160 TOPS/W的通用智能计算 算什么水平？能效是H100的1000倍。

据说灵感来自周易

首创分布式广度智能光计算架构，全球首款大规模干涉衍射异构集成芯片

这里有full access

https://zenodo.org/records/10908167

只读文章，这里下载

https://www.science.org/action/downloadSupplement?doi=10.1126%2Fscience.adl1203&file=science.adl1203_sm.pdf

Editor’s summary
Rapid advances in artificial general intelligence (AGI) come with increased performance and energy efficiency requirements for next-generation computing. Photonic computing has the potential to achieve these goals, but despite attracting attention, current photonic integrated circuits, specifically optical neural networks (ONNs), have limited scale and computing capabilities, barely supporting modern AGI tasks. Xu et al. explored a distributed diffractive-interference hybrid photonic computing architecture to effectively increase the scale of the ONN to the million-neuron level. They experimentally realized an on-chip 13.96-million-neuron ONN for complex, thousand-category-level classification and AI-generated content tasks. The present work is a promising step toward real-world photonic computing, supporting various applications in AI. —Yury Suleymanov