Discussion related to cado-nfs

[Paul Leyland <paul.leyland@gmail.com>]

On Fri, 2015-04-17 at 09:18 +0200, Emmanuel Thomé wrote:
> 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.

Good, that's what I wanted to know.  If it was known to be difficult
there would seem to be little point in polluting the mailing list with
large quantities of almost useless diagnostics.

The result of "git show" is

commit 49023e7eaba0c0a727d62ed1ce0543870b1fe3c8
Merge: b517fc6 eade416
Author: Alexander Kruppa <akruppa@gmail.com>
Date:   Tue Aug 5 21:21:24 2014 +0200

    Merge branch 'master' of git
+ssh://scm.gforge.inria.fr//gitroot/cado-nfs/cado-nfs

lines 1-7/7 (END)


Luckily the screen output was still in the terminal's scroll-back
buffer.  It is the file "cado_screen" in the attached tarball.  Included
is the params file as it presently stands.  The first version didn't
contain tasks.linalg.bwc.threads at all; the second set it to 2x2 and
the final version, that now running the LA, has the line commented out.
That is, the only difference between the failing and the now successful
file is the presence of a "# " at the beginning of that line.  Also
included are work/c6-345.bwc.bwc.std* and work/c6-345.log.

If further information is required I'll send along what I can.


Thanks,
        Paul

Attachment: bwc_prob.tgz
Description: application/compressed-tar