measurably effect everyday system performance, only specific CPU-intensive operations. Kris [-- Attachment #2 --] -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.1 (FreeBSD) iD8DBQFClfGcWry0BWjoQKURAhCVAKC+HLlTdGM/B+pFs/gJgPvTJAzA3QCgkOt2 3z1cwuAWWf1nQw3yI20EAqs= =AZ0I -----END PGP SIGNATURE-----home | help
Want to link to this message? Use this
URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050526155612.GA38421>