CeMESS operates a medium-sized high-performance compute cluster specialised in bioinformatics and computational life science. The main difference to larger, generic computing facilities such as the Vienna Scientific Cluster (VSC) is the rich, flexible, and up-to-date bioinformatics software repository, the availability of major biological databases on-site, and fast, local storage space for processing of big data. This system allows most users to analyse their data without any software installation, simply by using the pre- installed tools and databases.

The cluster is based on common PC architecture and contains several login nodes for job testing and submission, the actual compute nodes, and a large storage array. It contains more than 3500 CPU cores and up to 2 TB RAM per node. Copies of relevant biological databases (such as NCBI nt and nr) are available. Local high-speed disks in all compute nodes accelerate I/O intensive tasks. Software is provided via a modular environment, where applications and specific versions are activated and deactivated as needed. The storage system has a total capacity of about 1.5 PetaByte based on redundant, network attached disk arrays and parallel filesystems. We operate three redundant virtualisation servers that host specific working environments. Virtual machines are also used to operate our publicly available resources, such as web portals, databases and user-friendly visualisation tools.