APPLICATIONS

SEATTLE--Global supercomputer leader Cray Inc. (Nasdaq:CRAY) today reported that its systems captured first, second and third place in the most powerful class of single computers in IDC's latest supercomputer rankings released earlier this week. "We expect to become increasingly prominent in the IDC and other rankings as our new Cray X1 systems are installed in greater numbers and larger configurations, and as initiatives such as our 'Red Storm' program for Sandia National Laboratories become operational," said Cray Chairman and CEO Jim Rottsolk. Eight of the 10 highest-ranking single computers in the Capability Class were from Cray(R), with 120-processor Cray X1(TM) systems finishing first and second, followed by a large Cray T3E(TM) supercomputer system in third place. IDC defines the Capability Class as including "computers used to tackle the most demanding individual problems (the traditional 'supercomputer' segment of the market)." In reporting the results, IDC noted that "Cray showed renewed momentum." Cray captured the top spots and represented 36 percent of the 200 highest-ranked systems in the Capability Class single computer category. Cray also did well in the Enterprise Class that includes systems "priced at $1 million or more and used primarily for running many small to medium size jobs." With its large installed based of Cray SV1(TM) systems, the company accounted for 31 percent of the 200 top-ranked Enterprise Class single computers. Cray Chairman and CEO Jim Rottsolk said, "It is also important to remember that the performance advantage of Cray systems typically is much larger on demanding real-world applications than on high-level benchmark tests." In May 2003, Cray reported that the Cray X1 supercomputer demonstrated superior speed and efficiency on the industry-standard Linpack test. The results were published in the Linpack report maintained by Professor Jack Dongarra, University of Tennessee. On Cray X1 systems varying from 4 to 60 processors, the per-processor speed averaged 11.55 billion calculations per second (gigaflops), 2.5 to 10.6 times faster than the published per-processor speeds of HPC products from other U.S. vendors. In addition to its absolute speed advantage, the Cray X1 system demonstrated efficiency (actual speed as a percentage of theoretical "peak" speed) averaging 90 percent, substantially better than HPC systems from major U.S. competitors.