Optimizing on-chip mesh connectivity with Arteris’ FlexNoC 5 physically aware network-on-chip enables Rain AI to realize faster data transfers at ultra-low power to achieve record performance for Generative AI and Edge AI computing at scale
Arteris, a leading provider of system IP which accelerates system-on-chip (SoC) creation, announced that Rain AI, an AI company building the world’s most cost and energy efficient hardware for AI, has selected Arteris’ FlexNoC 5 physically aware network-on-chip (NoC) IP. The company will utilize the Arteris interconnect IP for its AI accelerator family. The on-chip connectivity enabled by Arteris’ IP supports the design of an advanced mesh network topology for superior performance that helps support Rain AI’s digital in-memory compute for AI workloads.
Recommended:Â CIO Influence Interview with Rosaria Silipo, VP of Data Science Evangelism at KNIME
The core of Rain AI’s endeavor lies in co-designing fundamental innovations across software, hardware, and algorithms to both speed up processing and lower power consumption. The mesh network-on-chip topology design for on-chip connectivity is a cutting-edge approach to solve the technical challenge of maintaining high performance while interconnecting various AI processing elements. Arteris’ FlexNoC 5, connecting a mesh topology for high-density AI computing, will enable Rain AI to achieve optimal performance at a lower cost of operation.
“The AI problem is an energy problem. Creating a future with abundant and scalable artificial intelligence is critical for the AI revolution,” said William Passo, CEO of Rain AI. “The right NoC is critical for AI computing and Arteris FlexNoC 5 was an easy choice given its unmatched product performance including ultra-low power, lowest latency, and highest bandwidth, along with deep expert support and proven track record in reducing time to market.”
Recommended:Â CIO Influence Interview with Sumeet Arora, Chief Development Officer at ThoughtSpot
Rain AI is on a mission to build the compute platform for the future of AI, including training and inference on the same platform to enable scale on-device AI. Utilizing the versatility of the RISC-V instruction set architecture (ISA) and the proven high-performance NoC IP from Arteris, Rain AI expects to deliver products that outperform GPUs and are radically more cost-effective.
“We are very excited to support Rain AI in their vision to transform AI compute through their novel approach to machine learning,” stated K. Charles Janac, president and CEO of Arteris. “FlexNoC 5’s ability to deliver high performance, flexibility and scalability was a great fit for Rain AI’s approach to redefining compute for Generative AI and on-device AI applications.”
Arteris remains steadfast in its commitment to delivering state-of-the-art system IP products, empowering innovators like Rain AI to achieve groundbreaking advancements in semiconductor technology.
Recommended:Â CIO Influence Interview with Philip George, Executive Technical Strategist at Merlin Cyber
[To share your insights with us as part of editorial or sponsored content, please write to sghosh@martechseries.com]
