[Wien] parallel segmentation fault

Luis Ogando lcodacal at gmail.com
Wed Feb 6 14:04:25 CET 2013


Hi Arturo,

   You have to check the compilation options for the parallel version (not
the serial one) and change    -lmkl_blacs_lp64    by
 -lmkl_blacs_openmpi_lp64    in the    RP_LIB(SCALAPACK+PBLAS):    line.
    Good luck,
                Luis





2013/2/6 Arturo <artginer at bifi.es>

>  Hi Luis,
>
> First of all, thanks for help!!
>
> In the first suggestion, how can I know if I'm using this library?
> In the compilations options, I don't use that library. I used:
>
>     -lmkl_lapack95_lp64 -lmkl_intel_lp64 -lmkl_intel_thread -lmkl_core
> -openmp -lpthread
>
> So the solution you suggest is to add the library mkl_blacs_openmpi_lp64
> to this line?
>
> Regards
>
>
> El 06/02/13 13:32, Luis Ogando escribió:
>
> Hi Arturo,
>
>      Try
> http://zeus.theochem.tuwien.ac.at/pipermail/wien/2012-July/017207.html
>
>      The first suggestion given by Prof. Marks solved a similar problem to
> me.
>     All the best,
>                   Luis
>
>
>
>
>
>  2013/2/6 Arturo <artginer at bifi.es>
>
>>  Hi,
>>
>> We are trying  to run wien2k v12, compiled with openmpi 1.5.4 and intel
>> compilers 12.1 but it gives us a segmentations fault while executing the
>> following:
>>
>> mpirun  -np 4  /cm/shared/apps/WIEN2k_12/lapw1_mpi  uplapw1_1.defcat
>>
>> The errors are these:
>>
>> w2k_dispatch_signal(): received: Segmentation fault
>> w2k_dispatch_signal(): received: Segmentation fault
>> w2k_dispatch_signal(): received: Segmentation fault
>> w2k_dispatch_signal(): received: Segmentation fault
>> --------------------------------------------------------------------------
>> MPI_ABORT was invoked on rank 1 in communicator MPI_COMM_WORLD
>> with errorcode 91.
>>
>> 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.
>> --------------------------------------------------------------------------
>>  Child id           0 SIGSEGV, contact developers
>>  Child id           1 SIGSEGV, contact developers
>>  Child id           2 SIGSEGV, contact developers
>>  Child id           3 SIGSEGV, contact developers
>> --------------------------------------------------------------------------
>> mpirun has exited due to process rank 2 with PID 25559 on
>> node node042 exiting without calling "finalize". This may
>> have caused other processes in the application to be
>> terminated by signals sent by mpirun (as reported here).
>> --------------------------------------------------------------------------
>> [node042:25556] 3 more processes have sent help message help-mpi-api.txt
>> / mpi-abort
>> [node042:25556] Set MCA parameter "orte_base_help_aggregate" to 0 to see
>> all help / error messages
>>
>> And the ulimit -s is unlimited.
>>
>> Could you help us executing wien2k in parallel mode? Sequential is
>> working fine.
>>
>> Best Regards
>> Arturo
>>
>>
>> _______________________________________________
>> Wien mailing list
>> Wien at zeus.theochem.tuwien.ac.at
>> http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
>>
>>
>
>
> _______________________________________________
> Wien mailing listWien at zeus.theochem.tuwien.ac.athttp://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
>
>
> _______________________________________________
> Wien mailing list
> Wien at zeus.theochem.tuwien.ac.at
> http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://zeus.theochem.tuwien.ac.at/pipermail/wien/attachments/20130206/5ad08383/attachment.htm>


More information about the Wien mailing list