Researchers at Peking University have made a major breakthrough in analog computing. A team led by Associate Researcher Sun Zhong from the university’s Artificial Intelligence Research Institute, in collaboration with the School of Integrated Circuits, has developed a high-precision, scalable analog matrix-computing chip based on resistive memory technology.

The chip represents the first analog computing system capable of achieving precision comparable to that of conventional digital computation. According to the research team, the new system delivers 100 to 1,000 times higher throughput and energy efficiency than current top-tier digital processors, such as GPUs, when tackling critical scientific problems including large-scale MIMO signal detection.

The findings were published on October 13 in the journal Nature Electronics.