If you don’t know what Dennard Scaling is, the chances are strong you don’t labor in electronics. Robert Dennard, longtime IBM researcher, inventor of the DRAM and the fellow for whom Dennard Scaling was named, is this year’s recipient of the Robert N. Noyce Award from the Semiconductor Industry Association. It is the semiconductor industry’s highest honor.
Fittingly IBM recently posted a tribute article to Dennard written by John Markoff.
Dennard observed that scaling transistor area down roughly 50 percent for each technology generation would increase clock frequency about 40 percent and keep power consumption constant (for twice the number of transistors). Gordon Moore’s observation – Moore’s Law – was that the number of transistors on a chip doubles approximately every two years.
While Moore’s Law became the louder rallying cry, Dennard Scaling represents the physics underpinning Moore’s Law. Markoff’s tribute piece recalls that Dennard was one of what IBM chair Thomas Watson referred to as wild ducks – those folks who don’t stick to flying in formation but go in their own, often-inspired direction.
As noted in the IBM article:
“Dennard’s insight would soon lead to DRAM chips with a kilobit (a thousand bits) of memory. Over the next five-and-a-half decades DRAM would, generation by generation, evolve into an 8-gigabit (8 billion bits) storage medium. Today, 8-gigabit DRAM chips are found in everything from the smartphones in our pockets to the supercomputers that power the global economy. And 16-gigabit DRAM is on the way. Not only did DRAM memory sweep away the earlier magnetic technologies. It became the foundational technology for an industry that has reshaped human society – from the way we work, to the way we entertain ourselves and even to the way we fight wars.”
For several years, the industry has been bemoaning the decline of Moore’s Law and Dennard’s Scaling as bringing the end to an era of rapid advance in computational technology performance.
True to his ‘wild duck’ instinct, Dennard is quoted by his colleague Russ Lange, an IBM Fellow and former IBM Vice President of Technology: “Bob, and I would always have lively discussions about whether there was there going to be an end to the scaling. And he would say, ‘Yes, there’s an end to scaling. But there’s no end to creativity.’”
Feature photo source: IBM Research