This is the mail archive of the fortran@gcc.gnu.org mailing list for the GNU Fortran project.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]
Other format:	[Raw text]

Re: benchmarking.

From: IainS <developer at sandoe-acoustics dot co dot uk>
To: Tobias Schlüter <tobias dot schlueter at physik dot uni-muenchen dot de>
Cc: gfortran <fortran at gcc dot gnu dot org>
Date: Sat, 14 Jun 2008 23:04:07 +0100
Subject: Re: benchmarking.
References: <9DE4A741-DFE2-44A2-9F9B-757B05590EB5@sandoe-acoustics.co.uk> <485427AE.2020503@physik.uni-muenchen.de>

On 14 Jun 2008, at 21:18, Tobias Schlüter wrote:

IainS wrote:
hi, Is there a gfortran preferred or standard performance benchmark suite?
gfortran is regularly tested with the Polyhedron benchmark suite <http://polyhedron.com/polyhedron_benchmark_suite0html> and with the SPEC fp benchmark suites <http://www.spec.org/>.

Are you planning to do tests in unusual environments? Please let us know your results.

Systems are not that unusual (PPC64/Quad - PPC/Dual - Core Duo). I've been working on a patch to implement the static linking of the fortran lib on darwin (which is complete, bar testing in a wider variety of situations). In principle, the static linked lib should (potentially) be slightly higher performance - I was interested to know if there was a formal way to test this.

thanks for the links,
Iain

References:
- benchmarking.
  - From: IainS
- Re: benchmarking.
  - From: Tobias Schlüter

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]