Photonic computing chips under the speed-complexity trade-off

Xinyue Sun; Guoqiang Yang; Yitong Chen; Guangtao Zhai

doi:10.1088/1674-4926/26020065

J. Semicond. > In Press

RESEARCH HIGHLIGHTS

Photonic computing chips under the speed-complexity trade-off

Xinyue Sun^§, Guoqiang Yang^§, Yitong Chen and Guangtao Zhai

+ Author Affiliations

Institute of Image Communication and Network Engineering, School of Information Science and Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
^§Xinyue Sun and Guoqiang Yang contributed equally to this work and should be considered as co-first authors.

Author Bio:

Xinyue Sun got her bachelor’s degree from Shandong University in 2024. Now she is a Ph.D. student at Shanghai Jiao Tong University. Her research focuses on optical computing for generative tasks.

Guoqiang Yang got his bachelor’s degree from Xidian University in 2024. Now he is a Ph.D. student at Shanghai Jiao Tong University. His research focuses on optical neural networks and deep learning.

Yitong Chen is a tenure-track assistant professor in the School of Integrated Circuits (School of Information Science and Electronic Engineering) at Shanghai Jiao Tong University. She received her B.S. degree from the Qian Xuesen Class, Tsinghua University, in 2019, and her Ph.D. degree from the Department of Automation, Tsinghua University, in 2024. Her current research interests focus on high-speed, low-power optoelectronic intelligent computing chips and their applications.

Guangtao Zhai is a Distinguished Professor at Shanghai Jiao Tong University, a jointly appointed scientist at the Shanghai Artificial Intelligence Laboratory, an IEEE Fellow, and a national-level high-caliber talent. He has conducted long-term research in multimedia intelligence and has been recognized globally as a Clarivate Highly Cited Researcher. Professor Zhai has received over 30 international awards, including Best Paper Awards from IEEE Transactions on Multimedia and IEEE Transactions on Broadcasting.

Corresponding author: Yitong Chen, yitongchen@sjtu.edu.cn; Guangtao Zhai, zhaiguangtao@sjtu.edu.cn

