Intel builds world's largest neuromorphic system to support research for future brain-inspired AI


Devdiscourse News Desk | California | Updated: 18-04-2024 16:33 IST | Created: 18-04-2024 16:33 IST
Intel builds world's largest neuromorphic system to support research for future brain-inspired AI
Representative Image.

Intel has announced the development of Hala Point - the world's largest and Intel's most advanced neuromorphic system to date. The new system aims to support research for future brain-inspired AI and tackles challenges related to the efficiency and sustainability of today's AI

Initially deployed at Sandia National Laboratories, Hala Point utilizes Intel's Loihi 2 processor to achieve over 10 times more neuron capacity and up to 12 times higher performance.

According to the chipmaker, Hala Point can support up to 20 quadrillion operations per second, or 20 petaops, with an efficiency exceeding 15 trillion 8-bit operations per second per watt (TOPS/W) when executing conventional deep neural networks.

Its unique capabilities make it ideal for tasks requiring real-time, continuous learning across diverse applications, from scientific and engineering problem-solving to logistics and smart city infrastructure management to large language models (LLMs) and AI agents.

Using Hala Point, researchers at Sandia National Laboratories will focus on solving scientific computing problems in device physics, computer architecture, computer science and informatics.

"Working with Hala Point improves our Sandia team’s capability to solve computational and scientific modeling problems. Conducting research with a system of this size will allow us to keep pace with AI's evolution in fields ranging from commercial to defense to basic science," said Craig Vineyard, Hala Point team lead at Sandia National Laboratories.

Hala Point, which is currently a research prototype, is expected to advance the capabilities of future commercial systems, with Intel anticipating it to drive numerous advancements in AI functionalities, particularly in how large language models (LLMs) operate and learn.

"Together with an ecosystem of more than 200 Intel Neuromorphic Research Community (INRC) members, including leading academic groups, government labs, research institutions and companies worldwide, Intel is working to push the boundaries of brain-inspired AI and progressing this technology from research prototypes to industry-leading commercial products over the coming years," the chipmaker said in a statement on Wednesday.

Give Feedback