The University of Leicester in the UK has consolidated its HPC capabilities into a private cloud infrastructure with Panasas ActiveStor, a high-performance parallel storage system running over 10GbE and InfiniBand. The centralised supercomputer, Advanced Leicester Information and Computational Environment (ALICE), allows multi-disciplinary researchers to run computationally intensive research projects quickly and efficiently while resulting in significant cost savings for the university.
‘Academic departments typically struggle to secure research funding to employ skilled IT support staff simply to administer their HPC systems,’ said Dr Chris Rudge, facility manager for the UK Astrophysics Fluids Facility at the University of Leicester, who was tasked with creating the centralised supercomputing facility. ‘Panasas storage performance and manageability were the key reasons that the University of Leicester chose Panasas for ALICE. Benchmarking during the tender process demonstrated clearly that Panasas offered the best performance both on a per-node basis and also without degradation of the aggregate performance with access from multiple nodes.’
Prior to ALICE, Leicester’s researchers utilised custom HPC clusters scattered throughout the campus. The new system had to scale out performance on a single system and be both reliable and easy to use, particularly for academics who do not have expertise in managing HPC clusters. By consolidating its high-performance storage and compute resources into a centralised private cloud, the university avoided the cost of over-provisioning individual HPC clusters to meet the demands of peak workloads. The private cloud allows researchers to test new ideas with smaller problem sizes, as well as perform a small number of large runs that utilise all 2,048 of ALICE’s processing cores.
