Recently, a groundbreaking research paper titled "A sub-10-millisecond neural dynamical system based on phase change memristors" was published in the internationally acclaimed academic journal Science. This work was the collaborative effort of a team led by Professor Yang Yuchao, a New Cornerstone Investigator at Peking University’s School of Integrated Circuits and Advanced Innovation Center for Integrated Circuits, as well as the dean of the School of Information Engineering at the Shenzhen Graduate School. The team also included researchers from the Shanghai Institute of Microsystem and Information Technology at the Chinese Academy of Sciences, led by Researcher Song Zhitang. This achievement signifies a major advancement in the field of novel neural dynamics computing chips.

The team successfully developed the world’s first millisecond-level neural dynamics system chip based on phase change memristors. This breakthrough overcame the longstanding international challenge of achieving "controllable in-memory computing" for phase change memristors. For the first time, the single-step computation latency of the neural dynamics system was reduced to just 2.12 milliseconds. This milestone not only sets a new benchmark for the real-time computing capabilities of neural dynamics systems but also provides innovative hardware support for applications such as brain-computer interfaces, brain digital twins, neural navigation, and intelligent diagnosis and treatment of neurodegenerative diseases.

Experimental data reveal that when performing the same neural dynamics computations, the system achieves speedups ranging from 3.82 to 36.27 times while reducing power consumption by 11.75 to 24.73 times compared to the current state-of-the-art dedicated accelerators. In high-fidelity brain modeling tasks, such as cortical surface reconstruction, the system demonstrates speedups of 50.38 to 478.18 times compared to the NVIDIA A100 GPU.

This research has received support from multiple prestigious sources, including the New Cornerstone Investigator Program, the National Key Research and Development Program, and the National Natural Science Foundation of China.