According to Science and Technology Daily, Tsinghua University has made significant breakthroughs in research in the field of chips. According to reports, the research group led by Associate Professor Fang Lu from the Department of Electronic Engineering at Tsinghua University and Academician Dai Qionghai from the Department of Automation have abandoned traditional electronic deep computing paradigms and taken a new approach to address the challenges of large-scale optoelectronic intelligent computing. They have pioneered a distributed breadth optical computing architecture and developed a large-scale interference diffraction heterogeneous integrated chip, Taichi, to achieve universal intelligent computing of 160 TOPS/W.

Intelligent optical computing, as an emerging computing mode, has shown far greater performance and potential than silicon-based electronic computing in the post Moore's era. However, its computational tasks are limited to simple character classification, basic image processing, and so on. The pain point is that the computing advantages of light are trapped in unsuitable electrical architectures, with limited computing scale and inability to support complex large-scale intelligent computing that urgently requires high computing power and energy efficiency.

It is reported that the computing energy efficiency of Tai Chi light chips exceeds that of existing intelligent chips by 2-3 orders of magnitude, and will provide computing power support for intelligent analysis of light speed in large scenes with billions of pixels, training and inference of large models with billions of parameters, and milliwatt level low-power autonomous intelligent unmanned systems.

In the era of booming development of large-scale general artificial intelligence, this scientific research achievement explores new inspiration, architecture, and paths for high-performance computing power through the path of photons.