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

Institutions

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

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Parallel optical computing capable of 100-wavelength multiplexing

Shulan Yi, Guangwei Hu, Yingbo Chu, Ziqi Wei et al.
19 citations
eLight
Neural Networks and Reservoir Computing
47.14
article

Parallel optical computing capable of 100-wavelength multiplexing

Shulan Yi, Guangwei Hu, Yingbo Chu, Ziqi Wei, Yuhu Cheng, Xinyu Wang, Hongwei Wang, Zhen Wang, Peng Xie, Xiaohong Han, Sha Fu, Xiaojiang Yu
article en
19 citations

Abstract

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.

eLightVol. 5(1)
Nanyang Technological University (SG), Peking University (CN), Shanghai Institute of Optics and Fine Mechanics (CN), University of Chinese Academy of Sciences (CN)
Shanghai Institute of Optics and Fine Mechanics, Chinese Academy of Sciences
Openalex Percentile: Top 0%
Neural Networks and Reservoir Computing
47.14
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.