Re: [OMPI users] New Cluster Centos 6.4 with Openmpi 1.6.4

That is what i belive aswell, i have done a few tests now the past few hours, and heavily tested my queue system with submitting jobs diretly with qsub, and i have no problem allocating resources across several nodes. but when i try through the task manager of numeca fine/marine, it stops, and h

Re: [OMPI users] New Cluster Centos 6.4 with Openmpi 1.6.4

This usually means that you are inadvertently mixing versions of Open MPI between your nodes (e.g., version A.B.C on your head node, and version X.Y.Z on your compute nodes). On Jun 21, 2013, at 3:02 AM, thomas.fo...@ulstein.com wrote: > Hi > > im running into a strange problem when trying to

Re: [OMPI users] OpenMPI 1.6.4 and Intel Composer_xe_2013.4.183: problem with remote runs, orted: error while loading shared libraries: libimf.so

Hi Stefano That doesn't seem to be an Open MPI problem, but an Intel environment problem. Here I have this library directory (on a slightly older version): .../composerxe/2013.3.163/compiler/lib/intel64/ but Intel keeps changing their directory structure, playing with bunches of soft links, e

Re: [OMPI users] OpenMPI 1.6.4 and Intel Composer_xe_2013.4.183: problem with remote runs, orted: error while loading shared libraries: libimf.so

Hi Jeff, You are right, but as I said before the first thing my startup script does is to source compilevars.sh that sources all others Intel paths. See you soon. Il giorno 21/giu/2013 19:23, "Jeff Squyres (jsquyres)" ha scritto: > On Jun 21, 2013, at 11:54 AM, Gus Correa wrote: > > > 1) Instal

Re: [OMPI users] OpenMPI 1.6.4 and Intel Composer_xe_2013.4.183: problem with remote runs, orted: error while loading shared libraries: libimf.so

Hi Gus, thank you for your replay. The strange path I have chosen is because this was only a test. However my home dir is shared on all nodes and the lib dir is not a simple simlink. I think that Thomas is right, I have to remove intel64 from Intel/lib path. Monday I will try. Thank you again. Il

Re: [OMPI users] error running with mpirun

The ras/proxy plugin hasn't been around in a long, long time -- what version of OMPI are you running? Regardless, it sounds like a busted Open MPI install. You should wholly re-install OMPI from scratch. Be sure to *uninstall* the prior Open MPI install (which is easiest if you installed it i

Re: [OMPI users] OpenMPI 1.6.4 and Intel Composer_xe_2013.4.183: problem with remote runs, orted: error while loading shared libraries: libimf.so

On Jun 21, 2013, at 11:54 AM, Gus Correa wrote: > 1) Install them on all nodes, via RPM, or configure/make/install, or other > mechanism. > This is time consuming and costly to maintain, but scales well > in big or small clusters. Note, too, that the Intel compiler suite gives you scripts to so

Re: [OMPI users] MPI Finalize hangs!

Hi I tested by valgrind and the problem was  stack size and memory size, it works now. Thanks From: Matthieu Brucher To: Mohamad Ali Rostami ; Open MPI Users Sent: Friday, June 21, 2013 11:31 AM Subject: Re: [OMPI users] MPI Finalize hangs! Hi, I gue

Re: [OMPI users] OpenMPI 1.6.4 and Intel Composer_xe_2013.4.183: problem with remote runs, orted: error while loading shared libraries: libimf.so

Hi Stefano Make sure your Intel compiler's shared libraries are accessible on all nodes. Is your /home directory shared across all nodes? How about /opt (if Intel is installed there)? By default Intel installs the compilers on /opt, which in typical clusters (and Linux distributions) is a local

[OMPI users] no daemonizing orted.

Dear all, in OpenMPI 1.2.8 it was possble to not daemonize the orted using the mca paramater: MCA orte: parameter "orte_no_daemonize" is there any, or which is the equivalent in following versions? I note that starting, at least, from OpenMPI 1.4.2 there is the support to daemonize (o

Re: [OMPI users] MPI Finalize hangs!

Hi, I guess you have another problem in your application, surely a memory error somewhere else. Cheers, 2013/6/21 Mohamad Ali Rostami > Hi there > > My MPI program works completely without any problem in the interactive > mode, i.e. before submitting to HPC. However when I submit it with "bsu

[OMPI users] MPI Finalize hangs!

