CEVA’s NeuPro Family of Edge AI Processors Wins “Digital Semiconductor Product of the Year” at Elektra Awards 2018
CEVA, Inc., the leading licensor of signal processing platforms and artificial intelligence processors for smarter, connected devices, announced that its NeuPro family of AI processors for deep learning at the edge has won “Digital Semiconductor Product of the Year” at the Elektra Awards 2018. These prestigious annual awards, hosted by Electronics Weekly and judged by a panel of industry experts, have been celebrating innovation and achievement in the electronics industry since 2003.
“CEVA is extremely proud to be recognized with an Elektra Award for our NeuPro AI processor family, which aims to bring the limitless possibilities of artificial intelligence to every electronics device,” said Ilan Yona, general manager and vice president of the vision business unit at CEVA. “The realization of AI at the edge is dependent on the underlying hardware enabling it, and our NeuPro processors lead the industry in performance, power efficiency and ability to infer any neural network based workload or application.”
The Elektra Awards 2018 judges commented: “The digital semiconductor product of the year was an extremely competitive category with several of the world’s top ten companies shortlisted. CEVA’s NeuPro is an incredible performance neural network processor for AI applications.”
NeuPro™ is a dedicated low power AI processor family for deep learning at the edge. These self-contained, specialized AI processors scale in performance to address a broad range of end markets including IoT, smartphones, surveillance, automotive, robotics, medical and industrial. NeuPro builds on CEVA’s industry-leading position and experience in deep neural networks for computer vision applications, and leverages the award-winning CDNN software compiler technology to streamline the transition of any deep neural network to an embedded environment. This new family of dedicated AI processors offers a considerable step-up in performance, ranging from 2 Tera Ops Per Second (TOPS) for the entry-level processor and 12.5 TOPS for the most advanced configuration.