‘Virtually unhackable’ chip could make GPU more power efficient and much faster at AI – by combining light and silicon for a fundamental mathematical operation

A groundbreaking new chip developed by Penn Engineers uses light waves instead of electricity for AI computations, marking a possibly significant leap in processing speeds and energy efficiency.

The chip, based on silicon-photonics (SiPh), blends esteemed Penn Professor Nader Engheta’s research on manipulating materials at the nanoscale to perform mathematical computations using light, with the SiPh platform that uses silicon, a cheap and abundant element in computer chips.

This revolutionary approach to chip design could potentially outpace the limitations of today’s chips, which SciTechDaily points out, still operate on principles from the dawn of the computing revolution in the 1960s.

Mathematical calculations at the speed of light

The chip was developed in collaboration with Firooz Aflatouni, Associate Professor in Electrical and Systems Engineering, whose research group has been at the forefront of nanoscale silicon devices. The team aimed to create a platform for vector-matrix multiplication, a fundamental mathematical operation in neural networks, which are the backbone of modern AI tools.

The chip’s design involves varying the height of the silicon wafer in specific regions, allowing light to scatter in specific patterns, and enabling the chip to perform mathematical calculations at the speed of light.

The design is reportedly ready for commercial applications, and could potentially be adapted for use in GPUs, which have seen a surge in demand due to the growing interest in AI system development.

In addition to improved speed and reduced energy consumption, the chip also offers privacy advantages. As many computations can occur simultaneously, there is no need to store sensitive information in a computer’s working memory, making a future computer powered by such technology virtually unhackable.

The new chip’s design was detailed in a paper published in Nature Photonics.

More from TechRadar Pro