IBM has unveiled a “brain-like” chip with the potential to transform the energy consumption patterns of artificial intelligence systems. This development promises to redefine how energy is consumed in the AI sector.
IBM’s Energy-Efficient Vision
The current demands of AI operations on power and resources have been a growing concern. With large warehouses filled with computers, the carbon footprint is escalating.
IBM’s prototype chip seeks to address this.
Scientist Thanos Vasilopoulos from IBM’s Zurich lab highlighted the chip’s efficiency, stating, “the human brain is able to achieve remarkable performance while consuming little power.” This is what IBM aims to replicate with their prototype.
Reducing Carbon Emissions
Emissions from large warehouses filled with AI computers have sparked concerns. Vasilopoulos suggests this new chip means “large and more complex workloads could be executed in low power or battery-constrained environments”, such as cars and mobile phones.
He added, “cloud providers will be able to use these chips to reduce energy costs and their carbon footprint.”
Digital to Analogue: The Shift
Current standard chips operate on a digital foundation, storing information in binary – 0s and 1s. This new prototype from IBM, however, leans on memristors, which operate in an analogue manner, accommodating a spectrum of numbers.
This shift in technology could be likened to the transition from a basic light switch to a more intricate dimmer switch, as detailed by Professor Ferrante Neri from the University of Surrey.
He emphasised the chip’s ability to “remember” its electric history, much like synapses in human brains. Such capabilities push this technology closer to emulating human brain functions.
More from News
- Trump Lifts Sanctions in Syria: What Does This Mean For Syrian Businesses?
- Retail Cyber Attacks: Cartier And North Face Are The Next Retailers Affected
- A Look At The Different Technologies Volvo Is Bringing To Its Cars
- Klarna Launches Debit Card To Diversify Away From BNPL
- T-Mobile Now Has Fibre Internet Plans Available For Homes
- Bitdefender Finds 84% of Attacks Use Built In Windows Tools, Here’s How
- Japan Starts Clinical Trials For Artificial Blood Which Is Compatible With All Blood Types
- UK Unicorn Monzo Breaks £1 Billion in Revenue
Navigating the Roadblocks and CHallenges
Though the chip presents a very inviting glimpse into a more energy-efficient future, Neri spoke on the challenges like material costs and complexities in manufacturing.
His feeling was one of guarded hopefulness: positive about the technology’s potential but very much aware of possible challenges.
Blending with Existing Systems
The way new technologies are first integrated is often a concern. However, IBM’s chip is constructed with adaptability in mind.
Considering that many of today’s smartphones use AI chips, highlighted by features such as the iPhone’s “neural engine”, IBM’s new technology might lead to extended battery durations and fresh applications for these devices.
A Shift for Data Centres?
If this prototype does become mainstream, it might just alter the face of data centres around the world. The considerable energy and water demands of contemporary data centres could see a substantial decrease.
While the potential is clear, experts like Professor James Davenport from the University of Bath have their reservations.
He recognises the chip’s potential but reminds us that it’s merely “a possible first step” in a much longer journey.
Regardless, IBM’s newest contribution could be a huge step towards a more sustainable technological future.
