Once you have an account on the platform, you can connect via SSH to the genocluster2.irisa.fr server.

Genocluster2 is the front-end of the cluster where you can submit jobs help with the Sun Grid Engine tool (SGE). You connect to the server via SSH from the computer declared at the creation of your account.

Once logged, you have access to your home directory and a shared directory. Those directories are available on all nodes. We have around 60TB of storage capacity to host your data plus an additional storage to host databanks, automatically updated and indexed on regular basis.

When you submit a job, it is dispatched on one of the computing nodes of the cluster.

Those nodes have different characteristics (cpu,ram), so we have created queues to differentiate them. The list of the queues can be obtained with the command “qconf -sql”. The queue sgi64g.q will for example refer to the servers having 64G of RAM.

We have servers from 32G up to 512G RAM on the nodes, with at least 8 cores each.

You can submit a job with the “qsub” command, and you can monitor your jobs with the “qstat” command.
by default, a “qsub” suppose you will use only 1 core. If you need more, you can ask for more resources (see tutorial).

For interactive operations, it is possible to use the “qrsh” command to login onto a node.

A memento on usages with the cluster is available.
You can find a quick tutorial on SGE on this web site.