SGI Unveils Blade Platform

SUNNYVALE, Calif. -- SGI (NASDAQ: SGIC) today unveiled SGI Altix® ICE, a next-generation platform that brings all the advantages of the company’s expertise in high-performance computing (HPC) to a tightly integrated, cool-running blade solution. Designed by SGI to close the growing gap between performance and user productivity, SGI® Altix® ICE 8200 is the first in a new line of bladed servers purpose-built to handle true HPC applications and large scaleout workloads.

Even as it accommodates larger and more varied workloads, SGI Altix ICE doesn’t force users to accept compromises in price/performance, power and space efficiency, reliability and manageability. In fact, many of the platform’s advantages – including price/performance – actually improve as customers add blades and racks. SGI Altix ICE enables large scale-out environments while minimizing their demands on the data center’s space and power. Its ultra-dense rack architecture delivers up to 40 percent more compute performance per floor tile than competing blades. A single SGI Altix ICE 8200 rack can be powered by as many as 512 Intel® Xeon® processor cores and deliver 6 TFLOPS of performance.

Around the world, SGI is seeing strong customer interest in the new platform. SGI Altix ICE systems have already been installed at a number of customer sites, including the University of Exeter in England and General Atomics in San Diego.

“General Atomics is always looking for the fastest computer because we work with increasingly large models,” said Dave Wade, senior systems programming analyst, General Atomics, one of the world’s leading resources for high-technology systems development. “But the capacity of our computer room is maxed, and asking it to handle more heat is not cost-effective. With SGI Altix ICE, SGI has delivered the fastest computer with a significant bonus – an exceptionally small footprint and a very, very low cost in energy. SGI Altix ICE meets every criterion, and allows our scientists and engineers to solve large models in days, rather than weeks.”

SGI