Date: Mon, 27 Mar 2006 15:33:09 -0600 From: "Nikolas Britton" <nikolas.britton@gmail.com> To: "Kris Kennaway" <kris@obsecurity.org> Cc: freebsd-stable@freebsd.org Subject: Re: -march=pentium2 + -mtune=pentium4 faster then -march=pentium4? Message-ID: <ef10de9a0603271333i591b2fa5x3ed8e8cb2c27198c@mail.gmail.com> In-Reply-To: <20060327192044.GA70891@xor.obsecurity.org> References: <ef10de9a0603271105v3f68bd69q883e853366fb36d@mail.gmail.com> <20060327192044.GA70891@xor.obsecurity.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On 3/27/06, Kris Kennaway <kris@obsecurity.org> wrote: > On Mon, Mar 27, 2006 at 01:05:13PM -0600, Nikolas Britton wrote: > > Why does GCC produce faster code using "-march=3Dpentium2 > > -mtune=3Dpentium4" on a Pentium 4 chip versus plain -march=3Dpentium4? > > > > Try it... > > > > CPUTYPE=3Dpentium2 > > CFLAGS+=3D -mtune=3Dpentium4 > > COPTFLAGS+=3D -mtune=3Dpentium4 > > Talk to the gcc developers (and provide benchmarks). > What would be an adequate, proof, benchmark? I've already run several tests with nbench, testing all of the possible configurations of -march and -mtune. -- BSD Podcasts @ http://bsdtalk.blogspot.com/
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?ef10de9a0603271333i591b2fa5x3ed8e8cb2c27198c>