Integrated Neuromorphic Photonic Computing for AI Acceleration: Emerging Devices, Network Architectures, and Future Paradigms
Advanced Materials · 2026-09 · 38 (50)
DOI: 10.1002/adma.202508029 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Advanced Materials, online erschienen am 21.10.2025. Verfasst von Gaofei Wang und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Integrated Circuits & Micro-Nano Electronics, Fudan University, 220 Handan Road, Shanghai, 200433, P. R. China. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 209 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Key Research and Development Program of China, Fundamental Research Funds for the Central Universities, National Natural Science Foundation of China.
Abstract (Originalsprache)
Deep learning stands as a cornerstone of modern artificial intelligence (AI), revolutionizing fields from computer vision to large language models (LLMs). However, as electronic hardware approaches fundamental physical limits—constrained by transistor scaling challenges, von Neuman architecture, and thermal dissipation—critical bottlenecks emerge in computational density and energy efficiency. To bridge the gap between algorithmic ambition and hardware limitations, photonic neuromorphic computing emerges as a transformative candidate, exploiting light's inherent parallelism, sub‐nanosecond latency, and near‐zero thermal losses to natively execute matrix operations—the computational backbone of neural networks. Photonic neural networks (PNNs) have achieved influential milestones in AI acceleration, demonstrating single‐chip integration of both inference and in situ training—a leap forward with profound implications for next‐generation computing. This review synthesizes a decade of progress in PNNs core components, critically analyzing advances in linear synaptic devices, nonlinear neuron devices, and network architectures, summarizing their respective strengths and persistent challenges. Furthermore, application‐specific requirements are systematically analyzed for PNN deployment across computational regimes: cloud‐scale and edge/client‐side AIs. Finally, actionable pathways are outlined for overcoming material‐ and system‐level barriers, emphasizing topology‐optimized active/passive devices and advanced packaging strategies. These multidisciplinary advances position PNNs as a paradigm‐shifting platform for post‐Moore AI hardware.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Integrated Circuits & Micro-Nano Electronics, Fudan University, 220 Handan Road, Shanghai, 200433, P. R. China.
- State Key Laboratory of Integrated Chips and Systems, Fudan University, 220 Handan Road, Shanghai, 200433, P. R. China.
- Shaoxin Laboratory, Shaoxing, 312000, P. R. China.
- Institute of Optoelectronics, Fudan University, 220 Handan Road, Shanghai, 200433, P. R. China.
ORCID-Profile: Peng Zhou
Förderung
- National Key Research and Development Program of China
- Fundamental Research Funds for the Central Universities
- National Natural Science Foundation of China
- New Cornerstone Science Foundation through the XPLORER PRIZE
- Start-up funding from Fudan University.
Zitieren
APA
Wang, G., Che, J., Gao, C., Han, Z., Shen, J., Cheng, Z., & Zhou, P. (2026). Integrated Neuromorphic Photonic Computing for AI Acceleration: Emerging Devices, Network Architectures, and Future Paradigms. Advanced Materials, 38(50). https://doi.org/10.1002/adma.202508029
Vancouver
Wang G, Che J, Gao C, Han Z, Shen J, Cheng Z, et al. Integrated Neuromorphic Photonic Computing for AI Acceleration: Emerging Devices, Network Architectures, and Future Paradigms. Advanced Materials. 2026;38(50). doi:10.1002/adma.202508029
BibTeX
@article{Wang2026,
author = {Wang, Gaofei and Che, Junyan and Gao, Chen and Han, Zhou and Shen, Jiabin and Cheng, Zengguang and Zhou, Peng},
title = {Integrated Neuromorphic Photonic Computing for AI Acceleration: Emerging Devices, Network Architectures, and Future Paradigms},
journal = {Advanced Materials},
year = {2026},
volume = {38},
number = {50},
doi = {10.1002/adma.202508029}
}
EUVIMED