Intel Deploys World's Largest Neuromorphic Computer System at Sandia National Laboratories

Intel deploys world's largest neuromorphic computer, Hala Point, at Sandia Labs, enabling more sustainable and efficient AI research and applications with 1.15 billion neurons and 50x faster performance than GPUs.

author-image
Justice Nwafor
Updated On
New Update
Intel Deploys World's Largest Neuromorphic Computer System at Sandia National Laboratories

Intel Deploys World's Largest Neuromorphic Computer System at Sandia National Laboratories

Intel has deployed the world's largest neuromorphic computer system, called Hala Point, at Sandia National Laboratories in Albuquerque, New Mexico. Hala Point integrates Intel's Loihi 2 processor and is designed to support research aimed at advancing more sustainable and efficient AI applications. The system can handle 1.15 billion neurons, offering up to 50 times faster performance and 100 times less energy usage compared to traditional GPUs.

Hala Point is capable of executing up to 20 quadrillion operations per second and exceeds 15 trillion 8-bit operations per second per watt when running conventional deep neural networks. It contains 1,152 Loihi 2 processors that support up to 1.15 billion neurons and 128 billion synapses distributed over 140,544 neuromorphic processing cores. This represents a significant upgrade over Intel's previous neuromorphic system, Pohoiki Springs, with over 10 times more neuron capacity and up to 12 times higher performance.

Why this matters: Hala Point's deployment marks a major milestone in the development of neuromorphic computing, which aims to mimic the human brain's neural plasticity to reduce energy consumption for computational needs. The research conducted with Hala Point is expected to lead to significant advancements in commercial AI systems, particularly in enabling large language models to learn continuously from new data and reducing the unsustainable training burdens associated with widespread AI deployment.

Researchers at Sandia National Laboratories plan to leverage Hala Point for advanced brain-scale computing studies, particularly in tackling complex scientific computing problems. Intel anticipates that the lessons learned from Hala Point will lead to practical advancements, such as the ability for large language models to learn continuously from new data, which could significantly reduce the unsustainable training burden of widespread AI deployment.

Key Takeaways

  • Intel deployed world's largest neuromorphic computer, Hala Point, at Sandia Labs.
  • Hala Point has 1.15 billion neurons, 50x faster and 100x more energy-efficient than GPUs.
  • Hala Point aims to advance sustainable and efficient AI applications, including large language models.
  • Hala Point will enable continuous learning for AI agents, models, and smart city infrastructure.
  • Intel plans to transition brain-inspired AI from research to industry-leading commercial products.