Intel has announced the development of a cutting-edge neuromorphic system with 1.15 billion neurons, using its Loihi 2 processors to push the boundaries of AI technology. Dubbed Hala Point, this research prototype is currently deployed at Sandia National Laboratories and is designed to support brain-inspired AI analysis. The system can perform an astounding 20 quadrillion operations per second with unparalleled efficiency.
At its core, Hala Point consists of 140,544 neuromorphic processing cores and 2,300 x86 processors for auxiliary calculations. It also features an impressive array of high memory, inter-core, and inter-chip communication bandwidth, which allows it to handle even the most complex tasks with ease.
Intel believes that Hala Point’s capabilities will pave the way for breakthroughs in real-time continuous learning for AI applications in fields such as scientific problem-solving, logistics, smart city management, language models, and AI agents. Compared to its predecessor, the system demonstrates significant improvements in performance and efficiency for real-time processing tasks like video and voice.
Researchers at Sandia National Laboratories will utilize Hala Point to tackle a wide range of scientific computing problems across various disciplines. Intel plans to share the system with research collaborators as part of a new family of large-scale neuromorphic research systems that will help shape the future of AI technology.
/cdn.vox-cdn.com/uploads/chorus_asset/file/24776336/236715_Best_gaming_mouse_AKrales_0123.jpg)
