HPC Grid Tutorial: How to Run a Converge Job

How to Run a Job for Converge on a Single Node

Follow these steps to run a Converge job on a single node.

Watch the video tutorial here!

1. Log on to the Grid. 

2. Copy the required contents using the following command:

cp -R /wsu/el7/scripts/tutorial/WSU-Case . 

3. The job script is jobfile_singlenode_converge.txt. It contains the following script: 

#!/bin/bash

#PBS -N Singlenode_Converge

#PBS -q wsuq

#PBS -l select=1:ncpus=4:mem=5GB:net=10e:mpiprocs=5:cpu_type=Intel

#PBS -m ea

#PBS -M zz9992@wayne.edu

 

echo "MPD_SECRETWORD=${USER}" > ~/.mpd.conf

chmod 600 ~/.mpd.conf

 

cd ~/WSU-Case/

module load converge/2.4-serial

converge-2.4.16-serial super > output_singlenode_converge.out

NOTE: Be sure to change '#PBS -M zz9992@wayne.edu' with YOUR email! 

4. Change to the directory that has the job script by typing the following command: cd WSU-Case

5. To submit the job type: qsub jobfile_singlenode_converge.txt

6. The job is submitted. You can check to see what node it is running on with the following command: qme

The red box shows the job ID, the blue one shows the name of the job and the yellow one shows the node the job is running on. The output can be found in output_singlenode_converge.out.

How to Run a Job for Converge on Multiple Nodes

Follow these steps to run a Converge job on many nodes.

Watch the video tutorial here!

1. Log on to the Grid.

2. Copy the required contents using the following command:

cp -R /wsu/el7/scripts/tutorial/WSU_Case .

3. The file that has job script is jobfile_multinode_converge.txt. It contains the following script: 

#!/bin/bash

#PBS -N Converge_Multinode

#PBS -q wsuq

#PBS -l select=2:ncpus=12:mem=10GB:net=10e:mpiprocs=12:cpu_type=Intel

#PBS -m ea

#PBS -M zz9992@wayne.edu

 

### Replace jobdir with the directory with the .in files (working directory)

WORKDIR=${HOME}/WSU-Case

echo "MPD_SECRETWORD=${USER}" > ~/.mpd.conf

chmod 600 ~/.mpd.conf

 

if [[ ! -d ${WORKDIR} ]]

then   

echo "WORKDIR ${WORKDIR} does not exist" >&2   

exit 1

fi

 

THREADS=`cat $PBS_NODEFILE | wc -l`


cd ${WORKDIR}

ml swap openmpi3 mpich/3.2.1

ml converge/2.4-mpich

time mpirun -np ${THREADS} converge-2.4.16-mpich super > output_multinode_converge.out

 

NOTE: Be sure to change '#PBS -M zz9992@wayne.edu' with YOUR email! 

4. Change to the directory that has the job script by typing the following command: cd WSU-Case

5. To submit the job, type: qsub jobfile_multinode_converge.txt

6. The job is submitted. You can check to see what node it is running on with the following command: qme

The red box shows the job ID, the blue one shows the name of the job and the yellow one shows the nodes the job is running on. The output can be found in the output_multinode_converge.out.