Researchers from Princeton University and the Indian Institute of Technology have harnessed artificial intelligence to cut the time and cost of designing new wireless microchips, in the process discovering new functionalities to meet expanding demands for better wireless speed and performance.
Specialised microchips that manage signals at the cutting edge of wireless technology are astounding works of miniaturisation and engineering, but they’re also difficult and expensive to design. The researchers’ methodology uses an AI to create complicated electromagnetic structures and associated circuits in microchips based on a set of design parameters, accomplishing in hours tasks that used to take weeks for highly skilled workers to complete.
Advertisement
What’s more, the AI behind the new system has produced strange new designs that feature unusual patterns of circuitry. According to Kaushik Sengupta, a professor of electrical and computer engineering and co-director of NextG, Princeton’s industry partnership programme to develop next-generation communications, the designs were unintuitive and unlikely to be developed by a human mind; however, they frequently offered marked improvements over even the best standard chips.
‘We are coming up with structures that are complex and look random-shaped, and when connected with circuits, they create previously unachievable performance. Humans cannot really understand them, but they can work better,’ said Sengupta.
Advertisement
The circuits can be engineered toward more energy-efficient operation or to make them operable across an enormous frequency range that isn’t currently possible. Furthermore, the method synthesises inherently complex structures in minutes, while conventional algorithms may take weeks. In some cases, the new methodology can create structures that are impossible to synthesise with current techniques.
Uday Khankhoje, an associate professor of electrical engineering at IIT Madras, said the new technique not only delivers efficiency but promises to unlock new approaches to design challenges that have been beyond the capability of engineers.
Advertisement
‘This work presents a compelling vision of the future,’ he said. ‘AI powers not just the acceleration of time-consuming electromagnetic simulations, but also enables exploration into a hitherto unexplored design space and delivers stunning, high-performance devices that run counter to the usual rules of thumb and human intuition.’
Wireless chips are a combination of standard electronic circuits like those in computer chips and electromagnetic structures such as antennas, resonators, signal splitters and combiners. These combinations of elements are put together in every circuit block, carefully handcrafted and co-designed to operate optimally. This method is then scaled to other circuits, subsystems and systems, making the design process extremely complex and time consuming, particularly for modern, high-performance chips behind applications such as wireless communication, autonomous driving, radar and gesture recognition.
‘Classical designs carefully put these circuits and electromagnetic elements together, piece by piece, so that the signal flows in the way we want it to flow in the chip. By changing those structures, we incorporate new properties,’ Sengupta said. ‘Before, we had a finite way of doing this, but now the options are much larger.’
Advertisement
It can be difficult to comprehend the vastness of a wireless chip’s design space. The circuitry in an advanced chip is so small, and the geometry so detailed, that the number of possible configurations for a chip exceeds the number of atoms in the universe, Sengupta said. There’s no way for a person to understand that level of complexity, so human designers don’t try. They build chips from the bottom up, adding components as needed and adjusting the design as they build.
The AI approaches the challenge from a different perspective, Sengupta said. It views the chip as a single artifact. This can lead to strange but effective arrangements. He said humans play a critical role in the AI system, in part because that AI can make faulty arrangements as well as efficient ones. It’s possible for AI to ‘hallucinate’ elements that don’t work, at least for now. Thus the process requires some level of human oversight.
Advertisement
‘There are pitfalls that still require human designers to correct,’ Sengupta said. ‘The point is not to replace human designers with tools. The point is to enhance productivity with new tools. The human mind is best utilised to create or invent new things, and the more mundane, utilitarian work can be offloaded to these tools.’
The researchers have used AI to discover and design complex electromagnetic structures that are co-designed with circuits to create broadband amplifiers. Sengupta said future research will involve linking multiple structures and designing entire wireless chips with the AI system.
‘Now that this has shown promise, there is a larger effort to think about more complicated systems and designs,’ he said. ‘This is just the tip of the iceberg in terms of what the future holds for the field.’
The research has been published in Nature Communications.