| Revision as of 21:55, 29 February 2012 editRunningonbrains (talk | contribs)Administrators22,896 editsm wl NCAR← Previous edit | Revision as of 22:34, 12 June 2012 edit undoBrianbncar (talk | contribs)45 edits This is the first in a series of edits to update this page. I work for NCAR, and my new information has been reviewed and approved by senior management.Next edit → | ||
| Line 1: | Line 1: | ||
| '''Yellowstone'''<ref>, NCAR Computational and Information Systems Laboratory (CISL) website: Resources. Retrieved 2012-06-12.</ref> will be the inaugural computing resource at the ]-Wyoming Supercomputing Center<ref>, University Corporation for Atmospheric Research (UCAR) website, Retrieved 2012-06-12.</ref> (NWSC) in Cheyenne, Wyoming. It is being installed, tested, and readied for production in the summer of 2012<ref>, IBM News Release, 08 Nov 2011.</ref>. Yellowstone will be a highly capable ] system designed for conducting breakthrough scientific research in the interdisciplinary field of ]. | |||
| The '''Yellowstone''' is the name of the new petascale supercomputing resource in the ]-Wyoming Supercomputing Center (NWSC) in Cheyenne, Wyoming with production computing operations expected to begin in the summer of 2012. | |||
| Yellowstone will be an IBM iDataPlex supercomputer system, consisting of 4,662 nodes, each with two Intel Sandy Bridge EP processors, for a total of 74,592 processor cores and 149.2 terabytes of memory. Nodes will be connected using a Mellanox FDR InfiniBand full fat tree. Nodes will run Red Hat Enterprise Linux Version 6. | Yellowstone will be an IBM iDataPlex supercomputer system, consisting of 4,662 nodes, each with two Intel Sandy Bridge EP processors, for a total of 74,592 processor cores and 149.2 terabytes of memory. Nodes will be connected using a Mellanox FDR InfiniBand full fat tree. Nodes will run Red Hat Enterprise Linux Version 6. | ||
Revision as of 22:34, 12 June 2012
Yellowstone will be the inaugural computing resource at the NCAR-Wyoming Supercomputing Center (NWSC) in Cheyenne, Wyoming. It is being installed, tested, and readied for production in the summer of 2012. Yellowstone will be a highly capable petascale system designed for conducting breakthrough scientific research in the interdisciplinary field of Earth system science.
Yellowstone will be an IBM iDataPlex supercomputer system, consisting of 4,662 nodes, each with two Intel Sandy Bridge EP processors, for a total of 74,592 processor cores and 149.2 terabytes of memory. Nodes will be connected using a Mellanox FDR InfiniBand full fat tree. Nodes will run Red Hat Enterprise Linux Version 6.
The central file and data storage resource, called GLADE, will consist of file system servers and storage devices that will be linked to the supercomputer systems and eventually provide 16.42 petabytes of usable disk space.
The Yellowstone system features 9.7 million times the computational rate, 3.4 million times the disk capacity, and 19 million times the central memory size of one of the world’s first supercomputers, the Cray 1-A, which supported NCAR’s computational science between 1977 and 1989.
References
- "Yellowstone", NCAR Computational and Information Systems Laboratory (CISL) website: Resources. Retrieved 2012-06-12.
- "NCAR-Wyoming Supercomputing Center Fact Sheet", University Corporation for Atmospheric Research (UCAR) website, Retrieved 2012-06-12.
- NCAR Advances Weather Research Capabilities With IBM Supercomputing Technology, IBM News Release, 08 Nov 2011.
- http://www.theregister.co.uk/2011/11/10/ncar_yellowstone_super_ibm
- http://www-03.ibm.com/press/us/en/pressrelease/35946.wss
- http://www.cesm.ucar.edu/management/SSC/Presentations/yellowstone.pdf