compute.cla is the name of CLA's Linux cluster which is capable of using multiple servers to speed processing.  In its current configuration it consists of 6 servers totaling 148 physical (296 with Hyper-Threading) CPU cores and a total of just under 2TB of RAM.  It uses TORQUE, a job queuing system, to allocate resources efficiently across the servers.  It also has an Nvidia P100 GPU available for use.  Please let us know if you’d like to use the GPU so we can provide access to the appropriate queue.  Anyone with a CLA Linux/Unix account can use compute.cla.

Connect

Connect to lts.cla.umn.edu using the NX client (see z.umn.edu/ltsconnect).
Once connected to lts, SSH to compute.cla.umn.edu

Decide Session Type

  • Use an interactive session when you need to see what is happening - e.g. using a graphical application
  • Use a batch session when you have a script to run
  • Use a batch session when you need more power or longer runtimes

Interactive Session

Open a Terminal and ssh to compute.cla.umn.edu (just “compute” works for short if connecting via lts.cla.umn.edu) and login when prompted.

 cla-lts:~> ssh compute


Enter qsub -IX to start an interactive session using the default resources (8GB of memory, 24 hour walltime, and 2 cores on one node).  Please note that at the end of the "walltime" your session is terminated so resources are available for others.  Adjust your walltime as needed (see below table for limits).

The below example starts an interactive session, loads the module for MATLAB, and then runs MATLAB.

  compute:~> qsub -IX
 c5:~> module load matlab
 c5:~> matlab
-I tells it you want an interactive session and -X tells it you want graphical programs forwarded to your screen.  compute.cla will find a node with resources and you’ll be at the command prompt of that node (nodes are numbered C1 - C6).  From here you can run software just as you would on any of our Linux servers.  Most of our software is now provided via modules.  Please see using modules for information on how to load and use software via modules.

If you find you need a more powerful interactive session you can ask qsub to give you more resources by following the example below.  This command will give you 16GB of memory, 48 hours, and 8 cores on one node.

 compute:~> qsub -IX -l mem=16GB,walltime=48:00:00,nodes=1:ppn=8

For more information on using modules, please see our page on using modules.

Batch

Using compute.cla for batch jobs is similar to interactive in command but you drop the -IX, add the queue (-q batch) and add the name of the script you want to run.

In the below example we have a script called analysis.sh that we'd like to run.  To run it, enter this command:

 compute:~> qsub -q batch analysis.sh

This example shows the command for a batch job requesting specific resources.

 compute:~> qsub -q batch -l mem=16GB,walltime=48:00:00,nodes=1:ppn=8 analysis.sh

Launching Applications

In general, the latest applications are best used via modules.  See our page on using modules for more information.
If the app you need isn't in modules, software is located in /pkg/software_depot/app and /pkg/software_depot/bliss (neuroimaging specific apps)

Options

 -l walltime=hh:mm:ssRequests the amount of time needed for the job. Default is 24 hours.  At the end of the walltime, the session terminates.
 -l nodes=n:ppn=pRequests number of nodes and processors per node. The range of ppn values depends on the hardware you are running on.  If this option is not used the default is 1 node and 4 cores
 -l mem=amountRequest the total amount of memory needed across all nodes. e.g. mem=4GB
 -q queue nameRequests a particular queue.  With out this, it defaults to the Interactive queue

Resource Availability

The below tables shows the default and maximum compute resources for each queue.  If you find you're needing more resources than are available let us know and we can add you the highmem or multinode queues as needed.