Researchers from the University of Oxford’s Department of Physics have made a discovery that could pave the way for the next big breakthrough in AI.
The team has successfully created “hurricane-like” magnetic vortices in hematite, the main component of rust, that could potentially power energy-efficient, brain-like processors running at hundreds of gigahertz.
These magnetic vortices, which can travel at astonishing speeds of up to kilometers per second, are being touted as potential information carriers for the next generation of green and super-fast computing platforms.
100-1000 times faster
The study, published in Nature Materials, overcame the challenge of producing these vortices in materials previously incompatible with silicon, a major hurdle in its practical application.
The research was led by Dr. Hariom Jani from the University of Oxford, in collaboration with the National University of Singapore and Swiss Light Source. Dr. Jani believes that silicon-based computing, with its high energy inefficiency, is not suitable for next-generation computing applications such as full AI and autonomous devices.
The solution, he suggests, lies in harnessing magnetic vortices in a special class of materials called antiferromagnets, which work 100 to 1,000 times faster than modern devices.
“Today, silicon transistors use charges to perform calculations, which can disappear as soon as the power supply is turned off. Therefore, they tend to be very power-hungry and inefficient. In addition, conventional computers keep data storage separate from data processing. Information between them is time and energy intensive, creating a performance bottleneck,” Dr. Jani us.
“On the other hand, hurricane-like vortices in antiferromagnetic materials are ‘shielded’ nanoscale spin structures that are intrinsically stable due to their unique winding. They can remain stable even without electrical impulses. Moreover, they also harbor rich and ultra-fast dynamics that can be exploited to perform unconventional information processing, combining memory and logic functions. In the future, such platforms could be used to perform brain-like computing to create efficient and fast AI hardware. “
The team achieved their breakthrough by fabricating ultra-thin crystalline membranes from hematite on a crystal template covered with a special ‘sacrificial layer’. The layer dissolved in water, separating the hematite from the crystal base, which was then transferred to silicon and several other platforms.
The researchers also developed a new imaging technique using linearly polarized X-rays to visualize the nanoscale magnetic patterns within these membranes. The technique revealed that the free-standing layers can house a robust family of magnetic vortices, opening the door to ultra-fast information processing.
The team is now developing prototype devices to harness the dynamics of these super-fast vortices. Dr. Jani concluded: “Ultimately, such devices could be integrated into new types of computers that more closely resemble the human brain – we are very excited about what will happen.”