New ferroelectric memory breakthroughs improve energy efficiency and storage density, offering promising pathways for ...

The human brain is the ultimate supercomputer. It uses a highly branched and interconnected network of neurons and synapses ...

As artificial intelligence (AI) proliferates rapidly, AI models and datasets are also growing rapidly in size. This growth far outpaces performance improvement in hardware systems, and is increasing ...

A new approach to neuromorphic computing proposes using acoustic waves — rather than electrical ...

Bull, a leader in advanced computing and AI, today announced that its systems continue to lead the Green500 ranking of the world's most energy-efficient supercomputers, occupying the top three ...

The growth and impact of artificial intelligence are limited by the power and energy that it takes to train machine learning models. So how are researchers working to improve computing efficiency to ...

AI data centers are power-hungry. Not only do artificial intelligence computations consume enormous amounts of electricity, but a significant amount of energy is also required to cool the ...

The growth of energy efficiency in traditional computer chips is slowing due to physical limitations, coinciding with a rapid increase in energy demands from the tech sector, especially artificial ...

Researchers have managed to generate propagating spin waves at the nanoscale and discovered a novel pathway to modulate and amplify them. Their discovery could pave the way for the development of ...

Transformer-based large language models (LLMs) have demonstrated state-of-the-art capabilities across a spectrum of tasks 1,2,3,4, and their remarkable generative capacity has led to a transformative ...

The US Department of Energy (DOE) is funding research at the University of Arkansas exploring more efficient computing. Charles Paillard, research professor of physics and director of the Smart ...

“Brain-like energy-efficient computing has remained elusive for neuromorphic (NM) circuits and hardware platform implementations despite decades of research. In this work we reveal the opportunity to ...