In 1965, Gordon Moore predicted that the number of components in integrated circuits would grow exponentially. Somehow, miraculously, that prediction held true for decades, giving the world progressively more powerful and efficient electronics.
It would be hard to overstate the impact of Moore’s Law. We can see it all around us, in the myriad gadgets, computers, and networks that power modern life. But the winning streak can’t last forever; in fact, the benefits we see from the miniaturization of transistors—a key driver of Moore’s Law—are already on the wane.
To keep making computers better and better, researchers are contemplating new technologies, including circuits modeled on the human brain, carbon nanotube computers, and processors that make do with approximate rather than exact answers. At SXSW 2017, held in March in Austin, Tx., IEEE Spectrum moderated a panel discussion with leaders in this space: Tom Conte of the Georgia Institute of Technology, Tsu-Jae King Liu of the University of California at Berkeley, and Greg Yeric of ARM Research. This short video features parts of the event as well as conversations afterward with the panelists.