Re: Lapack test suite results for gcc 3.3 on i686-pc-linux-gnu

[Toon Moene <toon at moene dot indiv dot nluug dot nl>]

poschmid at lbl dot gov wrote:

> On Tue, 25 Mar 2003, Toon Moene wrote:

> > poschmid at lbl dot gov wrote:

> > > I ran the Lapack test suite on my computer, a i686-pc-linux-gnu
> > > system, equipped with a Pentium IV processor operating at 1.8 GHz
> > > clock speed. In comparison to gcc 3.2 there are 58 regressions.
> >
> > It'll help if you told us what options you use to compile the sources.
> >
> > Cheers,

> Thank you very much for your reply. Hopefully, some of the regressions can 
> be investigated or eliminated.
>
> I closely followed the instructions (see 
> gcc.gnu.org/testing/testing-lapack.html). 
>
> Therefore, I set OPTS to "OPTS = -g -O2 -funroll-loops".

Arrghh, sorry, I forgot I specified the options in the description for 
the LAPACK runs.

But perhaps you could perform the test I can't anymore (because I canned 
 my ix86 laptop):

Compare your run with the options above with one where you add 
-ffloat-store to those options.  This will show if the outcome of the 
LAPACK tests is sensitive to small differences in rounding.

Thanks in advance,

--
Toon Moene - mailto:toon at moene dot indiv dot nluug dot nl - phoneto: +31 346 214290
Saturnushof 14, 3738 XG  Maartensdijk, The Netherlands
Maintainer, GNU Fortran 77: http://gcc.gnu.org/onlinedocs/g77_news.html
GNU Fortran 95: http://gcc-g95.sourceforge.net/ (under construction)