Global Sources
EE Times-Asia
Stay in touch with EE Times Asia
?
EE Times-Asia > Manufacturing/Packaging
?
?
Manufacturing/Packaging??

Is there life after CMOS?

Posted: 23 Oct 2014 ?? ?Print Version ?Bookmark and Share

Keywords:Moore's Law? technology? IEEE?

Technology is getting more complicated, and whatever comes next will likely challenge old assumptions both for technologists and society at large. That was one of the conclusions from an IEEE symposium in California, which explores the 20-year technology horizon.

The discussions examined some of the ways engineers need to take responsibility to represent the capabilities and limits of technology to a world that depends on it but often fails to understand it.

Technology is "getting more complicated as we go, and the public is not catching on to this," said Robert Colwell, a consultant and former processor architect at Intel.

He noted troubling issues such as people increasingly taking for granted and de-valuing increasingly complicated technologies such as smartphones and GPS systems. The consumer products are expected to operate perfectly, and when they don't society seeks someone to blame and punish. "That doesn't fix the problem," he said.

Even more troubling, sometimes in a debate non-technical individuals disregard scientific findings and offer their personal experience as if it were valid scientific evidence, Colwell said.

Dean Kamen, a veteran inventor and advocate of engineering education, touched on the topic in a keynoted delivered on videotape:

If we as an engineering community don't focus on the right issues and help the pubic understand, we should not expect the future to continue to afford all the advantages of the advancing technology. A lot of people are afraid of [increasingly complex technology] and unwilling to invest in it. Yet society demands the best of technology and has lower and lower tolerance for any risk. We need people to be better educated about the risks and rewards of technology.

Beyond Moore's Law

The panellists agreed Moore's Law is approaching an end, and it's not clear what enabling technology could replace it as an engine of exponential technology growth.

"We are no longer on the exponential free ride called Moore's Law... so we will look for other opportunities that will not be exponential and then shift to something that will change our assumptions," said Thomas Sterling, a supercomputer guru and professor at Indiana University.

He predicted new kinds of devices and non Von Neumann computer architectures will be adopted in the next 20 years as today's chips and computers run out of gas. In the meantime, "we continue to make computers based on ideas from 40 years ago," he said.

Sterling and others agreed that even with today's technology, there is still opportunity for orders of magnitude improvements in energy efficiency. "The vast majority of energy cost today is in data movement between chips," said Sterling.

IBM researcher Wilifried Haensch said neuromorphic systems patterned on the human brain look like the most promising bet for post-CMOS advances. "For pattern recognition in big data, this could be a game changer," he said.

The approach requires a switch to analogue computing, a power-hungry technique that requires research in new materials. Current work focuses on creating devices that could mimic a synapse, he said.

Carbon nanotubes are seeing a resurgence of interest among researchers. Haensch showed concepts for using them to grow 3D structures on silicon wafers as an alternative to chip stacks using through-silicon vias. "The only fundamental road block is that there are no tools to get a reasonable contact at small dimensions," he said.

He also discussed other options such as adiabatic and quantum computing that so far seem less promising.

"None of those technologies will be mainstream, but some may find very useful niches," said Colwell of all the techniques Haensch described. Colwell, a former Intel processor architect, is well known for his views on the outlook for today's CMOS technology:

We are in the twilight of Moore's Law. You can argue when it will end but there's no chance it will continue until 2035, and there are no credible replacements.

I don't see Intel doing the kind of preparation I think they should be doing. It's a little scary for me as a stockholder with lots of friends working there... I think the industry will stagger on like walking dead not headed in any useful direction for a while.

The main thing we have to do is admit Moore's Law is going to die and think through that reality.

- Rick Merritt
??EE Times





Article Comments - Is there life after CMOS?
Comments:??
*? You can enter [0] more charecters.
*Verify code:
?
?
Webinars

Seminars

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

?
?
Back to Top