Intel builds world's largest neuromorphic system

Called Hala Point, this large-scale neuromorphic system was originally built at Sandia National Laboratories in New Mexico. It simulates the human brain in its information processing. With architectural improvements that increase the capacity of neurons by more than 10 times and increase peak performance by 12 times, Hala Point is an improvement over Intel's first-generation large research system, Pohoiki Springs. Researchers at Sandia National Laboratories plan to use Hala Point for advanced brain-scale computing research, focusing on solving scientific computing problems in device physics, computer architecture, computer science, and computer science.

According to Mike Davies, director of the Neuromorphic Computing Lab at Intel Labs, the computational costs of today’s AI models are increasing at an unsustainable rate. The industry needs fundamentally new approaches that can scale. So Intel developed Hala Point, which combines deep learning performance with brain-inspired learning and optimization. Intel experts hope that research with Hala Point will help improve the efficiency and adaptability of large-scale AI technology.