NetSpeed unveils Orion AI – Delivering extreme performance and ultimate efficiency for next-gen AI SoCs

NetSpeed Systems today announced the release of Orion AI, the industry’s first SoC interconnect solution targeted specifically for AI-enable SoC applications. It includes advanced features such as multicast and broadcast to improve performance and efficiency in AI-enable SoCs and accelerator ASICs used for datacenters, autonomous vehicles, AR/VR, and advanced video analytics. Orion AI builds on NetSpeed’s silicon-proven Orion IP which has been licensed to pioneering AI companies including Horizon Robotics, Cambricon, Baidu and Esperanto.

Artificial Intelligence (AI) is making its way into many applications including vision, speech, forecasting, robotics and diagnostics. These emerging applications require a whole new level of processing capability and are driving sweeping changes in computational architectures and a dramatic shift in SOC design.

“Inside these new SOCs there is a new data flow,” said Sundari Mitra, CEO of NetSpeed. “Typically, there are a large number of compute elements which need to perform peer to peer data exchange rapidly and efficiently. Previous architectures operated differently, with processing units using a central memory as an interchange system. AI systems need ‘any-to-any’ data exchanges that benefit from wide interfaces and need to support long bursts. One of the key advantages that Orion AI brings is the ability to support many multicast requests and to support non-blocking transfers.”

Orion AI was designed to provide extreme performance—terabits of on-chip bandwidth—and has an underlying architecture that can support thousands of compute engines. It provides super-wide data paths with interfaces of up to 1024 bits, higher for internal structures, and can support long bursts of up to 4K Bytes.

Orion AI is powered by NetSpeed’s Turing machine learning engine which uses supervised learning to explore and optimize SoC design and architecture. This is an AI-inside approach that Linley Gwennap, principal analyst at the Linley Group described, “is like having a guru architect on call to provide design advice. Processor architects can take Turing’s advice and then devote their time to solving the other hard problems in their SoC design.”