[prev in list] [next in list] [prev in thread] [next in thread] 

List:       npaci-rocks-discussion
Subject:    [Rocks-Discuss]  FW: Gromacs & Mpirun issue
From:       "Rahul" <rahul () isplpune ! com>
Date:       2017-10-06 7:57:33
Message-ID: 011301d33e77$18ba01b0$4a2e0510$ () isplpune ! com
[Download RAW message or body]

Hi,

 

I am trying to run gromacs on small gpu cluster using mpirun, but out of
two compute nodes gromacs are run on only one compute node. 

 

While the output of qstat -an  command shows the job are running on two
compute nodes.

 

PBS Job script are like this.

 

 

#!/bin/sh

#PBS -l walltime=1:00:00      

#PBS -l pmem=1gb 

#PBS -l nodes=2:ppn=24

#PBS -Nmpi-verify-openmpi    

 

cd $PBS_O_WORKDIR

 

cat $PBS_NODEFILE > nodes

 

mpirun -np 2 -machinefile nodes /usr/local/gromacs/bin/gmx_mpi mdrun -ntomp
6 -gpu_id 01 -v -deffnm npt

 

both the nodes are having two gpu's installed each. We want to run the job
on 4 gpu but somehow it's not working.

 

please correct me if I missed something.

 

Regards,

Rahul.

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.sdsc.edu/pipermail/npaci-rocks-discussion/attachments/20171006/c9226d1a/attachment.html \



[prev in list] [next in list] [prev in thread] [next in thread]