Cognifiber Downsizes its System for Edge Computing With Breakthrough Glass Processors
March 31, 2022 | CognifiberEstimated reading time: 2 minutes
The limitations of edge computing put a strain on connected devices to store, transfer, and manage data. “The miniaturization capabilities of glass-based photonic chips will bring server-size products to the edge,” said Dr. Eyal Cohen, Co-founder & CEO of Cognifiber.
Cognifiber, a deep technology company focusing on revolutionizing photonic computing, 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.
Testimonial
"The I-Connect007 team is outstanding—kind, responsive, and a true marketing partner. Their design team created fresh, eye-catching ads, and their editorial support polished our content to let our brand shine. Thank you all! "
Sweeney Ng - CEE PCBSuggested Items
Macronix Introduces Cutting-Edge Secure-Boot NOR Flash Memory
08/08/2025 | PRNewswireMacronix International Co., Ltd., a leading integrated device manufacturer in the non-volatile memory (NVM) market, announced ArmorBoot MX76, a robust NOR flash memory combining in a single device, the essential performance and an array of security features that deliver rapid boot times and iron-clad data protection.
Inside the AI Hardware Boom: Servers, Substrates and Advanced Packaging
08/07/2025 | Edy Yu, Printed Circuit Information, China, and Marcy LaRont, I-Connect007AI is rewriting the hardware playbook, marrying complex software and algorithms to run and improve machine and equipment operations. Sorting through, managing, and utilizing massive amounts of data takes tremendous data storage and processing power. Enter the new generation of supercomputers and data servers. The data servers being built today are not your momma’s server, as they say.
AI Is the Golden Track Reviving Electronics and PCBs
08/06/2025 | Edy Yu, Chief Editor, ECIO, and the I-Connect007 Editorial TeamRemember 2021? Despite COVID, the electronics industry hit a high. Then came the slide. By 2023, the industry was deep in the red. With inflation, policy shifts, and exchange rate shocks, the problems were long, and the outlook was bleak. Recovery finally appeared in 2024, but it was fragile. Automotive electronics slumped, wireless demand stayed soft, and the ride up was anything but smooth. Yet, amid the uncertainty, one bright track emerged: artificial intelligence (AI).
Brent Laufenberg Appointed CIO of the Global Electronics Association, Advancing Technology and Member Services
07/31/2025 | Global Electronics AssociationThe Global Electronics Association (formerly IPC International Inc.) announces the appointment of Brent Laufenberg as its new Chief Information Officer (CIO).
SES AI Accelerates Timeline for Revenue Growth and Profitability with Acquisition of UZ Energy
07/31/2025 | BUSINESS WIRESES AI Corporation, a global leader in the development and manufacturing of AI-enhanced high-performance Li-Metal and Li-ion batteries, today announced it has executed a definitive agreement to acquire 100% of UZ Energy, an energy storage systems (“ESS”) provider, for a purchase price of approximately $25.5 million, subject to earnout adjustment based on the achievement of specified financial targets.