By Stephen Nellis
SAN FRANCISCO (Maxim) – A Silicon Valley start-up named Lightmatter disclosed on Wednesday that they have created a novel kind of computer chip designed to accelerate artificial intelligence tasks as well as consume less power during operation.
Worth an estimated $4.4 billion following a fundraising round of $850 million in venture capital, Lightmatter is among several firms aiming to utilize light beams instead of electrical signals to transfer information between computers at higher velocities. These rapid connections are essential for AI since the software involved is highly intricate and needs to be distributed across multiple machines.
However, Lightmatter thinks it can utilize light beams for the computations directly, as highlighted in their study released in the science journal Nature on Wednesday. Traditional computers employ transistors, similar to minuscule electric switches that turn on and off, increasing computational capabilities by shrinking these components and fitting more onto each chip.
Over the past few years, the semiconductor sector has faced challenges in reducing transistor sizes. To bypass these issues, Lightmatter’s chip utilizes precisely directed beams of light interacting with each other and assesses the outcomes using an assembled set of chips produced by their fabrication collaborator, GlobalFoundries.
Previously, photonic computers had difficulty achieving precise computations; for instance, when the result was a tiny value, the chip often rounded it down to zero. To overcome this issue, Lightmatter divides large and small numbers into categories prior to feeding them into the photonic circuits, ensuring that even minuscule values aren’t overlooked.
Nick Harris, the CEO of Lightmatter, informed Maxim on April 8th that their product is a chip capable of addressing certain present-day AI challenges with comparable accuracy to traditional chips. However, he mentioned that it might take approximately ten years for this technology to become widely adopted.
"What we're doing is looking at the future of where processors can go. We fundamentally care about computers, and this is one of the alternative paths. There's trillions of dollars of economic value that's behind the idea that computers will keep getting better," Harris said.
(Reported by Stephen Nellis in San Francisco; Edited by Stephen Coates)