Discussion related to cado-nfs

[Emmanuel Thomé <emmanuel.thome@inria.fr>]

As Paul said it's nearly impossible to diagnose stuff without further info.

Changing the number of threads should be possible with the current version of 
the bwc script, with no particular magic. At least that's the theory. There 
could be bugs.

E.

Le 16 avr. 2015 23:09, paul zimmermann <Paul.Zimmermann@inria.fr> a écrit :
>
>        Dear Paul, 
>
> 1) please say which version you are using (2.1.1 or git revision xxx) 
>
> 2) please provide the console output you get (including the error) and the 
>    *.log file 
>
> Paul Z. 
>
> > From: Paul Leyland <paul.leyland@gmail.com> 
> > Date: Thu, 16 Apr 2015 10:09:38 +0100 
> > 
> > Apologies if this in the documentation somewhere but I haven't yet found 
> > it. 
> > 
> > Early this morning the linear algebra started with the default 1x2 
> > threads.  The machine has 8 cpus (dual quad-cores) and it would seem to 
> > make sense run on at least four of them so I killed the running krylov, 
> > edited the params file to set tasks.linalg.bwc.threads = 2x2 and 
> > restarted. 
> > 
> > Almost instant failure. 
> > 
> > What is the recommended way of making this change? 
> > 
> > Thanks, 
> > Paul 
> > 
> > 
> > _______________________________________________ 
> > Cado-nfs-discuss mailing list 
> > Cado-nfs-discuss@lists.gforge.inria.fr 
> > http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/cado-nfs-discuss 
> > 
> _______________________________________________ 
> Cado-nfs-discuss mailing list 
> Cado-nfs-discuss@lists.gforge.inria.fr 
> http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/cado-nfs-discuss