The High End Computing Cluster is a centrally-run service to support researchers and research students at Lancaster who require high performance computing. This includes workloads with requirements that can't be met by the IUS or desktop PCs.
The combined facility offers 2200 CPU cores, 11TB of memory, 32TB of high performance filestore and 1PB of medium performance filestore. The service combines what was the previously separately supported services of local high performance computing (HPC) users, the local Particle Physics research group (GridPP) and Lancaster's contribution to the National Grid Service / National Grid Initiative (NGS/NGI).
The cluster operating system is CentOS Linux, with job submission handled by Platform's Load Sharing Facility (LSF). The service supports a wide variety of third-party software including numerical packages, libraries and C and Fortran compilers.
The HEC has three basic components; a login node, where users login in to submit jobs; the compute nodes, which run those jobs; and dedicated file systems, which share user and other files across the cluster.
From the login node, users create a batch job script which describes the tasks their job(s) are to perform in a format similar to a unix shell script. The batch job is then submitted to the Load Sharing Facility job scheduler which will portion out user jobs to free compute nodes. Job submission commands can be supplemented with additional information, such as requests for specific amounts of memory (for large memory jobs), or multiple nodes (in the case of parallel jobs).
Login node: The login node is a Viglen HX420Hi with two quad core Intel Nehalem 2.26GHz CPUs and 24G of memory.
Compute nodes: The compute nodes consist of Viglen HX420Ti chassis, each housing four servers, for a total of 262 compute nodes. Compute nodes are dual socket quad core or hexacore. The standard memory size per compute node is 24G, with a few nodes offering 96G in order to support very large memory jobs. A further 18 nodes support GPU computing, each offering two NVIDIA Tesla M2075 cards.
File store: The primary file storage system is an 32TB Panasas Activescale Series 8 Storage Cluster. A series of Viglen HS424i storage nodes act as secondary file system providing medium-performance filestore for the local GridPP initiative.
A number of statistical and numerical packages and libraries are installed in addition to Fortran 90, C and C++ compilers. Guides to the use of the packages are available here