DOI: 10.1088/1674-4926/26020065CSTR: 32376.14.1674-4926.26020065

References

[1]	Fu T Z, Zhang J F, Sun R, et al. Optical neural networks: progress and challenges. Light Sci Appl, 2024, 13: 263 doi: 10.1038/s41377-024-01590-3
[2]	Fu T Z, Zang Y B, Huang Y Y, et al. Photonic machine learning with on-chip diffractive optics. Nat Commun, 2023, 14: 70 doi: 10.1038/s41467-022-35772-7
[3]	Cheng J W, Huang C R, Zhang J L, et al. Multimodal deep learning using on-chip diffractive optics with in situ training capability. Nat Commun, 2024, 15: 6189 doi: 10.1038/s41467-024-50677-3
[4]	Zhu H H, Zou J, Zhang H, et al. Space-efficient optical computing with an integrated chip diffractive neural network. Nat Commun, 2022, 13: 1044 doi: 10.1038/s41467-022-28702-0
[5]	Cong G W, Yamamoto N, Inoue T, et al. On-chip bacterial foraging training in silicon photonic circuits for projection-enabled nonlinear classification. Nat Commun, 2022, 13: 3261 doi: 10.1038/s41467-022-30906-3
[6]	Shi Y, Ren J Y, Chen G Y, et al. Nonlinear germanium-silicon photodiode for activation and monitoring in photonic neuromorphic networks. Nat Commun, 2022, 13: 6048 doi: 10.1038/s41467-022-33877-7
[7]	Gu Z J, Shi Y, Zhu Z M, et al. All-integrated multidimensional optical sensing with a photonic neuromorphic processor. Sci Adv, 2025, 11(22): eadu7277 doi: 10.1126/sciadv.adu7277
[8]	Zhang H, Huang B J, Cheng C T, et al. On-chip silicon photonic neural networks based on thermally tunable microring resonators for recognition tasks. Photonics, 2025, 12(7): 640 doi: 10.3390/photonics12070640
[9]	Ma P Y, Tait A N, Ferreira de Lima T, et al. Photonic independent component analysis using an on-chip microring weight bank. Opt Express, 2020, 28(2): 1827 doi: 10.1364/OE.383603
[10]	Yu W Z, Zheng S, Zhao Z Y, et al. Reconfigurable low-threshold all-optical nonlinear activation functions based on an add-drop silicon microring resonator. IEEE Photonics J, 2022, 14(6): 5559807 doi: 10.1109/jphot.2022.3219246
[11]	Huang C R, Bilodeau S, Ferreira de Lima T, et al. Demonstration of scalable microring weight bank control for large-scale photonic integrated circuits. APL Photonics, 2020, 5(4): 040803 doi: 10.1063/1.5144121
[12]	Chen Y T, Nazhamaiti M, Xu H, et al. All-analog photoelectronic chip for high-speed vision tasks. Nature, 2023, 623: 48 doi: 10.1038/s41586-023-06558-8
[13]	Wei K X, Li X, Froech J, et al. Spatially varying nanophotonic neural networks. Sci Adv, 2024, 10(45): eadp0391 doi: 10.1126/sciadv.adp0391
[14]	Wang X, Redding B, Karl N, et al. Integrated photonic encoder for low power and high-speed image processing. Nat Commun, 2024, 15: 4510 doi: 10.1038/s41467-024-48099-2
[15]	Ahmed S R, Baghdadi R, Bernadskiy M, et al. Universal photonic artificial intelligence acceleration. Nature, 2025, 640: 368 doi: 10.1038/s41586-025-08854-x
[16]	Hua S Y, Divita E, Yu S S, et al. An integrated large-scale photonic accelerator with ultralow latency. Nature, 2025, 640: 361 doi: 10.1038/s41586-025-08786-6
[17]	Zhu H Q, Gu J Q, Wang H R, et al. Lightening-transformer: a dynamically-operated optically-interconnected photonic transformer accelerator. 2024 IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2024: 686 doi: 10.1109/HPCA57654.2024.00059
[18]	Chen Y T, Zhou T K, Wu J M, et al. Photonic unsupervised learning variational autoencoder for high-throughput and low-latency image transmission. Sci Adv, 2023, 9(7): eadf8437 doi: 10.1126/sciadv.adf8437
[19]	Chen Y T, Zhou T K, Guo Y C, et al. Hardware-implemented photonic neural network for high-throughput and low-latency image transmission. Optica Imaging Congress, 2023: JTh1A.3 doi: 10.1364/3D.2023.JTh1A.3
[20]	Chen Y T, Sun X Y, Tan L T, et al. All-optical synthesis chip for large-scale intelligent semantic vision generation. Science, 2025, 390(6779): 1259 doi: 10.1126/science.adv7434

Fig. 1. (Color online) (a) Three mainstream photonic chip architectures include on-chip interference, on-chip diffraction, and microring resonators. Adapted from Ref. [20]. Copyright 2025, American Association for the Advancement of Science. (b) Photonic chips used for high-speed visual tasks requiring single-pass inference and for general-purpose computing tasks, respectively. Adapted from Refs. [12, 15]. Copyright 2023 and 2025, Springer Nature. (c) The LightGen architecture and the generative tasks it realizes. Adapted from Ref. [20]. Copyright 2025, American Association for the Advancement of Science.

