We’re excited to bring Transform 2022 back in person on July 19 and virtually July 20 – August 3. Join AI and data leaders for insightful conversations and exciting networking opportunities. Learn more about Transform 2022
Cognifiber, a company building stand-alone photonic artificial intelligence (AI) accelerators for IoT analytics, has set its sights on a new goal: replacing traditional silicon with glass. By miniaturizing its in-fiber photonics, the startup claims it can bring server-grade capabilities to the edge.
The startup focuses on photonic computing, which goes a step further than most current commercial applications that only use photonics for communication over racks in the data center. Cognifiber has now announced a “first of its kind” glass-based photonic chip made specifically for edge computing.
The company claims it has been able to shrink its previous designs to “a fraction” of the size. The “rack-size” system has been reduced to a 4U server with a height of 18 cm, making it usable in offices, also leading to lower costs.
Photonic glass chips as a solution
The goal of edge computing is to increase compute capabilities at the edge, eliminating the need for IoT devices to rely on the cloud without impacting their performance, while also reducing response time (also known as latency) for real-time operation. † As some examples of where Cognifiber thinks its solution could be deployed, it cites smart meters and home assistants, connected vehicles, automated trains and drone fleet management.
“Combining photonic glass chips advances our edge solution to bring fast AI and Machine Learning locally to edge devices, which are limited in their capacity and power,” said Ze’ev Zalevsky, Cognifiber co-founder and CTO.
The company claims that the in-fiber processing can improve performance 100 times and reduce AI/ML training costs by 80%. Cognifiber’s technology is based on exploiting the crosstalk – which should traditionally be avoided – between fibers. This allows for programmable and reconfigurable interactions, similar to field programmable gate arrays (FPGAs). Both linear and non-linear operations are supported, making the technology suitable for AI.
The Israeli startup, which was previously part of Intel’s Ingenuity Partner Program, announced $6 million in Series A last month. It has shown a “successful” proof-of-concept during its launch phase and aims to have a full-scale launch by the end of 2023. system to market.
The mission of VentureBeat is a digital city square for technical decision makers to gain knowledge about transformative business technology and transactions. Learn more about membership.