[FLASH-USERS] FLASH setup on stampede.tacc.utexas.edu

[Mark L Richardson]

Hello Klaus,
  This is the same Sedov build that runs fine on Lonestar.

The line appears to be in mpi_amr_morton_limits:

      call MPI_Allgather(morton_limits(1,1,1,mype+1),  6*4,MPI_INTEGER, &
     &                   morton_limits,6*4,MPI_INTEGER, &
     &                   MPI_COMM_WORLD,ierror)

Thanks for your help,
  -Mark



On Fri, Apr 5, 2013 at 7:43 AM, Klaus Weide <klaus at flash.uchicago.edu>wrote:

> On Fri, 5 Apr 2013, Mark L Richardson wrote:
>
> > [cli_0]: aborting job:
> > Fatal error in PMPI_Allgather:
> > Invalid buffer pointer, error stack:
> > PMPI_Allgather(975): MPI_Allgather(sbuf=0xd665eb0, scount=24,
> MPI_INTEGER,
> > rbuf=0xd665eb0, rcount=24, MPI_INTEGER, MPI_COMM_WORLD) failed
> > PMPI_Allgather(950): Buffers must not be aliased
> >
> >
> > Has anyone dealt with this before?
>
> Mark,
>
> You seem to have somewhere in the source a call to Allgather that
> improperly uses the same buffer as the first and 4th actual argument.
>
> Try to locate this call. I assume it is in user-provided code; if it
> was in a part of the FLASH code that gets exercised under normal
> circumstances, we should have already run into it and fixed it.
>
> Klaus
>



-- 
Mark Richardson,
Mark.L.Richardson at asu.edu
Ph.D. Candidate: Astrophysics
ISTB4 623
School of Earth and Space Exploration
Arizona State University
480 318-4449
www.public.asu.edu/~mlricha4
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://flash.rochester.edu/pipermail/flash-users/attachments/20130405/d34c632d/attachment-0001.htm>