This is the mail archive of the
fortran@gcc.gnu.org
mailing list for the GNU Fortran project.
Re: Optimization of forall loops
- From: Steven Bosscher <stevenb dot gcc at gmail dot com>
- To: fortran at gcc dot gnu dot org
- Cc: Dominique Dhumieres <dominiq at lps dot ens dot fr>
- Date: Mon, 27 Feb 2006 18:15:12 +0100
- Subject: Re: Optimization of forall loops
- Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:to:subject:date:user-agent:cc:references:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:message-id:from; b=TQXKzmzBVCI7uGpDfCyTDIkk+EtDL46aPwuk9fxuhn7J89CMzOHMZNetEWcaS+vY2kZCBcqjOsS8r/jFEeMVX5PpgReaQJM5+O/C3VZTrC2McvmCfdq6ixc+sSvi+5XX5M+JqC9FCo9Zrr1+CpA9T1000CVvYQqaBwBjrQ+84/8=
- References: <4402F0D0.mail4XK1W8J4U@tournesol.lps.ens.fr>
On Monday 27 February 2006 13:30, Dominique Dhumieres wrote:
> 117c117,119
> < b(:,j) = b(:,j)-temp*c
> ---
>
> > forall ( p = 1:n )
> > b(p,j) = b(p,j)-temp(p)*c
> > end forall
FORALL is often more difficult to optimize, but in this case it looks
like a weakness (just another one, you know... ;-) in the dependency
checking code.
Can you file a bug about this with a small test case (not taken from
Polyhedron please, copyright reasons)? If you do, please add me to
the CC: list.
Thanks,
Gr.
Steven