[Users] MPI killing issue in running the simulation

[Roland Haas]

Hello0 Karima,

sorry for the very long delay on this mailing list.

Unfortunately based on the information that you are providing, it is
not clear what caused the problem. 

MPI_ABORT is called by Cactus when it detect and error but also by MPI
itself under certain circumstances.

If Cactus called MPI_Abort then there will be some extra information
above the MPI_ABORT error message explaining the problem.

If you could attach the full *.err and *.out filesgenerators by the
simulation, then this would help a lot deciding what the issue is.

Yours,
Roland

> Hi there,
> 
> I am running a simple test (parameter file) using simfactory.
> 
> Input:
> 
> > ./simfactory/bin/sim create-run tstadm \
> >     --parfile repos/einsteinanalysis/testADM-0018.par  
> 
> Error:
> 
> > MPI_ABORT was invoked on rank 0 in communicator MPI_COMM_WORLD
> > with errorcode 1.
> >
> > NOTE: invoking MPI_ABORT causes Open MPI to kill all MPI processes.
> > You may or may not see output from other processes, depending on
> > exactly when Open MPI kills them  
> along with the warning,
> > Warning: Too many threads per process specified: specified num-threads=2 (ppn-used is 2)
> > Warning: Total number of threads and number of threads per process are inconsistent: procs=1, num-threads=2 (procs*num-smt must be an integer multiple of num-threads).  
> How to resolve the issue?
> 
> Thanks in advance,
> 
> Best
> 
> karima
> 
> 
> 


-- 
My email is as private as my paper mail. I therefore support encrypting
and signing email messages. Get my PGP key from http://pgp.mit.edu .
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 833 bytes
Desc: OpenPGP digital signature
Url : http://lists.einsteintoolkit.org/pipermail/users/attachments/20201222/38c5d862/attachment.bin