acm-header
Sign In

Communications of the ACM

ACM TechNews

Five Reasons the ­.s. Tech Lead Is in Danger


View as: Print Mobile App Share:
Cray XK6 supercomputer

The U.S. is hoping that the Cray XK6 high-performance computer will help it win back pole position in global supercomputing.

Credit: Cray

The United States is falling behind other countries in the race to build the next generation of supercomputers.

The development of exascale platforms requires new processor, storage, and networking technologies, and while other countries are making strides in these areas, the U.S. has yet to see similar breakthroughs. The U.S. does not have a plan in place for exascale computing, mostly due to the huge costs involved. For example, the European plan will cost an estimated 3.5 billion Euros over 10 years. Although the U.S. continues to fund petaflop projects, the government has yet to set a budget for exascale development.

"The bottom line is that the U.S. appears stalled and the [European Union], China, and Japan are gearing up for the next generation," says University of Tennessee professor Jack Dongarra.

The White House has said that it does not want to be in an arms race in computer speed, claiming that a focus on speed "could divert resources away from basic research aimed at developing the fundamentally new approaches to [high-performance computing] that could ultimately allow us to 'leapfrog' other nations." However, the U.S. will need sustained basic research funding, including the development of an exascale system, to keep pace with other nations.

From Computerworld
View Full Article

Abstracts Copyright © 2011 Information Inc. External Link, Bethesda, Maryland, USA 


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account