Chinese scientists have developed a high-precision, scalable analog matrix computing chip based on resistive memory, creating for the first time an analog computing system whose accuracy rivals that of digital computing, according to Science and Technology Daily.

The breakthrough was led by researcher Sun Zhong from the Institute for Artificial Intelligence at Peking University in collaboration with the School of Integrated Circuits. The chip achieves computing throughput and energy efficiency 100 to 1,000 times higher than current top digital processors (GPUs) for key scientific tasks such as large-scale MIMO signal detection. The findings were published on October 13 in Nature Electronics.

Achieving both high precision and scalability in analog computing has long been a century-old challenge for the global scientific community, as it is essential for fully leveraging analog computing’s advantages in modern computational tasks. Sun’s team used an integrated innovation approach, combining novel devices, original circuits, and classical algorithms to build a high-precision, scalable analog matrix solver based on resistive memory arrays. For the first time, they achieved 24-bit fixed-point accuracy in analog computing.