Cognifiber announced the development of a glass-based photonic chip that will bring its technology one step closer to revolutionizing edge computing. Being the first of its kind, this glass-based chip reduces power consumption and takes a fraction of the size of previous designs in CogniFiber's solutions.

Edge devices, including smart meters, smart home assistants, connected vehicles, and other IoT devices, rely primarily on cloud computing to rapidly recognize patterns and act in a seamless manner. Today, due to the edge devices' size and power limitations, they require a constant uplink with data centers, which face their own problems surrounding capacity and power consumption. Existing edge solutions may include low-power chips; however, these may limit speed, model size, and accuracy. To address this problem, Cognifiber is developing glass-based photonic chips that reduce its data center rack-size systems to a mere 4U server (~18cm high), making it deployable in any office.

"The downsizing potential using glass-based photonic chips in conjunction with our proprietary fibers promises to bring superb-performance servers to the edge, removing many existing bottlenecks while dramatically reducing power consumption," said Dr. Eyal Cohen, Co-founder & CEO of Cognifiber. "Anything that generates vast amounts of data every second, such as connected vehicles, automated trains, or fleet management of large shipment drones can respond in real-time to events without reliance on data centers."

Cognifiber has already set the stage for reimagining Moore's Law. Replacing legacy silicon-based semiconductors, they are already in the advanced stages of developing in-fiber processing that minimizes the reliance on chips altogether by conducting complex computations within specialty optical fiber. "The future of computing demands a whole new way of transferring and processing vast amounts of data," said Professor Ze'ev Zalevsky, Co-founder & CTO of Cognifiber. "Combining photonic glass chips promotes our edge solution to bring rapid AI and Machine Learning locally to edge devices, which are limited in their capacity and power allowance."

Even with in-fiber processing, which can deliver a 100-fold boost in computing capabilities, there is still a reliance on semiconductors to conduct various operations of control and training. Future glass photonic chips, beyond downsizing, may provide a replacement for today's silicon ones, while reducing manufacturing costs, power consumption, and the removal of bandwidth bottlenecks.

This giant leap for the photonics industry creates the foundation for future capabilities while companies rely on edge devices to make increasingly complex autonomous decisions. "Devices will react faster and more reliably with our expected edge computing capacity," said Cohen.