Global Sources
EE Times-Asia
Stay in touch with EE Times Asia
EE Times-Asia > Processors/DSPs

Power use restricts HPC progress, says CEO

Posted: 18 Nov 2011 ?? ?Print Version ?Bookmark and Share

Keywords:supercomputing? HPC? energy consumption?

The quest for developing the fastest supercomputer may never actually end, but designers may be headed for a detour if one issue doesn't get addressed soon enough. Nvidia Corp.'s CEO, Jen-Hsun Huang, validates that concern saying "the graphics processor company now thinks in terms of 'power limits' as it designs future products because power has become a limiting factor."

The future of computing could be seriously constrained by the subject of electrical power rather than raw computing horsepower. Huang stated that increasing energy efficiency of high-end computers is needed to continue pushing the limits of what can be done. That includes realistic graphics for video games and animated movies, but also more powerful specialized devices such as portable medical devices or consumer robots.

The company makes GPUs for video game consoles and professional workstations but are also being used in high-performance computing (HPC). In fact, one of the reasons the Barcelona Supercomputing Center chose to build its system with Nvidia's GPUs and ARM-based CPUs is because they are relatively energy efficient, according to the center.

Barcelona Supercomputing Center

The Barcelona Supercomputing Center, which will build a supercomputer using Nvidia GPUs, is located in a former chapel.

"We think as a company in power envelopes now," Huang revealed. "In order for us to deliver the best performance, we need to know the power limits we have."

The industry target he set was to achieve one exaflop of computations with 20MW by 2019. In this year's list of the Top500 supercomputers, the K supercomputer from Japan topped the 10 petaflops mark and consumes 12MW of power. 'Flops' stands for floating-point operations per second, or how many calculations a computer can do using an industry benchmark. One exaflop would be a bit less than 100 times the computing power of the K supercomputer yet 20MW would be far less power per computing operation.

"Translating that sort of power efficiency to a workstation would result in a workstation that consumes 1,000W of power and can perform hundreds of teraflops, which was what IBM's Blue Gene supercomputer did in 2006," Huang continued.

Concern over the rapid escalation in power consumption has led to significantly more efficient processors from Intel, AMD and others. But it has also resulted in high-end computers being designed specifically to take advantage of low-power processors.

- Martin LaMonica

Article Comments - Power use restricts HPC progress, sa...
*? You can enter [0] more charecters.
*Verify code:


Visit Asia Webinars to learn about the latest in technology and get practical design tips.

Back to Top