[gambit-list] [Fwd: Measuring FSF gcc from 4.1.2 to today on various benchmarks.]
lucier at math.purdue.edu
Fri May 29 16:04:10 EDT 2009
I've run some statistics with various versions of gcc and sent the
following message to the gcc mail list, which is archived at
Perhaps some of you may be interested.
-------- Forwarded Message --------
> From: Bradley Lucier <lucier at math.purdue.edu>
> To: gcc at gcc.gnu.org
> Cc: Bradley Lucier <lucier at math.purdue.edu>
> Subject: Measuring FSF gcc from 4.1.2 to today on various benchmarks.
> Date: Fri, 29 May 2009 15:58:00 -0400
> I've put at
> some compile-time and run-time statistics related to PR 39157 and PR
> 33928 and compile times and run times for the programs in the Gambit
> Scheme benchmark suite. The statistics are for 4.1.2 release, 4.2.4
> release, 4.3.3 release, 4.4.1 20090522, 4.5.0 20090521 (revision
> 147758), and 4.5.0 20090521 (revision 147758) with
> -fno-forward-propagate; they use (mainly) the set of options
> -O1 -fno-math-errno -fschedule-insns2 -fno-trapping-math -fno-strict-aliasing -fwrapv -fomit-frame-pointer -fPIC -fno-common -mieee-fp
> on a Core 2 quad processor (running basically nothing else at the time).
> I would conclude from the statistics that, right now, the cost of
> including -fforward-propagate in -O1 overrides any performance benefit
> that may result.
More information about the Gambit-list