Parallel optical computing capable of 100-wavelength multiplexing
Abstract In the era of artificial intelligence, the computing hardware is of critical importance, with various new modalities explored. Information processing using photons, with abundant intrinsic degrees of freedom, as the carrier could embrace low loss, high speed, low latency, low power consumption, and high parallelism. Here, harvesting the intrinsic frequency channels, we propose and demonstrate a parallel optical computing architecture powered by a soliton microcomb source, a broadband Mach–Zehnder interferometer (MZI) mesh and a parallel MZI mesh computing model. The examinations validate the system's capability to perform over 100-frequency channel multiplexed parallel optical information processing. Both spectral consistency and matrix consistency exceed 0.9. This achievement enables a 100-fold increase (and even beyond) in optical computility through ultra-high parallelism without scaling up the chip size, offering a novel technological pathway for future optical computers.
Authors
- Shulan Yi (ORCID: https://orcid.org/0009-0009-1015-1826)
- Guangwei Hu (ORCID: https://orcid.org/0000-0002-3023-9632)
- Yingbo Chu (ORCID: https://orcid.org/0000-0003-4767-7652)
- Ziqi Wei (ORCID: https://orcid.org/0000-0001-9402-8386)
- Yuhu Cheng (ORCID: https://orcid.org/0000-0003-2022-9999)
- Xinyu Wang (ORCID: https://orcid.org/0000-0001-8477-1774)
- Hongwei Wang (ORCID: https://orcid.org/0000-0002-8503-719X)
- Zhen Wang (ORCID: https://orcid.org/0000-0003-4134-1779)
- Peng Xie (ORCID: https://orcid.org/0000-0002-3636-3001)
- Xiaohong Han
- Sha Fu (ORCID: https://orcid.org/0000-0001-8720-9162)
- Xiaojiang Yu (ORCID: https://orcid.org/0000-0002-7044-6417)
Institutions
- Nanyang Technological University (SG)
- Peking University (CN)
- Shanghai Institute of Optics and Fine Mechanics (CN)
- University of Chinese Academy of Sciences (CN)
Publication Details
- Journal
- eLight
- Published
- 2025-06-16
- DOI
- https://doi.org/10.1186/s43593-025-00088-8
- Citations
- 19
- Primary Topic
- Neural Networks and Reservoir Computing
- Type
- article
- Field-Weighted Citation Impact
- 47.14
Funders
- Shanghai Institute of Optics and Fine Mechanics, Chinese Academy of Sciences