Israeli tech firm NeuReality has successfully moved its new AI-centric NR1 chip into the final, validated design phase, marking a pivotal moment in the semiconductor industry.The newly developed chip has the capacity to significantly transform how AI is used in various fields, including tasks like understanding human language, processing visual information, recognizing speech, and suggesting content or products to users.As the demand for AI as a service continues to surge, and resource-intensive applications like ChatGPT become increasingly prevalent, NeuReality’s innovation comes at a critical juncture.
Its NR1 chip, dubbed the world’s first AI-centric server-on-a-chip, promises to provide affordable access to modernized AI inference infrastructure, addressing a pressing need in the industry.Historically, AI inference — the part of AI that makes decisions based on data — has relied heavily on software and was quite expensive. According to NeuReality’s CEO, Moshe Tanach, NR1 is a solution to the limitations of traditional CPU-based AI systems. By shifting the focus from software to hardware, the NR1 chip allows deep learning accelerators (DLAs) to work more efficiently, speeding up AI tasks.“Function for function, hardware runs faster and parallelizes much more than software. As an industry, we’ve proven this model, offloading the deep learning processing function from CPUs to DLAs,” Tanach said.
The critical X-factor in NeuReality’s NR1 chip is its impressive performance-to-cost ratio. Compared to conventional CPU-centric systems, the NR1 chip showcased a 10-fold improvement in performance at equivalent costs during trials.
The innovative abilities of the NR1 chip
Each NR1 chip is a versatile device with different computing abilities, including the ability to work with various DLAs. It also includes advanced features like an embedded Network Interface controller and an AI-hypervisor to manage tasks efficiently.“NR1 offers an unprecedented competitive alternative to today’s general-purpose server solutions, setting a new standard for the direction our industry must take to fully support the AI Digital Age,” said Tanach.