Re: open64 versus gcc

"dz" <drizzle76@gmail.com>
29 Nov 2006 00:52:03 -0500

          From comp.compilers

Related articles
open64 versus gcc drizzle76@gmail.com (dz) (2006-11-22)
Re: open64 versus gcc shreyas76@gmail.com (shrey) (2006-11-24)
Re: open64 versus gcc touati.sid-pas-de-spam-svp@gmail.com-pasdespam (touati) (2006-11-24)
Re: open64 versus gcc stevenb.gcc@gmail.com (Steven Bosscher) (2006-11-26)
Re: open64 versus gcc Sid-pasdespam.Touati@inria.fr (Sid Touati) (2006-11-27)
Re: open64 versus gcc drizzle76@gmail.com (dz) (2006-11-29)
Re: open64 versus gcc dnovillo@redhat.com (Diego Novillo) (2006-11-29)
Re: open64 versus gcc alewando@fala2005.com (A.L.) (2006-12-01)
Re: open64 versus gcc alewando@fala2005.com (A.L.) (2006-12-01)
Re: open64 versus gcc jthorn@aei.mpg-zebra.de (Jonathan Thornburg -- remove -animal to reply) (2006-12-03)
Re: open64 versus gcc dnovillo@redhat.com (Diego Novillo) (2006-12-03)
Re: open64 versus gcc lindahl@pbm.com (Greg Lindahl) (2006-12-03)
[3 later articles]
| List of all articles for this month |

From: "dz" <drizzle76@gmail.com>
Newsgroups: comp.compilers
Date: 29 Nov 2006 00:52:03 -0500
Organization: Compilers Central
References: 06-11-09406-11-100 06-11-104 06-11-113
Keywords: GCC, performance

The criteria I am looking for is stability and the strength of some
basic analysis in the compiler such as alias analysis. Can anyone
comment on that ?
dz


On Nov 27, 2:45 pm, Sid Touati <Sid-pasdespam.Tou...@inria.fr> wrote:
> Steven Bosscher a écrit :
>
> > On 24 Nov 2006 08:21:12 -0500, touati wrote:
> >> Actually, Open64 produces better code than gcc.
>
> > Ah, generalizations... It depends on the target you want to look at.I
agree that my initial sentence looks like a generalization, but I am
> aware that it isn't. It is difficult to make a fair comparison between
> compilers, there are too parameters to explore...
>
> Indeed, since all code optimization techniques (and their order of
> execution) are based on ad hoc heuristics, we can never guarantee that
> a compiler is better than another for any input program. Usually,
> benchmarks are used, but benchmarks are rarely representative of
> programs (they may represent workloads, but not
> programs). Consequently, for any pair of distinct compilers C1 and C2,
> you can always find programs better optimized with C1, and others
> better optimized with C2.
>
> S



Post a followup to this message

Return to the comp.compilers page.
Search the comp.compilers archives again.