Computers that use light instead of electrical currents for processing are gaining traction and startups solving the engineering challenge of using photons in chips are getting huge funding.
Computers that use light instead of electric currents for processing, which were seen only as research projects years ago, are gaining traction and big funding to startups solving the engineering challenge of using photons in chips are getting.
In the latest example, Ayar Labs, the startup developing this technology called Silicon Photonics, on Tuesday said it has raised $130 million from investors including chip giant Nvidia Corp.
While transistor-based silicon chips have rapidly increased computing power over the past decades as transistors have reached the width of several atoms, reducing them further is challenging. Not only is it difficult to make something so small, but as they get smaller, signals can bleed between them.
Therefore, Moore’s law, which states that the transistor density on a chip will double every two years and reduce costs, is slowing, prompting the industry to find new solutions to handle the increasingly enormous artificial intelligence computing needs. Inspire to explore.
Silicon photonics startups raised more than $750 million last year, more than double that of 2020, according to data firm PitchBook. In 2016 it was about $18 million.
“AI is growing like crazy and taking over large chunks of data centers,” Ayer Labs CEO Charles Wooshpard told Reuters in an interview. “The data movement challenge and the energy consumption in that data movement is a big, big issue.”
The challenge is that many large machine-learning algorithms may use hundreds or thousands of chips for computing, and there is a bottleneck on the speed of data transmission between chips or servers using current electrical methods.
For decades, lighting has been used to transmit data via fiber-optic cables, including undersea cables, but it was difficult to bring it to the chip level because the components used to make or control the light The device was not as easy to shrink as the transistor.
Pitchbook Senior Emerging Technology Analyst Brendan Burke expects silicon photonics to become common hardware in data centers by 2025 and estimates that the market will reach $3 billion by then, similar to the market size of the AI graphic chips market in 2020.
In addition to adding transistor chips, startups using silicon photonics to build quantum computers, chips for supercomputers and self-driving vehicles are also raising big funds.
PsiQuantum has raised about $665 million so far, although the promise of quantum computers to change the world is still years old.
LightMatter, which makes processors using Light to accelerate AI workloads in datacenters, raised a total of $113 million and will release its chips later this year and test with customers soon.
Luminous Computing, a startup building AI supercomputers using silicon photonics backed by Bill Gates, raised a total of $115 million.
photonic casting
Not only startups are pushing this technology. Semiconductor makers are also gearing up to use their silicon chip-making technology for photonics.
GlobalFoundries Head of Computing and Wired Infrastructure Amir Fentuch said collaborations with PsiQuantum, Ayar, and Lightmatter have helped build a silicon photonics fabrication platform for others to use. This platform was launched in March.
Peter Barrett, founder of venture capital firm Playground Global, Ayer Labs and an investor in PsyQuantum, believes in the long-term potential for silicon photonics to accelerate computing, but says it’s a long road ahead.
“What the guys at Ayer Labs do so well… is they solve the data interconnect problem for traditional high-performance (computing),” he said. “But it’s going to be some time before we have pure digital photonic calculations for non-quantum systems.”
0 notes
(This story has not been edited by NDTV staff and is auto-generated from a syndicated feed.)
for the latest auto news And AnalysisFollow carandbike.com Twitter, Facebookand subscribe to us youtube Channel.