It wasn’t long ago we told you about how Intel had snatched one of AMD’s most important partners, Cray, and now it has slapped AMD’s already torn face another time. Intel and SGI has announced that the two of them will design and build two supercomputers for NASA. One sporting a capacity of 1 PetaFLOPS, which will be ready in 2009, and a second system with a capacity of 10 PetaFLOPS in 2012. The supercomputer will be built at NASA’s Ames Research Center, Moffett Field, in California.
“Achieving such a monumental increase in performance will help fulfill NASA’s increasing need for additional computing capacity and will enable us to provide the computational performance and capacity needed for future missions,” said Ames Director S. Pete Worden. “This additional computational performance is necessary to help us achieve breakthrough scientific discoveries.”
This collaboration spawns of the successful Columbia project which resulted in a system capable of 61 TeraFLOPS, which is enough for top 20 on the Top500 list of the world’s fastest supercomputers. The new Pleiades project will result in a system that is 160 times faster. The systems will be used for modeling and simulations at the NASA Advanced Supercomputing (NAS) facility.
“Intel, working with SGI, is proud to play an important role in helping NASA expand the pursuit of scientific discovery,” said Diane M. Bryant, vice president of Intel’s Digital Enterprise Group and general manager or Server Platforms Group, Intel Digital Enterprise Group. “Systems such as Pleiades challenge the imagination, and guide our exploration of Earth, space, and beyond. As we approach performance that was once thought impossible to achieve, our eyes are opened even wider to the vast possibilities enabled by supercomputing.”
