November 14, 2011 – Cray Inc. will take the place left by IBM in the development of a one-petaflop supercomputer for the National Science Foundation’s Blue Waters project at the University of Illinois’ National Center of Supercomputing Applications (NCSA).
NCSA finalized the $188 million, multi-year contract with Cray on Monday, with expectations to stay on track with the originally scheduled deployment in 2012. The Blue Waters supercomputer will focus on scalability and resilience of algorithms and applications, the use of solution accelerators, and simultaneous use of computational components with different characteristics to “move the state of computational science into the petascale era,” according to an NCSA news release. The Blue Waters massive information prowess is expected to be harnessed for research in areas such as nanotechnology, natural disasters, and the evolution of the universe.
Phyllis Wise, university chancellor, said in a news release on the deal: “The Blue Waters team has the technological capability and the commitment to make this important resource a reality – a resource that will help scientists and engineers solve their most challenging problems.”
IBM backed out of the project in August, after a joint announcement with NCSA where both parties stated they couldn’t reach an agreement on the completion and maintenance of the complex technology involved. Subsequently, IBM returned about $30 million it had received to complete the project and NCSA gave back three IBM P775 racks at its data center. The university selected IBM in 2007 with a finished project expected by next year.
Under the Cray contract, Blue Waters will consist of more than 235 Cray XE6 cabinets based on the recently announced AMD Opteron 6200 Series processor and more than 30 cabinets of a future version of the recently announced Cray XK6 supercomputer with NVIDIA Tesla GPU computing capability incorporated into a single, powerful hybrid supercomputer.
Based in Seattle with about 800 U.S. employees, Cray technology focused on “adaptive supercomputing,” a combination of multiple processing capabilities that adapt to the requirements of each application in a single system.
Register or login for access to this item and much more
All Information Management content is archived after seven days.
Community members receive:
- All recent and archived articles
- Conference offers and updates
- A full menu of enewsletter options
- Web seminars, white papers, ebooks
Already have an account? Log In
Don't have an account? Register for Free Unlimited Access