LightIN: a versatile silicon-integrated photonic field programmable gate array with an intelligent configuration framework for next-generation AI clusters

Ying Zhu; Yifan Liu; Xinyu Yang; Kailai Liu; Xin Hua; Ming Luo; Jia Liu; Siyao Chang; Jie Yan; Shengxiang Zhang; Miao Wu; Zhicheng Wang; Hongguang Zhang; Dong Wang; Daigao Chen; Xi Xiao; Shaohua Yu

doi:10.1038/s41377-026-02209-5

Your Location：

Home >

Browse articles >

LightIN: a versatile silicon-integrated photonic field programmable gate array with an intelligent configuration framework for next-generation AI clusters

Original Articles

- LightIN: a versatile silicon-integrated photonic field programmable gate array with an intelligent configuration framework for next-generation AI clusters
- Light: Science & Applications Vol. 15, Issue 5, Pages: 1736-1750(2026)
- Affiliations：
  
  1.National Information Optoelectronics Innovation Center, China Information and Communication Technologies Group Corporation, Youkeyuan Road 88, Wuhan 430074 Hubei, China
  2.State Key Laboratory of Optical Communication Technologies and Networks, China Information and Communication Technologies Group Corporation, Gaoxinsi Road 6, Wuhan 430074 Hubei, China
  3.Peng Cheng Laboratory, Shahexi Road 6001, Shenzhen 518108 Guangdong, China
- Author bio：
  
  Xi Xiao (xiaoxi@noeic.com)
- Funds：
- DOI：10.1038/s41377-026-02209-5
  CLC：
- Received：22 May 2025，
  
  Revised：2026-01-09，
  
  Accepted：23 January 2026，
  
  Online First：11 March 2026，
  
  Published：31 May 2026
- Accepted：
Scan QR Code
Zhu, Y. et al. LightIN: a versatile silicon-integrated photonic field programmable gate array with an intelligent configuration framework for next-generation AI clusters. Light: Science & Applications, 15, 1736-1750 (2026).
DOI：

Zhu, Y. et al. LightIN: a versatile silicon-integrated photonic field programmable gate array with an intelligent configuration framework for next-generation AI clusters. Light: Science & Applications, 15, 1736-1750 (2026). DOI： 10.1038/s41377-026-02209-5.

摘要

Abstract

Artificial Intelligence models pose serious challenges to intensive computing and high-bandwidth communication for conventional electronic circuit-based computing clusters. Silicon photonic technologies

due to their high speed

low latency

large bandwidth

and complementary metal-oxide-semiconductor compatibility

have been widely implemented for data transmission and actively explored as photonic neural networks in AI clusters. However

current silicon photonic integ

rated chips lack adaptability for multifunctional use and hardware-software systematic coordination

which is adverse to the development of photo-electronic AI clusters. Here

we develop a reconfigurable silicon photonic chip with 40 programmable unit cells integrating over 160 components

which

to the best of our knowledge

is the first to realize diverse functions for AI clusters with a chip

from computing acceleration and signal processing to network switching and secure encryption. Using a self-developed testing

compilation

and adjustment framework to the chip without in-chip monitoring photodetectors

we have demonstrated (1) 4 × 4 bi-direction unitary and 3 × 3 uni-direction non-unitary matrix multiplications

achieving a speed of over 1.92 TOPS with 6.22-bit precision and energy efficiency of 1.875 pJ MAC

−1

and neural networks for image recognition with a latency of 260 ps; (2) micro-ring modulator wavelength locking in the 5 to 32 Gb s

−1

transmission systems; (3) 4 × 4 photonic channel switching with low to –44 dB inter-channel crosstalk; (4) silicon photonic physical unclonable functions. This optoelectronic processing system

incorporating the photonic chip and its software stack

paves the way for both advanced photonic system-on-chip design and the construction of photo-electronic AI clusters.

关键词

Keywords

references

Chang, Y. P. et al. A survey on evaluation of large language models. ACM Trans. Intell. Syst. Technol. 15 , 39 (2024)..

Moor, M. et al. Foundation models for generalist medical artificial intelligence. Nature 616 , 259–265 (2023)..

Zhang, K. P. et al. AI-TP: Attention-based interaction-aware trajectory prediction for autonomous driving. IEEE Trans. Intell. Veh. 8 , 73–83 (2022)..

Zhang, Z. et al. Structured light meets machine intelligence. eLight 5 , 26 (2025)..

Wu, N. et al. Intelligent nanophotonics: When machine learning sheds light. eLight 5 , 5 (2025)..

Pan, S. et al. Facebook’s tectonic filesystem: Efficiency from exascale. Proceedings of the 19th USENIX Conference on File and Storage Technologies . Santa Clara, CA, USA: USENIX, 2021, 217-231.

