acm-header
Sign In

Communications of the ACM

ACM TechNews

Get Ready For the Computers of the Future


View as: Print Mobile App Share:
Sandia National Laboratories Francois Leonard holds a wire mesh cylinder similar in design to a carbon nanotube that might form the basis for future computing technology.

Computing experts at Sandia National Laboratories are exploring what computers of the future might look like: new types of machines that do more while using less energy.

Credit: Randy Wong

Sandia National Laboratories computer scientists are exploring ways next-generation computers can continue to make performance gains while reducing energy consumption.

Rob Leland, head of Sandia's Computing Research Center, says the lab's researchers are considering new transistor-level devices and computer architectures as part of the Beyond Moore Computing project on future computing.

Energy costs are approaching a point of making more powerful future supercomputers prohibitively expensive. Leland says new architectures are needed to reduce energy costs associated with moving data. Eventually, new technologies that use less energy at the transistor device-level also will be needed.

In the future, Sandia predicts multiple computing device-level technologies will replace a single dominant architecture, possibly including tunnel field-effect transistors, carbon nanotubes, and superconductors. Quantum computing, brain-inspired computing, and other new approaches also are possible.

Leland says Sandia's challenge is to determine what the next technology will be and to prepare for its implications and necessary architecture. The next technology must be broadly adopted to encourage continual advances, as the transistor did following its invention in 1947. He says industry needs to support the new technology and assemble it into a system that can be deployed for national security.

Sandia aims to identify computer designs that leverage new device technologies and to demonstrate technological feasibility to reduce risk for industry.

From Sandia National Laboratories
View Full Article

 

Abstracts Copyright © 2014 Information Inc., Bethesda, Maryland, USA


 

No entries found

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