DownLoad: Full-Size Img PowerPoint

[1]	Fu T Z, Zhang J F, Sun R, et al. Optical neural networks: progress and challenges. Light Sci Appl, 2024, 13: 263 doi: 10.1038/s41377-024-01590-3
[2]	Fu T Z, Zang Y B, Huang Y Y, et al. Photonic machine learning with on-chip diffractive optics. Nat Commun, 2023, 14: 70 doi: 10.1038/s41467-022-35772-7
[3]	Cheng J W, Huang C R, Zhang J L, et al. Multimodal deep learning using on-chip diffractive optics with in situ training capability. Nat Commun, 2024, 15: 6189 doi: 10.1038/s41467-024-50677-3
[4]	Zhu H H, Zou J, Zhang H, et al. Space-efficient optical computing with an integrated chip diffractive neural network. Nat Commun, 2022, 13: 1044 doi: 10.1038/s41467-022-28702-0
[5]	Cong G W, Yamamoto N, Inoue T, et al. On-chip bacterial foraging training in silicon photonic circuits for projection-enabled nonlinear classification. Nat Commun, 2022, 13: 3261 doi: 10.1038/s41467-022-30906-3
[6]	Shi Y, Ren J Y, Chen G Y, et al. Nonlinear germanium-silicon photodiode for activation and monitoring in photonic neuromorphic networks. Nat Commun, 2022, 13: 6048 doi: 10.1038/s41467-022-33877-7
[7]	Gu Z J, Shi Y, Zhu Z M, et al. All-integrated multidimensional optical sensing with a photonic neuromorphic processor. Sci Adv, 2025, 11(22): eadu7277 doi: 10.1126/sciadv.adu7277
[8]	Zhang H, Huang B J, Cheng C T, et al. On-chip silicon photonic neural networks based on thermally tunable microring resonators for recognition tasks. Photonics, 2025, 12(7): 640 doi: 10.3390/photonics12070640
[9]	Ma P Y, Tait A N, Ferreira de Lima T, et al. Photonic independent component analysis using an on-chip microring weight bank. Opt Express, 2020, 28(2): 1827 doi: 10.1364/OE.383603
[10]	Yu W Z, Zheng S, Zhao Z Y, et al. Reconfigurable low-threshold all-optical nonlinear activation functions based on an add-drop silicon microring resonator. IEEE Photonics J, 2022, 14(6): 5559807 doi: 10.1109/jphot.2022.3219246
[11]	Huang C R, Bilodeau S, Ferreira de Lima T, et al. Demonstration of scalable microring weight bank control for large-scale photonic integrated circuits. APL Photonics, 2020, 5(4): 040803 doi: 10.1063/1.5144121
[12]	Chen Y T, Nazhamaiti M, Xu H, et al. All-analog photoelectronic chip for high-speed vision tasks. Nature, 2023, 623: 48 doi: 10.1038/s41586-023-06558-8
[13]	Wei K X, Li X, Froech J, et al. Spatially varying nanophotonic neural networks. Sci Adv, 2024, 10(45): eadp0391 doi: 10.1126/sciadv.adp0391
[14]	Wang X, Redding B, Karl N, et al. Integrated photonic encoder for low power and high-speed image processing. Nat Commun, 2024, 15: 4510 doi: 10.1038/s41467-024-48099-2
[15]	Ahmed S R, Baghdadi R, Bernadskiy M, et al. Universal photonic artificial intelligence acceleration. Nature, 2025, 640: 368 doi: 10.1038/s41586-025-08854-x
[16]	Hua S Y, Divita E, Yu S S, et al. An integrated large-scale photonic accelerator with ultralow latency. Nature, 2025, 640: 361 doi: 10.1038/s41586-025-08786-6
[17]	Zhu H Q, Gu J Q, Wang H R, et al. Lightening-transformer: a dynamically-operated optically-interconnected photonic transformer accelerator. 2024 IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2024: 686 doi: 10.1109/HPCA57654.2024.00059
[18]	Chen Y T, Zhou T K, Wu J M, et al. Photonic unsupervised learning variational autoencoder for high-throughput and low-latency image transmission. Sci Adv, 2023, 9(7): eadf8437 doi: 10.1126/sciadv.adf8437
[19]	Chen Y T, Zhou T K, Guo Y C, et al. Hardware-implemented photonic neural network for high-throughput and low-latency image transmission. Optica Imaging Congress, 2023: JTh1A.3 doi: 10.1364/3D.2023.JTh1A.3
[20]	Chen Y T, Sun X Y, Tan L T, et al. All-optical synthesis chip for large-scale intelligent semantic vision generation. Science, 2025, 390(6779): 1259 doi: 10.1126/science.adv7434

