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)
Before you can use a system, you need to apply for access as described
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.
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.
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:
Where data should be stored depends on the type data:
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.
- important data such as scripts, results:
- temporary data: