ALBUQUERQUE, N.M. — In a significant development in the field of computing, Sandia National Laboratories recently received a groundbreaking brain-based computing system named Hala Point, containing a record-breaking 1.15 billion artificial neurons. The system, described as the largest brain-based computing system in the world, was transported from Intel Corp. in Portland, Oregon, to Albuquerque, New Mexico, where it will support research teams at Sandia and the National Nuclear Security Administration.
Lead researcher at Sandia, Craig Vineyard, expressed optimism about the potential of the new computing system, stating, "We believe this new level of experimentation — the start, we hope, of large-scale neuromorphic computing — will help create a brain-based system with unrivaled ability to process, respond to, and learn from real-life data."
Mike Davies, director of the Neuromorphic Computing Lab at Intel Labs, emphasized the collaborative efforts between Intel and Sandia, saying, "Our colleagues at Sandia have consistently applied our Loihi hardware in ways we never imagined, and we look forward to their research with Hala Point leading to breakthroughs in the scale, speed, and efficiency of many impactful computing problems."
The new computing system, which is ten times faster and 15 times denser than its predecessor, is equipped with 1,152 Loihi 2 research processors and represents a significant advancement in brain-based computing technology. Vineyard highlighted the need for developing efficient algorithms to utilize the system effectively, particularly in areas such as large-scale physics, chemistry, and environmental modeling.
Brad Aimone, a researcher at Sandia, explained the fundamental difference between brain-like computing and traditional computers, stating, "The computation is spread over many neurons in parallel, rather than long processes in series that are an inescapable part of conventional computing." Aimone emphasized the potential for innovation at scale with the billion-neuron system, envisioning the creation of more efficient AI algorithms and brain-like approaches to existing computer algorithms.
As Sandia prepares to explore the capabilities of Hala Point, funded by NNSA’s Advanced Simulation and Computing program, the future of large-scale neuromorphic computing holds promise for advancing various fields, from scientific research to societal applications.