As chip manufacturers cram increasing numbers of transistor switches in small areas to make faster, cheaper chips, heat dissipation has become a growing concern.
The Pentium II processor, introduced in 1997, was said to generate more heat than a hot plate, and Intel in 1999 predicted that the amount of heat generated by computer chips would increase linearly as chip sizes decrease.
Should the trend continue, future electronic devices could generate more heat than nuclear reactors and be ‘as hot as the Sun’ within two decades, researchers say.
“Laptops are very hot now, so hot that they are not 'lap' tops anymore,” said Avik Ghosh, who is researching new heat dissipation methods at the University of Virginia's School of Engineering and Applied Science.
“It [heat] is probably the most critical impediment to continued miniaturisation of transistors, which carry out logic operations in computers,” he told iTnews.
Ghosh and his colleague Mircea Stan are investigating a concept known as ‘non-equilibrium Brownian ratchets’ which could revolutionise how heat is dissipated between computer components.
Currently, devices are engineered to operate near thermal equilibrium, in accordance with the Second Law of Thermodynamics which states that heat tends to transfer from a hotter unit to a cooler one.
However, using the concept of Brownian ratchets, which are systems that convert non-equilibrium energy to do useful work, the researchers hope to allow computers to operate at low power levels, and harness power dissipated by other functions.
“The main quest we have is to see if by departing from near-equilibrium operation, we can perform computation more efficiently,” Ghosh told iTnews.
“We aren't breaking the Second Law -- that's not what we are claiming,” he said. “We are simply re-examining its implications, as much of the established understanding of power dissipation is based on near-equilibrium operation.”
But while the physics of non-equilibrium Brownian ratchets has been studied extensively for some time, the concept’s application in a technology context has not.
Ghosh expects to face challenges ranging from proof-of-concept demonstration, to going beyond models to experimental testing, and analysing the practicality, robustness and cost-effectiveness of these schemes.
“Until we do a proper study, we can't be sure whether this method would suffice
to address the considerable challenges of heat generation and removal,” he said.
“Our short-term plan is to study this over the next three to five years at this time to see where we end up with non-equilibrium switching, and whether it could offer a solution.”
Non-equilibrium chips could avoid overheating laptops
By Liz Tay on Oct 2, 2008 1:52PM