University spin-out secures funding to improve AI energy efficiency and bandwidth

CamGraPhIC, co-founded Professor Andrea Ferrari, Director of the Cambridge Graphene Centre, is developing new types of circuits for energy-efficient, high-bandwidth, optical interconnect technology. The investment will support continued innovation in graphene photonics transceivers, a technology that could improve energy efficiency, reduce latency, and increase bandwidth for artificial intelligence (AI) and cellular data transmission. With the investment, CamGraPhIC will enhance its research and development capabilities and establish a pilot manufacturing line. The facility will demonstrate a scalable mass production process compatible with commercial semiconductor and photonics foundries. The funding round was co-led by CDP Venture Capital, NATO Innovation Fund, Sony Innovation Fund, and Join Capital, with participation from Bosch Ventures, Frontier IP Group plc, and Indaco Ventures. CamGraPhIC’s graphene-based transceivers provide a viable, stable, and scalable alternative to current silicon-based photonics. These transceivers deliver higher bandwidth density, and exceptional latency performance, while consuming 80% less energy than traditional pluggable data centre optical transceivers. The company say their innovation is particularly effective for transferring large volumes of data between graphic processing units (GPUs) and high bandwidth memory (HBM), which are fundamental to generative AI and high-performance computing. The transceivers operate efficiently across a broad temperature range, eliminating the need for complex and costly cooling systems. Thanks to a simplified device architecture enabled by the integration of graphene into the photonic structure, these transceivers are also more cost-effective to manufacture. Thanks to this funding, CamGraPhIC will expand to applications in avionics, automotive advanced driver-assistance systems (ADAS), and space, where rugged, high-performance transceivers offer significant technical and commercial advantages over existing technologies. “We are thrilled for this new phase in the journey towards commercialisation of CamGraPhIC groundbreaking and energy efficient devices, to speed up development of AI hardware, without impacting global emissions,” said Ferrari. “Having Sony, Bosch and NATO as shareholders and board members will help focus the work towards the most relevant applications, including defence and security.” “With the backing of renowned investors, we are excited to propel towards commercialisation the Graphene Photonics technology to overcome the interconnection bottleneck of regenerative AI processing systems and driving the next leap in scaling bandwidth and reducing energy consumption for the future of optical data communications, ” said co-founder Marco Romagnoli, Head of Research Sector - Advanced Technologies for Photonic Integration of the Pisa National Inter-University Consortium for Telecommunications (CNIT). A University of Cambridge spin-out company working to improve AI efficiency and bandwidth has raised €25 million in new funding. Andriy Onufriyenko via Getty ImagesAbstract circular data tunnel
The text in this work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Images, including our videos, are Copyright ©University of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms. Yes

Read on the original site