Zhao, M. et al. Understanding data storage and ingestion for large-scale deep recommendation model training: industrial product. Proceedings of the 49th Annual International Symposium on Computer Architecture . New York, NY, USA: ACM, 2022, 1042–1057.

Yang, Y., Liu, K., Gao, Y., Wang, C. & Cao, L. Advancements and challenges in inverse lithography technology: A review of artificial intelligence-based approaches. Light Sci. Appl. 14 , 250 (2025)..

Morik, K.&Marwedel, P. Machine learning under resource constraints-fundamentals. (Berlin: Walter de Gruyter GmbH&Co KG, 2022).

Gholami, A. et al. Ai and memory wall. IEEE Micro 44 , 33–39 (2024)..

Zhao, C. G. et al. Insights into DeepSeek-V3: scaling challenges and reflections on hardware for AI architectures. Proceedings of the 52nd Annual International Symposium on Computer Architecture . Tokyo, Japan: ACM, 2025, 1731-1745.

Jacobs, R. et al. A practical guide to machine learning interatomic potentials–status and future. Curr. Opin. Solid State Mater. Sci. 35 , 101214 (2025)..

Mehonic, A. & Kenyon, A. J. Brain-inspired computing needs a master plan. Nature 604 , 255–260 (2022)..

Filipovich, M. J. et al. Silicon photonic architecture for training deep neural networks with direct feedback alignment. Optica 9 , 1323–1332 (2022)..

Liu, H. et al. A 4×112 Gb/s PAM-4 silicon-photonic transmitter and receiver chipsets for linear-drive co-packaged optics. IEEE J. Solid-State Circuits 59 , 3263–3276 (2024)..

Shi, Y. C. et al. Silicon photonics for high-capacity data communications. Photonics Res. 10 , A106–A134 (2022)..

Ruan, Z. S. et al. Flexible orbital angular momentum mode switching in multimode fibre using an optical neural network chip[J ] . Light Adv. Manuf. 5 , 23 (2024)..

Seok, T. J. et al. Wafer-scale silicon photonic switches beyond die size limit. Optica 6 , 490–494 (2019)..

Huang, C. R. et al. A silicon photonic–electronic neural network for fibre nonlinearity compensation. Nat. Electron. 4 , 837–844 (2021)..

Shastri, B. J. et al. Photonics for artificial intelligence and neuromorphic computing. Nat. Photonics 15 , 102–114 (2021)..

Ashtiani, F., Geers, A. J. & Aflatouni, F. An on-chip photonic deep neural network for image classification. Nature 606 , 501–506 (2022)..

Chen, Z. & Segev, M. Highlighting photonics: Looking into the next decade. eLight 1 , 2 (2021)..

Shekhar, S. et al. Roadmapping the next generation of silicon photonics. Nat. Commun. 15 , 751 (2024)..

Wade, M. et al. Driving compute scale-out performance with optical I/O chiplets in advanced system-in-package platforms. 2023 IEEE Hot Chips 35 Symposium (HCS) . Palo Alto, CA, USA: IEEE, 2023, 1.

Yu, X. et al. Parallel optical computing capable of 100-wavelength multiplexing. eLight 5 , 10 (2025)..

Zhu, S. & Zhu, N. H. Nonlinear optoelectronic engine drives monolithic integrated photonic computing. Light Sci. Appl. 14 , 302 (2025)..

Oguz, I. et al. Resource-efficient photonic networks for next-generation AI computing. Light Sci. Appl. 14 , 34 (2025)..

Xu, Z. H. et al. Large-scale photonic chiplet Taichi empowers 160-TOPS/W artificial general intelligence. Science 384 , 202–209 (2024)..

Bandyopadhyay, S. et al. Single-chip photonic deep neural network with forward-only training. Nat. Photonics 18 , 1335–1343 (2024)..

Pérez, D. et al. Multipurpose silicon photonics signal processor core. Nat. Commun. 8 , 636 (2017)..

Bogaerts, W. et al. Programmable photonic circuits. Nature 586 , 207–216 (2020)..

Zhang, Q., Zhang, Y. & Czarske, J. FPGA-accelerated mode decomposition for multimode fiber-based communication. Light Adv. Manuf. 6 , 272–283 (2025)..

Reck, M. et al. Experimental realization of any discrete unitary operator. Phys. Rev. Lett. 73 , 58–61 (1994)..

Clements, W. R. et al. Optimal design for universal multiport interferometers. Optica 3 , 1460–1465 (2016)..

Perez, D. et al. Silicon photonics rectangular universal interferometer. Laser Photonics Rev. 11 , 1700219 (2017)..

