Chaos theory offers solution to Moore’s law

1 min read

Researchers at North Carolina (NC) State University have developed nonlinear, chaos-based chips that could perform multiple functions with fewer transistors. These ICs could be manufactured with ‘off the shelf’ processes and could lead to novel computer architectures that do more with less circuitry and fewer transistors.

“We’re reaching the limits of physics in terms of transistor size, so we need a new way to enhance the performance of microprocessors,” said Behnam Kia, senior research scholar in physics at NC State. “We propose using chaos theory – the system’s own nonlinearity – to enable circuits to be programmed to perform different digital computations. A nonlinear transistor circuit contains different patterns that represent different functions, and they are selectable. We use these dynamics-level behaviours to perform different processing tasks using the same circuit.”

Traditionally, transistor-based circuits perform one task each. Computer processors operate by routing each instruction and its operands to the appropriate transistor circuit on the IC that implements that specific instruction. In the group’s design, the transistor circuit can be programmed to implement different instructions by morphing between different operations and functions.

“In current processors you don’t use all the circuitry on the processor all the time, which is wasteful,” Kia explained. “Our design allows the circuit to be rapidly morphed and reconfigured to perform a desired digital function in each clock cycle. The heart of the design is an analogue nonlinear circuit, but the interface is fully digital, enabling the circuit to operate as a fully morphable digital circuit that can be connected to the other digital systems.”

According to Kia, 100 morphable nonlinear chaos-based circuits could do the work equivalent to 100,000 circuits, or of 100million transistors doing work equivalent to 3billion transistors.

“We are nearing commercial size and power and ease of programming in our evolving designs that could well be of significant commercial relevance within a few months,” said William Ditto, professor of physics at NC state.