Intel says it has built the world’s largest neuromorphic computing system called Hala Point, that has the neuron capacity roughly equivalent to that of an owl brain. The system, deployed at Sandia National Laboratories, uses the Loihi 2 processor to support research into brain-inspired artificial intelligence.
Hala Point builds on Intel’s first-generation large-scale research system, Pohoiki Springs. The system can support up to 20 quadrillion operations per second (20 petaops) with an efficiency exceeding 15 trillion operations per second per watt (TOPS/W) when running conventional deep neural networks, according to Intel.
Researchers at Sandia National Laboratories will use Hala Point to conduct advanced brain-scale computing research, focusing on scientific computing problems in device physics, computer architecture, computer science, and informatics.
Hala Point packages 1,152 Loihi 2 processors in a six-rack-unit data center chassis, supporting up to 1.15 billion neurons and 128 billion synapses distributed over 140,544 neuromorphic processing cores, consuming a maximum of 2,600 watts of power.
Hala Point is currently a research prototype that will inform future commercial systems, says Intel.
[Image courtesy: Intel]