Welcome, Guest
Username: Password: Remember me

TOPIC: Run in Parallel

Run in Parallel 8 years 4 months ago #22297

  • Cristina
  • Cristina's Avatar
Hi,

I tried to run in parallel, but I got the following error.


/home/applications/telemac/v7p1r0/builds/fedgfopenmpi/bin/partel: error while loading shared libraries: libmetis.so: cannot open shared object file: No such file or directoryun


The control file that I used to run in parallel is below

#BSUB -q PQ_yuying
#BSUB -a openmpi
#BSUB -m "IB_16C_96G"

#BSUB -n 2

#BSUB -oo "out"
#BSUB -eo "err"
. $MODULESHOME/../global/profile.modules
module load telemac/7.1
export NPROCS=`echo $LSB_HOSTS | wc -w`
export OMP_NUM_THREADS=$NPROCS


runcode.py telemac2d -c fedgfopenmpi -s lobster2.cas


Anyone can help me to figure out?

File Attachment:

File Name: lobster2_2016-07-05.cas
File Size: 4 KB



thanks so much,

Cristina
The administrator has disabled public write access.

Run in Parallel 8 years 4 months ago #22300

  • c.coulet
  • c.coulet's Avatar
  • OFFLINE
  • Moderator
  • Posts: 3722
  • Thank you received: 1031
Hi

This looks like an installation problem on your machine.
Did you compile telemac without any problem?

Maybe some path missing in the module definition of telemac?
Or in the queuing system as it doesn't find the metis library...

hope this helps
Christophe
The administrator has disabled public write access.
The following user(s) said Thank You: Cristina

Run in Parallel 8 years 4 months ago #22321

  • Cristina
  • Cristina's Avatar
Thanks for your reply, Yes I compiled Telemac without any problem, maybe the problem in the previous control file was the version, but now I set module load telemac/7.1.1 (the correct version), but I got this new error :(
Do you know which is the problem now?


/bin/sh: line 1: 13471 Segmentation fault (core dumped) /home/applications/telemac/v7p1r1/builds/fedgfopenmpi/bin/partel < PARTEL.PAR >> partel_T2DGEO.log


Really thanks so much for your help


Best regards,

Cristina
The administrator has disabled public write access.

Run in Parallel 8 years 4 months ago #22342

  • cdcunha
  • cdcunha's Avatar
I have been trying to help Cristina get this to work. Here is some additional information about the error in the output file.

... partitioning base files (geo, conlim, sections and zones)
+> /home/applications/telemac/v7p1r1/builds/fedgfopenmpi/bin/partel < PARTEL.PAR >> partel_T2DGEO.log
runPartition:
|runPARTEL: Could not split your file T2DGEO (runcode=139) with the error as follows:
|
|... The following command failed for the reason above (or below)
|/home/applications/telemac/v7p1r1/builds/fedgfopenmpi/bin/partel < PARTEL.PAR >> partel_T2DGEO.log
|
| You may have forgotten to compile PARTEL with the appropriate compiler directive
| (add -DHAVE_MPI to your cmd_obj in your configuration file).


Attached is the config file that shows that -DHAVE_MPI is added to cmd_obj.

Thanks for your help!

File Attachment:

File Name: systel.cfg
File Size: 2 KB
The administrator has disabled public write access.
Moderators: pham

The open TELEMAC-MASCARET template for Joomla!2.5, the HTML 4 version.