This is the mail archive of the
fortran@gcc.gnu.org
mailing list for the GNU Fortran project.
Re: Polyhedron benchmark on Opteron
- From: "François-Xavier Coudert" <fxcoudert at gmail dot com>
- To: "Steve Kargl" <sgk at troutmask dot apl dot washington dot edu>
- Cc: "Fortran List" <fortran at gcc dot gnu dot org>, franke dot daniel at gmail dot com, burnus at net-b dot de
- Date: Fri, 29 Sep 2006 16:50:10 +0200
- Subject: Re: Polyhedron benchmark on Opteron
- Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=Z/Hwehn8pS6pqhm/GcnFnyXQKxHhUqABJBbx5o1k1iLS8Vxv+k9xV/Yi4GV6Nw67LmLYVtUNYforN3gSLkY83fQw91ipvQ5rpfQkPL6nahjrQmmpmve2XXaqeJNvjQNJge+j55uB/QZNSid2fueOB7bjfxT+K1Z1o6H3m8HTJbs=
- References: <19c433eb0609290713x64f74089m45e5ea291343e1d7@mail.gmail.com> <20060929143829.GB38624@troutmask.apl.washington.edu>
Options used are :
* gfortran -march=k8 -ffast-math -funroll-loops -static -O3
* ifort -O3 -xW -ipo -static -V
If -ipo means interprocedure optimization, then this
isn't something for someone new to gcc/gfortran to do.
What are the comparisons if -ipo is removed?
Yes, -ipo means interprocedure optimization. But in my experience, it
seldom makes a huge difference. Last time I took the time to profile a
polyhedron benchmark, it was AERMOD and I discovered we spent 20% of
the time call the (since inlined) string copying function in
libgfortran.
Anyway, I'll launch a benchmark without -ipo, and I'll report back.
FX