Search

GET CITATION

shu

Export: BibTex EndNote

Article Metrics

Article views: 17 Times PDF downloads: 6 Times Cited by: 0 Times

History

Received: 25 February 2026 Revised: 28 March 2026 Online: Accepted Manuscript: 14 April 2026Uncorrected proof: 14 April 2026

Article Navigation > Journal of Semiconductors > 2026 > Uncorrected proof

Xinyue Sun, Guoqiang Yang, Yitong Chen, Guangtao Zhai. Photonic computing chips under the speed-complexity trade-off[J]. Journal of Semiconductors, 2026, In Press. doi: 10.1088/1674-4926/26020065 ****X Y Sun, G Q Yang, Y T Chen, and G T Zhai, Photonic computing chips under the speed-complexity trade-off[J]. J. Semicond., 2026, accepted doi: 10.1088/1674-4926/26020065

Citation:

Xinyue Sun, Guoqiang Yang, Yitong Chen, Guangtao Zhai. Photonic computing chips under the speed-complexity trade-off[J]. Journal of Semiconductors, 2026, In Press. doi: 10.1088/1674-4926/26020065 ****

X Y Sun, G Q Yang, Y T Chen, and G T Zhai, Photonic computing chips under the speed-complexity trade-off[J]. J. Semicond., 2026, accepted doi: 10.1088/1674-4926/26020065

Citation:

X Y Sun, G Q Yang, Y T Chen, and G T Zhai, Photonic computing chips under the speed-complexity trade-off[J]. J. Semicond., 2026, accepted doi: 10.1088/1674-4926/26020065

PDF( 2449 KB)

Photonic computing chips under the speed-complexity trade-off

DOI: 10.1088/1674-4926/26020065

CSTR: 32376.14.1674-4926.26020065

Institute of Image Communication and Network Engineering, School of Information Science and Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China

More Information

Xinyue Sun got her bachelor’s degree from Shandong University in 2024. Now she is a Ph.D. student at Shanghai Jiao Tong University. Her research focuses on optical computing for generative tasks
Guoqiang Yang got his bachelor’s degree from Xidian University in 2024. Now he is a Ph.D. student at Shanghai Jiao Tong University. His research focuses on optical neural networks and deep learning
Yitong Chen is a tenure-track assistant professor in the School of Integrated Circuits (School of Information Science and Electronic Engineering) at Shanghai Jiao Tong University. She received her B.S. degree from the Qian Xuesen Class, Tsinghua University, in 2019, and her Ph.D. degree from the Department of Automation, Tsinghua University, in 2024. Her current research interests focus on high-speed, low-power optoelectronic intelligent computing chips and their applications
Guangtao Zhai is a Distinguished Professor at Shanghai Jiao Tong University, a jointly appointed scientist at the Shanghai Artificial Intelligence Laboratory, an IEEE Fellow, and a national-level high-caliber talent. He has conducted long-term research in multimedia intelligence and has been recognized globally as a Clarivate Highly Cited Researcher. Professor Zhai has received over 30 international awards, including Best Paper Awards from IEEE Transactions on Multimedia and IEEE Transactions on Broadcasting
Corresponding author: yitongchen@sjtu.edu.cn; zhaiguangtao@sjtu.edu.cn
Received Date: 2026-02-25
Revised Date: 2026-03-28

Available Online: 2026-04-14

Abstract

^§Xinyue Sun and Guoqiang Yang contributed equally to this work and should be considered as co-first authors.

FullText(HTML)

References(20)