Wang, J. W. et al. Integrated photonic quantum technologies. Nat. Photonics 14 , 273–284 (2020)..

Shen, Y. C. et al. Deep learning with coherent nanophotonic circuits. Nat. Photonics 11 , 441–446 (2017)..

Annoni, A. et al. Unscrambling light—automatically undoing strong mixing between modes. Light Sci. Appl. 6 , e17110 (2017)..

Choutagunta, K. et al. Adapting Mach–Zehnder mesh equalizers in direct-detection mode-division-multiplexed links. J. Lightwave Technol. 38 , 723–735 (2020)..

Zhuang, L. M. et al. Programmable photonic signal processor chip for radiofrequency applications. Optica 2 , 854–859 (2015)..

Pérez-López, D. et al. General-purpose programmable photonic processor for advanced radiofrequency applications. Nat. Commun. 15 , 1563 (2024)..

Zhao, M. Y., Wu, B. & Dong, J. J. On-chip multifunctional self-configurable quadrilateral MZI network. Opt. Mater. Expr. 13 , 3138–3147 (2023)..

Zhang, H. et al. An optical neural chip for implementing complex-valued neural network. Nat. Commun. 12 , 457 (2021)..

Pai, S. et al. Experimentallyrealized in situ backpropagation for deep learning in photonic neural networks. Science 380 , 398–404 (2023)..

Tischler, N., Rockstuhl, C. & Słowik, K. Quantum optical realization of arbitrary linear transformations allowing for loss and gain. Phys. Rev. X 8 , 021017 (2018)..

Hamerly, R. et al. Toward the information-theoretic limit of programmable photonics. APL Photonics 10 , 110803 (2025)..

Wade, M. et al. TeraPH Y: a chiplet technology for low-power, high-bandwidth in-package optical I/O. IEEE Micro 40 , 63–71 (2020)..

Cheng, Q. X. et al. Silicon photonic switch topologies and routing strategies for disaggregated data centers. IEEE J. Sel. Top. Quantum Electron. 26 , 8302010 (2020)..

Wang, R. P. et al. Recent advances of volatile memristors: devices, mechanisms, and applications. Adv. Intell. Syst. 2 , 2000055 (2020)..

Gao, Y. S., Al-Sarawi, S. F. & Abbott, D. Physical unclonable functions. Nat. Electron. 3 , 81–91 (2020)..

Athanas, P., Pnevmatikatos, D.&Sklavos, N. Embedded systems design with FPGAs. (New York: Springer, 2013).

Lee, K. K. et al. Fabrication of ultralow-loss Si/SiO2 waveguides by roughness reduction. Opt. Lett. 26 , 1888–1890 (2001)..

Shi, X. D. et al. Wet-oxidation-assisted chemical mechanical polishing and high-temperature thermal annealing for low-loss 4H-SiC integrated photonic devices. Materials 16 , 2324 (2023)..

Xie, Y. W. et al. Complex-valued matrix-vector multiplication using a scalable coherent photonic processor. Sci. Adv. 11 , eads7475 (2025)..

Hong, S. H. et al. Versatile parallel signal processing with a scalable silicon photonic chip. Nat. Commun. 16 , 288 (2025)..

Zhu, Y. et al. Silicon photonic neuromorphic accelerator using integrated coherent transmit-receive optical sub-assemblies. Optica 11 , 583–594 (2024)..

Hua, S. Y. et al. An integrated large-scale photonic accelerator with ultralow latency. Nature 640 , 361–367 (2025)..

Ahmed, S. R. et al. Universal photonic artificial intelligence acceleration. Nature 640 , 368–374 (2025)..

Aghaee Rad, H. et al. Scaling and networking a modular photonic quantum computer. Nature 638 , 912–919 (2025)..

Li, R. J. et al. Photonics for neuromorphic computing: Fundamentals, devices, and opportunities. Adv. Mater. 37 , 2312825 (2025)..

Jouppi, N. et al. TPU v4: An optically reconfigurable supercomputer for machine learning with hardware support for embeddings. Proceedings of the 50th Annual International Symposium on Computer Architecture . Orlando, FL, USA: ACM, 2023, 82.

Zhang, Y. G. et al. 240 Gb/s optical transmission based on an ultrafast silicon microring modulator. Photonics Res. 10 , 1127–1133 (2022)..

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

Continuous polarization–wavelength mapping with nonlocal metasurfaces

Deformation engineering enables precise dispersion control in an optical microcavity

Superextensive electrical power from a quantum battery

Deterministic quantum light emitters in DNA origami–engineered molecule–MoS2 hybrids

Robust chirality through merging BICs

Related Author

No data

Related Institution

No data

⁰