[News] Chinese Scientists Developed a Novel Chip, Crossing a Century-Old Hurdle

According to the Institute for Artificial Intelligence at Peking University, a research team led by Researcher Sun Zhong and his collaborators has recently published a paper in the international journal Nature Electronics, reporting a major breakthrough in novel computing architectures.

The team successfully developed a high-precision and scalable analog matrix computing chip based on resistive random-access memory (RRAM). For the first time, the chip achieves analog computation accuracy rival to that of digital systems, improving the precision of traditional analog computing by an astonishing five orders of magnitude.

Performance evaluations show that when solving large-scale MIMO signal detection and other key scientific problems, the chip’s computational throughput and energy efficiency are hundreds to thousands of times higher than those of today’s top-tier digital processors (GPU).

This achievement marks a significant milestone in China’s effort to overcome the century-old challenge of analog computing and represents a major breakthrough in the paradigm shift of computing in the post-Moore era. It blazes a new trail to address the growing computational demands in fields like artificial intelligence and 6G communications.

Sun noted that the research holds broad application potential to empower multiple computing scenarios, which may reshape the future computing landscape.

In next-generation 6G communication systems, the chip could enable base stations to process massive antenna signals in real time with ultra-low power consumption, thereby enhancing network capacity and energy efficiency. For the rapidly evolving field of AI, the technology is expected to accelerate second-order optimization algorithms in large-scale model training, significantly improving training efficiency. “More importantly,” Sun added, “its low-power characteristics will enable complex signal processing and integrated AI training–inference to run directly on end devices, greatly reducing dependence on the cloud and pushing edge computing into a new stage of development.”

(Photo credit: FREEPIK)