Cirrus is one of the EPSRC Tier-2 National HPC Facilities
Housed at EPCC's Advanced Computing Facility, Cirrus is a flexible, state-of-the-art High Performance Computing system that provides an ideal platform for users to solve their computational, simulation, modelling, and data science challenges.
Cirrus is available for users in both academia and industry.
Access to Cirrus
Information on how to access Cirrus resources is available on the Cirrus website:
The Cirrus service
The service, which began in 2017 and will run for at least 4 years, comprises a number of components:
- User and computational science and engineering support, including training (EPCC)
- Accommodation (University of Edinburgh)
- Hardware (SGI)
- Systems support (EPCC).
Support for science
Computational science & engineering support
Computational Science and Engineering (CSE) support on Cirrus is provided by EPCC. It includes responsibility for helping users with porting, optimising and developing their codes for Cirrus, ensuring that the correct scientific software is installed on the system to meet user requirements, providing advice and best practices to enable users to exploit Cirrus resources.
Any enquiries about using Cirrus should be sent to the Cirrus Helpdesk.
Cirrus is based around the core compute resource: a 280 node (10,080 core) SGI ICE XA high performance computing (HPC) cluster. The compute nodes each contain two 18-core Xeon "Broadwell" processors and have 256 GiB memory. The compute nodes are all linked using a low latency, high bandwidth FDR Infiniband network.
For more information on the Cirrus hardware please see: