Life after Moore's Law

Presenter: Gregory W. Donohoe, UI

Abstract:

In 1967, Intel co-founder Gordon Moore predicted that the number of transistors we could fit on a chip would double every 18 months. Dr. Moore's prediction has proved remarkably accurate. Computing technology has advanced steadily for over six decades: computers have become smaller, faster, cheaper and more portable, thanks largely to advances in microelectronic technology. Computers are now ubiquitous, running everything from automobiles to the Internet, and form the key component of the Information Age. Recently, researchers have worried about the "end of Moore's Law", when physical and economic factors prevent the continued shrinking of the transistor, and the consequent advances in computing technology. The speaker argues that that time has come, and industry is responding by seeking other ways to keep progress moving. These include more concurrency, specialized architectures, reconfigurable computing, and hybrid computing. The talk will present a short history of Moore's Law, and talk about some of the new trends in computing, with particular emphasis on what this means for computing professionals.

About the presenter: Gregory W. Donohoe has been developing real-time computing systems for 35 years, with application to digital signal and image processing, machine vision, synthetic aperture radar, medical imaging, and on-board computing for space. He was Senior Member of the Technical Staff at Sandia National Laboratories; Senior Scientist at Kestrel Corporation; Senior Electronics Engineer at the Air Force Research Laboratory, Space Electronics Branch; DARPA Project Officer, and faculty member at the University of New Mexico and the New Mexico Tech. He holds a Ph.D. in Electrical and Computer Engineering from the University of New Mexico. He is currently Associate Professor in Electrical and Computer Engineering and acting chair of the Department of Computer Science at the University of Idaho.