ScienceCluster is a batch-queue system capable of running different type of workloads including those requiring CPUs with a high speed interconnect and GPUs.
ScienceCluster and its different partitions run on top of ScienceCloud and is centrally managed by S3IT. Should your use case require some specific configuration, you also have the flexibility to setup your own virtual cluster using ScienceCloud.
Table of contents
Why would you need to run your application on ScienceCluster?
With a cluster you can access a set of machines that work together so that, in many respects, they can be viewed as a single system.
Our cluster gives you the possibility to choose the most suitable computational resources for each applications you need to run: CPU intensive workloads or workloads requiring a large amount of shared memory as well as workloads requiring a GPU accelerator.
How to get access
Before getting access to the ScienceCluster your group needs to have an S3IT Infrastructure Services agreement in place. After that, direct an authorized person (group leader / project owner or technical contact) to email S3IT and request that your account (i.e., username) be enabled under their ScienceCluster project. Once your account is enabled you'll have access to all cluster partitions. For more information on connecting to the cluster, refer to the relevant ScienceCluster documentation.