Misplaced Pages

Yellowstone (supercomputer): Difference between revisions

Article snapshot taken from Wikipedia with creative commons attribution-sharealike license. Give it a read and then ask your questions in the chat. We can research this topic together.
Browse history interactively← Previous editNext edit →Content deleted Content addedVisualWikitext
Revision as of 21:42, 28 December 2011 editSatusguy (talk | contribs)48 editsNo edit summary← Previous edit Revision as of 21:55, 29 February 2012 edit undoRunningonbrains (talk | contribs)Administrators22,896 editsm wl NCARNext edit →
Line 1: Line 1:
The '''Yellowstone''' is the name of the new petascale supercomputing resource in the NCAR-Wyoming Supercomputing Center (NWSC) in Cheyenne, Wyoming with production computing operations expected to begin in the summer of 2012. 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 21:55, 29 February 2012

The Yellowstone is the name of the new petascale supercomputing resource in the NCAR-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.

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

  1. http://www.theregister.co.uk/2011/11/10/ncar_yellowstone_super_ibm
  2. http://www-03.ibm.com/press/us/en/pressrelease/35946.wss
  3. http://www.cesm.ucar.edu/management/SSC/Presentations/yellowstone.pdf

External links

Category: