Chip startups that use light instead of wires gain speed and investment - New Style Motorsport

April 26 (Reuters) – Computers that use light instead of electrical currents for processing, seen only a few years ago as research projects, are gaining traction and startups that have solved the engineering challenge of using photons in chips are receiving a lot of funding.

In the latest example, Ayar Labs, a startup developing this technology called silicon photonics, said on Tuesday that it had raised $130 million from investors including chip giant Nvidia Corp (NVDA.O).

While the transistor-based silicon chip has increased computing power exponentially in recent decades, as transistors have grown to be several atoms wide, shrinking them further is a challenge. Not only is it difficult to make something this miniscule, but as they get smaller, signals can bleed into each other.

Sign up now for FREE unlimited access to

So Moore’s Law, which said that every two years the density of transistors on a chip would double and drive down costs, is slowing down, pushing the industry to look for new solutions to handle AI computing needs. getting heavier.

According to the data firm PitchBook, last year silicon photonics startups raised more than $750 million, twice as much as in 2020. In 2016, that was about $18 million.

“AI is growing like crazy and taking over much of the data center,” Ayar Labs chief executive Charles Wuischpard told Reuters in an interview. “The challenge of data movement and the power consumption in that data movement is a big deal.”

The challenge is that many large machine learning algorithms can use hundreds or thousands of chips for computation, and there is a bottleneck in the speed of data transmission between chips or servers using current electrical methods.

Light has been used to transmit data over fiber optic cables, including submarine cables, for decades, but bringing it down to the chip level was difficult, as the devices used to create or control light have not been as easy to shrink. like transistors.

PitchBook Senior Emerging Technology Analyst Brendan Burke expects silicon photonics to become common hardware in data centers by 2025 and estimates the market will reach $3 billion by then, similar to the size of the market for AI graphics chips in 2020.

Beyond connecting transistor chips, startups using silicon photonics to build quantum computers, supercomputers and chips for autonomous vehicles are also raising big money.

PsiQuantum has raised around $665 million so far, though the promise that quantum computers will change the world is still some way off.

Lightmatter, which builds processors that use light to speed up AI workloads in the data center, has raised a total of $113 million and will launch its chips later this year and test with customers soon after.

Luminous Computing, a Bill Gates-backed startup building an AI supercomputer using silicon photonics, raised a total of $115 million.

It is not just startups that are driving this technology. Semiconductor manufacturers are also preparing to use their silicon chip manufacturing technology for photonics.

Amir Faintuch, director of computing and wired infrastructure at GlobalFoundries, said the collaboration with PsiQuantum, Ayar and Lightmatter has helped build a silicon photonics fabrication platform for others to use. The platform was launched in March.

Peter Barrett, founder of venture capital firm Playground Global, an investor in Ayar Labs and PsiQuantum, believes in the long-term prospects for silicon photonics to speed up computing, but says there is still a long way to go.

“What the guys at Ayar Labs do so well … is that they solved the problem of data interconnection for traditional high-performance (computing),” he said. “But it will be a while before we have pure digital photonic computing for non-quantum systems.”

Sign up now for FREE unlimited access to

Reporting by Jane Lanhee Lee; Edited by Stephen Coates

Our standards: the Thomson Reuters Trust Principles.

Leave a Reply

Your email address will not be published. Required fields are marked *