Hi there My MPI program works completely without any problem in the interactive mode, i.e. before submitting to HPC. However when I submit it with "bsub", everything works again until "MPI_FINALIZE" hangs and following error comes up: mpirun noticed that process rank 2 with PID 8620 on node ...

Re: [OMPI users] Trouble with Sending Multiple messages to the Same Machine

Hi Claire, The most probable reason for the observed behaviour is that there are additional active network interfaces on the nodes that cannot be used to pass data around. Example of such interfaces are various virtual Ethernet devices (e.g. on systems with virtualisation enabled) or tunnels

Re: [OMPI users] OpenMPI 1.6.4 and Intel Composer_xe_2013.4.183: problem with remote runs, orted: error while loading shared libraries: libimf.so

Wow... I think you are right... I will am check after the job I have just started will finish. Thank you again. See you soon Stefano Zaghi Ph.D. Aerospace Engineer, Research Scientist, Dept. of Computational Hydrodynamics at *CNR-INSEAN* The Itali

Re: [OMPI users] OpenMPI 1.6.4 and Intel Composer_xe_2013.4.183: problem with remote runs, orted: error while loading shared libraries: libimf.so

hi Stefano /home/stefano/opt/intel/2013.4.183/lib/intel64/ is also the wrong path, as the file is in ..183/lib/ and not ...183/lib/intel64/ is that why? ./Thomas Den 21. juni 2013 kl. 10:26 skrev "Stefano Zaghi" : > Dear Thomas, > thank you again. > > Symlink in /usr/lib64 is not enough, I h

Re: [OMPI users] OpenMPI 1.6.4 and Intel Composer_xe_2013.4.183: problem with remote runs, orted: error while loading shared libraries: libimf.so

Dear Thomas, thank you again. Symlink in /usr/lib64 is not enough, I have symlinked also in /home/stefano/opt/mpi/openmpi/1.6.4/intel/lib and, as expected, not only libimf.so but also ibirng.so and libintlc.so.5 are necessary. Now also remote runs works, but this is only a workaround, I still not

Re: [OMPI users] OpenMPI 1.6.4 and Intel Composer_xe_2013.4.183: problem with remote runs, orted: error while loading shared libraries: libimf.so

your settings are as following: export MPI=/home/stefano/opt/mpi/openmpi/1.6.4/intel export PATH=${MPI}/bin:$PATH export LD_LIBRARY_PATH=${MPI}/lib/openmpi:${MPI}/lib:$LD_LIBRARY_PATH export LD_RUN_PATH=${MPI}/lib/openmpi:${MPI}/lib:$LD_RUN_PATH and your path to libimf.so file is /home/stefan

Re: [OMPI users] OpenMPI 1.6.4 and Intel Composer_xe_2013.4.183: problem with remote runs, orted: error while loading shared libraries: libimf.so

Dear Thomas, thank you very much for your very fast replay. Yes I have that library in the correct place: -rwxr-xr-x 1 stefano users 3.0M May 20 14:22 opt/intel/2013.4.183/lib/intel64/libimf.so Stefano Zaghi Ph.D. Aerospace Engineer, Research Scientist, Dept. of Computational Hydrodynamics at *

Re: [OMPI users] OpenMPI 1.6.4 and Intel Composer_xe_2013.4.183: problem with remote runs, orted: error while loading shared libraries: libimf.so

hi Stefano your error message show that you are missing a shared library, not necessary that library path is wrong. do you actually have libimf.so, can you find the file on your system. ./Thomas From: Stefano Zaghi To: us...@open-mpi.org, List-Post: users@lists.open-mpi.org Date:

[OMPI users] OpenMPI 1.6.4 and Intel Composer_xe_2013.4.183: problem with remote runs, orted: error while loading shared libraries: libimf.so

Dear All, I have compiled OpenMPI 1.6.4 with Intel Composer_xe_2013.4.183. My configure is: ./configure --prefix=/home/stefano/opt/mpi/openmpi/1.6.4/intel CC=icc CXX=icpc F77=ifort FC=ifort Intel Composer has been installed in: /home/stefano/opt/intel/2013.4.183/composer_xe_2013.4.183 Into the

[OMPI users] New Cluster Centos 6.4 with Openmpi 1.6.4

Hi im running into a strange problem when trying to start parallell processing with Numcea Fine Marine software for jobs. I have managed to setup openmpi 1.64 on qmaster and all nodes, so they all run the same version. Every time i try to start a job that requires more then 1 node the job die