[petsc-dev] segv on Cray with 64K processes

Mark F. Adams mark.adams at columbia.edu
Tue Jun 5 09:47:12 CDT 2012

On Jun 5, 2012, at 10:30 AM, Jed Brown wrote:

> On Tue, Jun 5, 2012 at 8:59 AM, Mark F. Adams <mark.adams at columbia.edu> wrote:
> I've got a consistent segv on the Cray at NERSC with 64K cores.  No problems with smaller jobs.
> It seems to happen in here:
>  /* Done after init due to a bug in MPICH-GM? */
>  ierr = PetscErrorPrintfInitialize();CHKERRQ(ierr);
> Do you have any more information? How did you identify that this was the point of error?

printf surrounded by barriers.

There are a lot of system calls in PetscErrorPrintfInitialize.  I've added printfs to this and submitted the job so I should have that info tomorrow.

> I can keep diving in, but anyone have any ideas on this?
> Mark

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-dev/attachments/20120605/7fb6fd97/attachment.html>

More information about the petsc-dev mailing list