This is the mail archive of the
fortran@gcc.gnu.org
mailing list for the GNU Fortran project.
Re: Polyhedron Benchmark
- From: Tobias Burnus <burnus at net-b dot de>
- To: "'fortran at gcc dot gnu dot org'" <fortran at gcc dot gnu dot org>
- Date: Mon, 16 Jul 2007 19:59:12 +0200
- Subject: Re: Polyhedron Benchmark
- References: <469BA698.8020404@net-b.de>
Uros Bizjak wrote:
> Could you perhaps add -fvect-cost-model to
> gcc-4.3 compile flags? There are some surprises there ;)
Well, a 2% overall improvement, some slower, some faster. Only for
induct an improvement by a 1/3.
Should I use -fvect-cost-model in general for my nightly runs or should
I add another column with one -fvect-cost-model run?
For Core2 the results with -fvect-cost-model are:
gfortran
benchmark Vec VecCost ifort
------------ ----- ------- -----
ac 12.95 12.84 17.36
aermod 36.32 36.17 25.30
air 9.41 9.16 9.16
capacita 51.85 52.55 0.09 (ifort crashed)
channel 2.87 2.97 3.56
doduc 47.41 48.00 47.69
fatigue 12.86 12.62 10.96
gas_dyn 8.57 8.59 3.97
induct 92.82 64.38 63.08 <<<<<
linpk 22.67 22.48 22.47
mdbx 19.03 18.98 17.66
nf 26.10 25.97 0.23 (ifort crashed)
protein 60.30 60.42 55.11
rnflow 35.11 35.06 42.29
test_fpu 12.68 12.64 10.78
tfft 2.97 3.04 2.88
------------ ----- -----
Geometr.mean 18.99 18.58
Tobias