Alternative methods of radically increasing the performance of CPUs, such as spintronics, won't find their way into production for at least another 10 years, Intel said this week in Taiwan.
Until now, computer processors have operated by using the binary on/off characteristic of electrons. However, the angular momentum of the electrons can be used, as well as the direction of that momentum, with the potential to increase the performance and capacity of chips.
However, over the next decade or so the focus will remain on incremental and more mundane improvements to get smaller and more efficient chips, according to Intel senior fellow and director communications technology lab, Kevin Kahn, who was speaking at the Intel Developer Forum in Taipei yesterday.
This is because the changes are better understood and relatively quantifiable as well as cheaper and more effective to deploy, Kahn said.
"We will push existing technology architectures as long and hard as we can because we know how to do them," he said, adding that a step-change such as using spin required a large amount of planning to be able to work with existing products: "No matter how hard you push on the new ones, it'll be a while."
The comments followed a futuristic keynote, in which Kahn detailed what humans could do to make computers smarter, perhaps heading towards a Terminator-like reality where computers outperformed their human counterparts.
He spoke about possible improvements in materials going into chips, as well as spintronics. He then moved onto sensors and actuators, displaying a robot which used an electronic field to sense when objects were near. The pre-touch had a shorter range than vision, but a longer range than touch, Kahn said.
The robot was able to take a dragon fruit without crushing it and hand it to Kahn. "You begin to believe that robot's alive," he said of the way it tracked his hand. "It's a very loose kind of following. It's like it's sniffing your hand out."
An actuation method he showed used sound. Sound, and not a fan, was generating the force that pushed a blue slip of paper upwards.
Another demonstration was a method of transferring power wirelessly using resonance frequencies — as demonstrated in the photo [below] showing a lamp being lit. The power transfer was 75 percent efficient, Kahn said, although the prototype shown could not operate over more than a metre or so.
If receivers were built into mobile devices, and transmitters in specific spaces, whenever receivers were in range, they could automatically charge the devices, Kahn said.
The most unusual thing Kahn described was programmable matter, or small units that moved relative to one another to form objects, changing the form of devices or helping with computer simulations so operators can simply push or pull a design to make changes.
Current research in the area was using magnets or electrostatic forces, Kahn said, adding that, for him the idea was "in the space of magic".