Today, supercomputers are used fora wide range of tasks: from various mathematical calculations and processing of data arrays to the modeling of pharmaceutical compounds and the work of artificial intelligence. However, there are computers aimed at the most accurate reproduction of the "architecture" of the human brain. And the most powerful such neuromorphic supercomputer today was recently launched for the first time.
This computer is called Spiking Neural Network.Architecture (SpiNNaker) and it can perform more than 200 million operations per second, and each of the microcircuits has 100 million parts. The machine was assembled on the basis of the School of Computer Science of the University of Manchester and 15 million pounds were spent on this project. But this amount is not as impressive as the time taken to develop: the concept of a supercomputer was worked out for 20 years and another 10 years were required for assembly.
SpiNNaker Supercomputer Chip
SpiNNaker can simulate in real timethe behavior of human neurons and it is unique in that, unlike traditional computers, it does not transfer large amounts of information from point A to point B, but sends data at a time to thousands of different directions. This is exactly how the cells of our brain work. As one of the ideologists of the project, professor of computer technology Steve Furber, said
“SpiNNaker completely changes the way ordinarycomputers. In fact, we created a machine that works more like a brain than a traditional computer, which is extremely interesting. The ultimate goal of our project has always been the use of a billion cores in one computer that would simulate the brain and today we have achieved this goal. And it's just fantastic. ”
It’s worth noting that even in spite ofSince the “real artificial brain” has earned, the number of nuclei that is now in it simulates the brain, which is equivalent to 1% of the human. However, now this neuromorphic supercomputer will help to understand how our central nervous system functions, and will also make it possible to carry out large-scale simulations that are not available on traditional machines.
You can discuss this and other news in our chat in Telegram.