World’s largest neuromorphic supercomputer, fitted with a million processor core and built to work in the same way as the human brain works, has been switched on for the first time.
The supercomputer, Spiking Neural Network Architecture (SpiNNaker) machine, has 100 million transistors on its each chip and can do more than 200 million actions per second.
It is designed and built in the University of Manchester, United Kingdom and can, in real-time, model more biological neurons than any other machine in the world.
The machine, initial build of which started in 2006, took £15 million in funding, 20 years in conception and more than 10 years in construction in order to reach this point.
SpiNNaker, unlike traditional machines, does not communicate by sending large amounts of information from one point to another via standard network. Instead, it works like the massively parallel communication architecture of the brain.
It sends small amounts of information simultaneously to thousands of different destinations.
The aim of the researchers on the project is to model up to a billion biological neurons in real-time.
SpiNNaker will help neuroscientists to better understand the functioning of the brain and can be used in robotics to interpret real-time visual information and navigation of certain objects while ignoring others.