Skip to main content
Dryad

Hypermultiplexed integrated-photonics-based optical tensor processor

Chen, Zaijun1; Ou, Shaoyun1; Xue, Kaiwen1; Zhou, Lian1; Lee, Chunho1; Sludds, Alexander2; Hamerley, Ryan2; Zhang, Ke3; Feng, Hanke3; Kopparapu, Reshma1; Zhong, Eric1; Yu, Yue1; Wang, Cheng3; Englund, Dirk2; Yu, Mengjie1

Published Jun 03, 2025 on Dryad. https://doi.org/10.5061/dryad.kprr4xhgj

Data files

Jun 03, 2025 version files 29.40 GB

Click names to download individual files Select up to 11 GB of files for zip download

Abstract

The escalating data volume and complexity resulting from the rapid expansion of artificial intelligence (AI), internet of things (IoT), and 5G/6G mobile networks is creating an urgent need for energy-efficient, scalable computing hardware. Here we demonstrate a hypermultiplexed integrated photonics-based tensor optical processor (HITOP) that can perform trillions of operations per second (TOPS) at the energy efficiency of 40 TOPS/W. Space-time-wavelength three-dimensional (3D) optical parallelism enables O(N2) operations per clock-cycle using O(N) modulator devices. The system is built with wafer-fabricated III/V micron-scale lasers and high-speed thin-film Lithium-Niobate electro-optics for encoding at 10s femtojoule/symbol. Lasing threshold incorporates an analog inline rectifier (ReLu) nonlinearity for low-latency activation. The system scalability is verified with machine learning models of 405,000 parameters. A combination of high clockrates, energy-efficient processing, and programmability unlocks the potential of light for large-scale AI accelerators in applications ranging from training of large AI models to real-time decision making in edge deployment.