Hardware news

Hardware

Atom-thin material could overcome key transistor bottleneck for next-generation computer chips

If computer chips could be built from semiconductors just one atom thick, they could pack far more transistors into a smaller space while using less power. So far, however, the technology has been held back by the weakness ...

Hardware

New magnetic computing system could tackle complex optimization problems

When designing new computer chips, engineers need to make various decisions about how to connect their underlying components while efficiently using limited space. Planning these connections involves combinatorial optimization, ...

Hardware

Broadband distributed amplifier for data centers, measurement systems and sensors

Modern data centers, high-precision measurement systems and high-resolution radar sensors rely on extremely broadband amplifier chips that combine low noise with high output power. Researchers at the Fraunhofer Institute ...

Hardware

Toward physical AI: When the hardware becomes the neural network

Digital computing using silicon chips has transformed nearly every aspect of modern life and enabled the remarkable growth of artificial intelligence. But as AI models scale up, that growth comes with increasing demands for ...

Hardware

New analog memory may make smart devices even smarter

A new approach to computing has quietly taken shape at Sandia National Laboratories, where researchers have developed a way to store information that could make future electronics more energy efficient.

Hardware

A novel chip-on-wafer platform for next-generation AI hardware

A new semiconductor integration platform developed at the Institute of Science Tokyo combines advanced chip packaging with high-density interconnects and improved thermal management. This combination of three complementary ...

Hardware

Genesis chip may help AI with its memory problem

One of artificial intelligence's most stubborn problems is enabling AI systems to accumulate new knowledge without losing what they previously learned. A team of researchers at the MATRIX AI Consortium at The University of ...