[petsc-users] petsc crash with intel compiler

Matthew Knepley knepley at gmail.com
Tue Jun 4 01:05:30 CDT 2013


On Tue, Jun 4, 2013 at 12:51 AM, Wang Feng <fengwang85 at gmail.com> wrote:

> Hi everyone
> I am trying to using petsc-3.1 with intel compiler version 13.0.1.
> Sometimes it crash with error information.
>

1) This does not even tell use what part of Hypre you are using. Never
truncate the error message.


>  [5]PETSC ERROR: --------------------- Error Message
> ------------------------------------
> Error in external library!
> Error in HYPRE solver, error code 1!
>

2) This is an error inside Hypre. I suggest contacting them.


> Configure options --prefix=/global/u2/f/fengwang/opt/petsc-3.1-intel_hyp
> --with-debugging=no --with-scalar-type=real --with-hypre=1
> --known-mpi-shared=1 --CC=cc --CXX=CC --FC=ftn --with-x11=0
> --download-superlu=download/superlu_4.3.tar.gz
> --with-hypre-dir=/global/u2/f/fengwang/opt/hypre-2.7.0
> --with-blas-lapack-lib=-mkl
>
> While in pgi compiler, it works well.
> Do you have any suggestions about it?
>

3) Even if we could track this down, it would be using the latest PETSc
release 3.4

  Thanks,

      Matt


> Thanks so much.
>
> -Feng
>
>
>
>
>
>
>
> --
> 王丰,大连理工大学,物理学院
> Feng Wang
> School of Physics and Optoelctronic Technology,
> Dalian University of Technology
> Princeton Plasma Physics Lab.
>



-- 
What most experimenters take for granted before they begin their
experiments is infinitely more interesting than any results to which their
experiments lead.
-- Norbert Wiener
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20130604/a49a7dc0/attachment.html>


More information about the petsc-users mailing list