Facts & Figures
- The cluster consists of a collection of compute servers (>2000 CPUcores, 30 GPUs, 20 TB ram), 1.7 PB high performance storage and 1.1 PB archive storage running on CentOS Linux.
- It is controlled by the SLURM batch-wise queueing system with a few head nodes and data transfer nodes.
- Data storage is separated between PI groups.
- We provide a central GUIX software management system, notebook services and containersupport.
- Two full time staff members are available to maintain, innovate and support this essential research resource.
To ensure future sustainability, users can participate after a free trial by buying virtual shares to cover their compute demand (in 2020: €1200,-/50k CPUhrs; €1150/5k GPUhrs; €180/TB high-perf storage/yr; €45,-/TB archive storage/yr).
The HPC is for and by the community, and for this reason we want to have an extremely low threshold to start using the HPC facility for researchers on the Utrecht Life Science Campus. Before people join the HPC community with paid accounts which helps ensure the sustainability of this service, there is an option to run in a trial configuration without costs to see if the HPC works for you. This trial account can be compared with ¼ share (so ~12.5 kCPUhrs, ~1.6 kGPUhrs, 250GB storage) and is valid for one year, but ad-hoc projects can always be discussed. Each PI can start a trial account only once. Just as for regular accounts, there are limits to the extend users can reserve resources for their jobs. All trial users share the limits of 1 regular account.