BwUniCluster3.0

This wiki is work-in-progress

The bwUniCluster 3.0+KIT-GFA-HPC 3 is the joint high-performance computer system of Baden-Württemberg's Universities and Universities of Applied Sciences for general purpose and teaching and located at the Scientific Computing Center (SCC) at Karlsruhe Institute of Technology (KIT). The bwUniCluster 3.0 complements the four bwForClusters and their dedicated scientific areas.

Transition bwUniCluster 2.0 to → bwUniCluster 3.0

The HPC cluster bwUniCluster 3.0 is the successor of bwUniCluster 2.0. It features accelerated and CPU-only nodes, with the host system of both node types consisting of classic x86 processor architectures. To ensure that you can use the new system successfully and set up your working environment with ease, the following points should be noted. Registration All users who already have an entitlement on bwUniCluster 2.0 are authorized to access bwUniCluster 3.0. The user only needs to register for the new service at https://bwidm.scc.kit.edu . Changes Hardware, software and the operating system have been updated and adapted to the latest standards. We would like to draw your attention in particular to the changes in policy, which must also be taken into account. Changes to hardware, software and policy can be looked up here: Summary of Changes Migration bwUniCluster 3.0 features a completely new file system. There is no automatic migration of user data! In order to move data that is still needed, user software, and user specific settings from the old HOME directory to the new HOME directory, or to new workspaces, instructions are provided here: Data Migration Guide

Training & Support

Getting Started E-Learning Courses Support FAQ Send Feedback about Wiki pages

User Documentation

Access: Registration, Deregistration Login Hardware and Architecture Compute Resources File Systems Cluster Specific Software Using Containers Runnning Jobs Running Batch Jobs Running Interactive Jobs Interactive Computing with Jupyter Operational Changes

Cluster Funding

Please acknowledge bwUniCluster 3.0 in your publications.