Technology: By 2026, consumption of data centers, artificial intelligence (AI) and cryptocurrencies will double from 2022 levels

Technology : It is estimated that energy consumption by those three sectors in 2026 could be almost equal to Japan’s annual energy needs.Companies such as Nvidia – whose computer chips form the basis of most AI applications today – are working on developing more energy-efficient hardware.But could an alternative path be to build computers with a fundamentally different type of architecture, one that is more energy efficient? Some firms certainly think so, and are relying on the structure and function of an organ that can perform more operations faster.

Traditional Computers Uses a fraction of the power of a traditional computer: the brain. In neuromorphic computing, electronic devices mimic neurons and synapses, and are interconnected in a way that resembles the brain’s electrical networks. It’s not new — researchers have been working on this technology since the 1980s. But the energy requirements of the AI ​​revolution have increased the pressure to bring the nascent technology into the real world. Current systems and platforms exist mainly as research tools, but supporters say they could offer huge gains in energy efficiency, Those with commercial ambitions include hardware giants such as Intel and IBM.

Some smaller companies are also in this area. “This opportunity is waiting for the company that can figure it out,” says Dan Hutcheson, an analyst at TechInsights.[और] The opportunity is such that it could topple Nvidia.” In May, SpineCloud Systems, a spinout of the Dresden University of Technology, announced it would start selling the first neuromorphic supercomputer, and is taking pre-orders. “We want to start selling neuromorphic supercomputers before other companies,” says its co-chief executive, Hector Gonzalez.

Commercialization have reached commercialisation.” This is an important development, says Tony Kenyon, professor of nanoelectronics and nanophotonic materials at University College London, who works in this field. “While there is still no killer app… there are many areas where neuromorphic computing will provide significant benefits in energy efficiency and performance, and I’m sure we’ll start to see widespread adoption of this technology as it matures,” he says.

Neuromorphic computing encompasses a variety of approaches – from simply a more brain-inspired approach, to a nearly perfect simulation of the human brain (which we’re really nowhere near). But there are some basic design properties that set it apart from traditional computing. First, unlike traditional computers, neuromorphic computers don’t have separate memory and processing units. Instead, those tasks are performed together in the same location on a chip. Professor Kenyon notes that removing the need to transfer data between the two reduces the energy used and speeds up processing times. Event-driven approaches to computing may also become common.

Unlike traditional computing, where every part of the system is always on and available to communicate with any other part at all times, neuromorphic computing can have low activation. The mimicked neurons and synapses only activate when they have something to communicate with, just as many neurons and synapses in our brains only activate when there is a reason to. Operating only when there is something to process also saves power. And while modern computers are digital – using 1s or 0s to represent data – a neuromorphic computing can be analog. Historically significant, that method of computing relies on continuous signals and can be useful where data coming in from the outside world needs to be analyzed. However, for reasons of ease, most commercially oriented neuromorphic efforts are digital.

Stay connected with Janta Se Rishta for news updates