By Elton Gomes
The world’s largest neuromorphic supercomputer has been fitted with its landmark one-millionth processor core and is being switched on for the first time. What’s impressive about this supercomputer is that it was designed and built to work in the same way a human brain does.
The newly formed million-processor-core named ‘Spiking Neural Network Architecture’ or ‘SpiNNaker’ machine can complete more than 200 million actions per second. Each of the machine’s chips have 100 million transistors.
Neuromorphic computing involves the use of computers to mimic the human brain. The method is a rapidly growing area in computer science research that focuses on developing system architectures and specialized computer chips that replicate the way the human brain processes information.
Neuromorphic computing allows neuroscientists to create unprecedented models of the brain. Additionally, it also helps roboticists in creating robots that can navigate complex environments using computer vision.
The SpiNNaker machine has been developed at a cost of 15 million euros in funding. It took a total of 20 years in conception and over 10 years in construction, and the initial build starting in 2006, according to a statement.
What is a supercomputer?
A supercomputer is a computer that performs at or near the currently highest operational rate for computers. In the traditional sense, supercomputers have been used for scientific and engineering applications that have to handle gargantuan databases or do a great amount of computation (or both).
Who owns the fastest supercomputer?
The US beat the Chinese in this race. For five years, China owned the world’s fastest computer, which was a symbolic achievement for a country trying to assert its dominance in the tech field. But the United States took the lead again.
In June 2018, US scientists unveiled the world’s most powerful and smartest scientific supercomputer machine named Summit. The supercomputer can complete over 200,000 trillion calculations per second. It was revealed at the US Department of Energy’s Oak Ridge National Laboratory. Summit was known to be eight times more powerful than its previous top-ranked system, Titan.
China is still home to the most number of supercomputers over all. China, Japan, and Europe are engaged in developing much faster machines, which could indicate that the US’ lead could be cut short.
What do we know about SpiNNaker?
The SpiNNaker machine was designed and built in The University of Manchester in the UK. The machine can model more biological neurons in real time than any other machine across planet Earth.
Biological neurons are basic brain cells that are resent in the nervous system. The cells communicate mainly by emitting ‘spikes’ of pure electro-chemical energy. With the help of large scale computer systems, neuromorphic computing emulates these spikes in a machine.
What makes the SpiNNaker unique is the way it sends information. Unlike traditional computers, the SpiNNaker does not communicate by sending large amounts of information from one point to another. It instead mimics the massively parallel communication architecture of the brain, and sends billions of small amounts of information simultaneously to several thousand destinations.
The SpiNNaker’s core comprises a special computer chip that consists of 18 tightly-packed processor cores. More than 55,000 of these chips were linked together to power the supercomputer with a million processor cores.
“SpiNNaker completely re-thinks the way conventional computers work,” Steve Furber, a computer scientist at the University of Manchester, said in a statement. “We’ve essentially created a machine that works more like a brain than a traditional computer, which is extremely exciting.”
How will it help scientists?
One of the fundamental uses for the SpiNNaker is to assist neuroscientists in better understanding of how our own brain works. It does this by running extremely large scale real-time simulations – such simulations are simply not possible on other machines.
SpiNNaker has been used to simulate high-level real-time processing in a range of isolated brain networks. This includes an 80,000-neuron model of a segment of the cortex – the outer layer of the brain that receives and processes information from the senses.
“Neuroscientists can now use SpiNNaker to help unlock some of the secrets of how the human brain works by running unprecedentedly large scale simulations,” Furber said, Vice reported.
The SpiNNaker supercomputer machine has also simulated a region of the brain called the Basal Ganglia, which is an area affected when a person is suffering from Parkinson’s disease. This indicates that the supercomputer has massive potential for neurological breakthroughs in several fields of science, such as pharmaceutical testing.
Elton Gomes is a staff writer at Qrius
Stay updated with all the insights.
Navigate news, 1 email day.
Subscribe to Qrius