Darpa seeks new power dynamic for continuation of Moore's Law

Jan 30, 2012

Computational capability is an enabler for nearly every military system.  But computational capability is increasingly limited by power requirements and the constraints on the ability to dissipate heat.  One particular military computational need is found in intelligence, surveillance and reconnaissance systems where sensors collect more information than can be processed in real time.  To continue to increase processing speed, new methods for controlling power constraints are required.

In the past, computing systems could rely on increasing computing performance with each processor generation.  Following Moore’s Law, each generation brought with it double the number of transistors.  And according to Dennard’s Scaling, clock speed could increase 40 percent each generation without increasing power density.  This allowed increased performance without the penalty of increased power.

“That expected increase in processing performance is at an end,” said DARPA Director Regina E. Dugan. “Clock speeds are being limited by power constraints. Power efficiency has become the Achilles Heel of increased .”

DARPA’s Power Efficiency Revolution for Embedded Computing Technologies (PERFECT) program seeks to improve for embedded computer systems, providing more computing per watt of electrical . To increase awareness of this program and attract potential researchers, DARPA has scheduled a Proposers’ Day workshop Feb. 15 in Arlington, Va. Proposers’ Day details are available through the Special Notice located here.

As transistor operating voltages approach logic threshold voltage, device operating characteristics change dramatically, decreasing both reliability and maximum operating frequency.  Since reliability and operating frequency are critical to its user base, commercial industry has only limited ability to reduce operating voltage to avoid these clock frequency decreases. PERFECT seeks revolutionary approaches to processing-power efficiency to overcome these limitations.  This approach includes near threshold voltage operation and massive heterogeneous processing concurrency, combined with techniques to effectively use the resulting concurrency and tolerate the resulting increased rate of soft errors.

Explore further: Dutch chipmaker NXP to buy Freescale Semiconductor for $12B

add to favorites email to friend print save as pdf

Related Stories

Versatile ultra-low power biomedical signal processor

Feb 25, 2011

At today’s International Solid-State Circuit Conference (ISSCC2011), imec, Holst Centre and NXP present a versatile ultra-low power biomedical signal processor, CoolBio, meeting the requirements of future ...

Efficiency record of combined cycle power plant

May 24, 2011

A new Siemens gas turbine operated in a combined cycle with a steam turbine in Irsching, Bavaria, has set a world record for efficiency, making it an outstanding example of green technology. The net efficiency ...

Shredder Challenge solved

Dec 05, 2011

Almost 9,000 teams registered to participate in DARPA's Shredder Challenge. Thirty-three days after the challenge was announced, one small San Francisco-based team correctly reconstructed each of the five challenge documents ...

Recommended for you

Dutch chipmaker NXP to buy Freescale Semiconductor for $12B

Mar 02, 2015

Dutch chipmaker NXP Semiconductors N.V. said Sunday it had agreed to buy its smaller rival Freescale Semiconductor Ltd. for $11.8 billion in a deal that will make it the biggest supplier of microchips to the automotive industry.

User comments : 0

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.