This is the mail archive of the
mailing list for the GCC project.
Re: GCC-4.5.0 comparison with previous releases and LLVM-2.7 on SPEC2000 for x86/x86_64
- From: Jan Hubicka <hubicka at ucw dot cz>
- To: Xinliang David Li <davidxl at google dot com>, gcc-patches at gcc dot gnu dot org
- Date: Thu, 29 Apr 2010 23:20:44 +0200
- Subject: Re: GCC-4.5.0 comparison with previous releases and LLVM-2.7 on SPEC2000 for x86/x86_64
- References: <4BD9B2EB.email@example.com> <firstname.lastname@example.org>
> This matches our previous observation that to bring the best out of
> LTO, FDO is also needed. (As a reference, LIPO improves over plain FDO
> by ~4.5%, vortex improves 23%). You will probably see even smaller
> improvement in SPEC2006.
There is FDO tester at http://gcc.opensuse.org/SPEC/CINT/sb-frescobaldi.suse.de-fdo-64-FDO/index.html
I switched it to LTO+FDO some time ago. For some reason vortex is not passing there, I will investigate (tehre is some vortex aliasing fix needed that probably
was not applied to that machine).
Yes FDO+LTO combine well. Still SPEC2000 is not the best suite for this,
since it contains only benchmarks that was optimized for LTO less compilers.
More modern benchmarks are more fun.
> It would be great if there is number collected comparing LTO + FDO vs
> plain FDO in the same setup.
> > ?Currently Graphite gives small improvements on x86 (one exception is
> > 2% for peak x86 SPECFP2000) and mostly degradation on x86_64 (with
> > maximum one more than 10% for SPECFP2000 because of big degradations
> > on mgrid and swim). ?So further work is needed on the project because
> > it seems not mature yet.
> > ?As for LLVM, LLVM became slower (e.g. in comparison with llvm-2.5 on
> > 15%-50% for x86-64). ?So the gap between compilation speed of GCC and
> > LLVM decreased and sometimes achieves 4% on x86_64 and 8% on x86 (both
> > for SPECInt2000 in -O2 mode). ?May be I am wrong but I don't think
> > CLANG will improve this situation significantly (in -O2 and -O3 mode)
> > because optimizations still take most of time of any serious
> > optimizing compiler.
> > ?LLVM did a progress in code performance especially for floating
> > point benchmarks. ?But the gap between LLVM-2.7 and GCC-4.5 in peak
> > performance (not including GCC LTO and Graphite) still 6-7% on
> > SPECInt200 and 13-17% on SPECFP2000.
> > ?In general, IMHO GCC-4.5.0 is a good and promising release.