Quick Start

Overview

We have one High-Performance Computing (HPC) system:
  • Soroban for problems with high CPU requirements and moderate memory needs (up to 90 GB per node)

Soroban
overview_soroban.png

System Access

Before you can use a system, you need to apply for access as described here.

To actually access a system a secure method, such as ssh, has to be used. This is normally run from a text console. You can find more information about how to do this here.

Using Software

A list of application software packages can be found here.

On Soroban, some software is automatically available; other packages have to be loaded via the command modules. You can also install software locally in your home directory.

Running Jobs

Programs apart from editors and the like should not be started directly, but should be submitted to the batch system.

In order to write submit scripts basic Unix skills are necessary. Here are some links to introductory tutorials:

Saving Data

Where data should be stored depends on the type data:

  • important data such as scripts, results: /home
  • temporary data: /scratch

For these two types of file system there are very different backup policies.

More information of on Soroban's file systems may be found here.