Core Insights - Zhejiang University has launched a new generation of neuromorphic brain-like computer named "Wukong," which is the first in the world to exceed 2 billion neurons based on dedicated neuromorphic chips [1][2] - "Wukong" features over 2 billion spiking neurons and more than 100 billion synapses, closely resembling the scale of a macaque brain, with a typical operating power consumption of approximately 2000 watts [1] - The previous largest neuromorphic brain-like computer was Intel's Hala Point system, which had a neuron scale of 1.15 billion [1] Group 1 - "Wukong" is equipped with 960 self-developed Darwin 3rd generation brain-like computing chips, organized into 15 blade-type neuromorphic brain-like servers [1] - Each chip supports over 2.35 million spiking neurons and hundreds of millions of synapses, along with a dedicated instruction set for brain-like computing and an online learning mechanism [1][2] Group 2 - The research team has developed the Darwin brain-like operating system alongside "Wukong," which can run intelligent applications such as DeepSeek brain-like models for logical reasoning, content generation, and mathematical problem-solving [2] - "Wukong" offers a new computational paradigm with its large scale, high parallelism, and low power consumption, providing a computational foundation for artificial intelligence development and serving as a simulation tool for neuroscientists [2]
神经拟态类脑计算机“悟空”问世
Ke Ji Ri Bao·2025-08-03 23:39