Access to supercomputing facilities may be available upon request. We have made arrangements with the University of Minnesota Supercomputer Institute which allow us to allot a limited amount of supercomputer time to IMA researchers. The exact equipment which may be available to IMA researchers changes frequently, and we suggest you check the website at http://www.msi.umn.edu/ for details on the computing facilities available.
The Supercomputing Institute currently provides supercomputing resource allocations and technical support for IBM SP, IBM Regatta and Altix 3000 supercomputers as well as for a Linux Cluster supercomputer.
The Institute has acquired a new 48-processor, 1.3 GHz Altix 3000 shared memory server from SGI. This machine runs on the Linux operating system and contains 96 GB of memory.
The Linux Cluster consists of 82 2-processor Netfinity nodes from IBM. Of these 82 nodes, 76 are available for computation through a queuing system, 5 are file servers, and one node is for interactive use. Seventeen of these nodes have two 733 MHz Intel Pentium III processors sharing 1 GB of memory. The remaining nodes have two 1.26 GHz Pentium III processors sharing 3.25 GB of memory. The nodes are connected together using Fast Ethernet and Myrinet. A cluster file system provides 2.5 TB of disk that can be used on all nodes.
The IBM SP consists of a 370-processor supercomputer with 663 GB of memory. There are 94 nodes in this system. The nodes available for computation are:
In addition, there is a 16-processor Silvernode IBM SP with 12 GB of memory and 332 MHz PowerPC 604e processors. There are 4 TB of disk available on the SP.
The IBM Regatta consists of four compute nodes with 1.3 GHz Power4 processors, file servers and an interactive node. Two of the compute nodes have 32 processors sharing 64 GB of memory, while the another node has 24 processors sharing 24 GB of memory, and the final node has 32 processors sharing 128 GB of memory. The interactive node is a WinterHawk+ node. Four 4-processor NightHawk nodes are used as file servers for 7 TB of disk.
In order to get computing time, you must submit a proposal consisting of one or two brief paragraphs to the associate program director describing your research project and the amount of CPU time that you think you will need. If this is of interest, please contact Arnd Scheel or Kumsup Lee.