Intel has unveiled a neuromorphic system, Hala Point, with 1.15 billion neurons and 128 billion synapses, which utilizes its Loihi 2 processors to advance AI technology. The system, deployed at Sandia National Laboratories, is designed to support brain-inspired AI analysis and can perform 20 quadrillion operations per second with greater efficiency.
Hala Point consists of 140,544 neuromorphic processing cores and 2,300 x86 processors for auxiliary calculations. It offers high memory, inter-core, and inter-chip communication bandwidth. This cutting-edge technology can enable real-time continuous learning for various applications like scientific problem-solving, logistics management, smart city management, language models, and AI agents.
Intel believes that the capabilities of Hala Point will lead to significant advancements in these fields. Compared to its predecessor, the system shows improved performance and efficiency for real-time processing tasks like video and voice. Sandia National Laboratories researchers will use the system to solve complex scientific computing problems in various domains. Intel plans to share the system with research collaborators as part of a new family of large-scale neuromorphic research systems.
In conclusion, Intel’s development of Hala Point represents a major step forward in advancing AI technology through brain-inspired analysis. With its advanced features and capabilities, this cutting-edge system can pave the way for breakthroughs in numerous fields that require real-time continuous learning.
