Research Progress and Perspectives in Optoelectronic Computing Systems (Invited)

Xiang Zhang; Hao Zhang; Wenlin Cui; Anle Shen; Zhijun Liang; Chong Li; Tao Fang; Jingwei Li; Jiayi Ouyang; Xinxiang Niu; Qinghai Guo; Xiaowen Dong

doi:10.3788/AOS251195

Acta Optica Sinica, Volume. 45, Issue 17, 1720006(2025)

Research Progress and Perspectives in Optoelectronic Computing Systems (Invited)

Xiang Zhang, Hao Zhang, Wenlin Cui, Anle Shen, Zhijun Liang, Chong Li, Tao Fang, Jingwei Li, Jiayi Ouyang, Xinxiang Niu, Qinghai Guo, and Xiaowen Dong^*

Author Affiliations

Huawei Technologies Co., Ltd., Shenzhen 518129, Guangdong , China

show less

Abstract Get PDF(in Chinese)

References(132)

[1] Lee J, Toutanova K. Pre-training of deep bidirectional transformers for language understanding[EB/OL]. https:∥arxiv.org/abs/1810.04805

[2] Radford A, Narasimhan K, Salimans T et al. Improving language understanding by generative pre-training[EB/OL]. https:∥cdn.openai.com/research-covers/language-unsupervised/language_understanding_paper.pdf

[3] Radford A, Wu J, Child R et al. Language models are unsupervised multitask learners[EB/OL]. https:∥cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf

[4] Brown T, Mann B, Ryder N et al. Language models are few-shot learners[EB/OL]. https:∥arxiv.org/abs/2005.14165

[5] Zoubeirou a Mayaki M, Charpenay V. Modeling energy consumption in deep learning architectures using scaling laws[EB/OL]. https:∥hal.science/hal-04977474/

[6] Bengio Y, Ducharme R, Vincent P et al. A neural probabilistic language model[EB/OL]. https:∥jmlr.org/papers/volume3/bengio03a/bengio03a.pdf

[7] Vaswani A, Shazeer N, Parmar N et al. Attention is all you need[EB/OL]. https:∥arxiv.org/abs/1706.03762

[8] Fedus W, Zoph B, Shazeer N. Switch transformers: scaling to trillion parameter models with simple and efficient sparsity[EB/OL]. https:∥arxiv.org/abs/2101.03961

[9] Radford A, Kim J W, Hallacy C et al. Learning transferable visual models from natural language supervision[EB/OL]. https:∥arxiv.org/abs/2103.00020

[10] Ramesh A, Pavlov M, Goh G et al. Zero-shot text-to-image generation[EB/OL]. https:∥arxiv.org/abs/2102.12092

[12] Team G, Anil R, Borgeaud S et al. Gemini: a family of highly capable multimodal models[EB/OL]. https:∥arxiv.org/abs/2312.11805

[13] Ramesh A, Dhariwal P, Nichol A et al. Hierarchical text-conditional image generation with clip latents[EB/OL]. https:∥arxiv.org/abs/2204.06125

[14] Ielmini D, Wong H S P. In-memory computing with resistive switching devices[J]. Nature Electronics, 1, 333-343(2018).

[16] Doevenspeck J, Garello K, Verhoef B et al. SOT-MRAM based analog in-memory computing for DNN inference[C], 1-2(2020).

[17] Patel A, Biswas D, Kundu J et al. Accelerating large language model training with in-package optical links for scale-out systems[C], 118-123(2024).

[18] Venkataramani S, Chakradhar S T, Roy K et al. Approximate computing and the quest for computing efficiency[C], 1-6(2015).

[19] Black B, Annavaram M, Brekelbaum N et al. Die stacking (3D) microarchitecture[C], 469-479(2006).

[20] Pai S, Sun Z H, Hughes T W et al. Experimentally realized in situ backpropagation for deep learning in photonic neural networks[J]. Science, 380, 398-404(2023).

[21] Kudithipudi D, Schuman C, Vineyard C M et al. Neuromorphic computing at scale[J]. Nature, 637, 801-812(2025).

[22] Gholami A, Yao Z, Kim S et al. AI and memory wall[J]. IEEE Micro, 44, 33-39(2024).

[23] Miller D A B, Ozaktas H M. Limit to the bit-rate capacity of electrical interconnects from the aspect ratio of the system architecture[J]. Journal of Parallel and Distributed Computing, 41, 42-52(1997).

[24] Chen X, Liao P, Tang F Y et al. 540 Gbps IMDD transmission over 30 km SMF using 110 GHz bandwidth InP EML[C], 1-3(2025).

[25] Li X, Davies J C, Koh E S C et al. Silicon photonic traveling wave Mach-Zehnder modulators for 400 G/lane transmitters[C]. United Kingdom, 1-2(2025).

[26] Hosseini K, Kok E, Shumarayev S Y et al. 8 Tbps co-packaged FPGA and silicon photonics optical IO[C]. DC, Th4A.2-11(2021).

[29] Mao J W, Uemura F, Yazdani S A et al. Ultra-fast perovskite electro-optic modulator and multi-band transmission up to 300 Gbit s-1[J]. Communications Materials, 5, 114(2024).

[30] Wolf S, Zwickel H, Hartmann W et al. Silicon-organic hybrid (SOH) Mach-Zehnder modulators for 100 Gbit/s on-off keying[J]. Scientific Reports, 8, 2598(2018).

[31] Burla M, Hoessbacher C, Heni W et al. 500 GHz plasmonic Mach-Zehnder modulator enabling sub-THz microwave photonics[J]. APL Photonics, 4, 056106(2019).

[32] Chelladurai D, Kohli M, Winiger J et al. Barium titanate and lithium niobate permittivity and Pockels coefficients from megahertz to sub-terahertz frequencies[J]. Nature Materials, 24, 868-875(2025).

[33] Wang J Y, Murty M V R, Jiang S Z et al. 200 Gb/s PAM4 oxide VCSEL development progress at Broadcom[J]. Proceedings of SPIE, 13384, 1338403(2025).

[36] Coherent demostrates 1.6 T optical transceivers based on. G VCSELS(200). https:∥www.coherent.com/news/press-releases/optical-transceivers-based-on-200g-vcsels

[37] Han C H, Zheng Z, Shu H W et al. Slow-light silicon modulator with 110-GHz bandwidth[J]. Science Advances, 9, eadi5339(2023).

[38] Zhang Y W, Shao L B, Yang J W et al. Systematic investigation of millimeter-wave optic modulation performance in thin-film lithium niobate[J]. Photonics Research, 10, 2380-2387(2022).

[39] Schwarzenberger A, Fang D, Kotz A et al. Silicon-organic hybrid (SOH) Mach-Zehnder modulator (MZM) for single-carrier IMDD line rates of 500 Gbit/s and beyond[C], M4K.1(2025).

[40] Horst Y, Moor D, Chelladurai D et al. Ultra-wideband MHz to THz plasmonic EO modulator[J]. Optica, 12, 325-328(2025).

[41] Qiu B, St-Arnault C, Li W J et al. 112 GBaud PAM4 barium titanate coupling modulated ring modulator monolithically integrated on a silicon substrate[C], M3K.4(2025).

[42] Sinatkas G, Christopoulos T, Tsilipakos O et al. Electro-optic modulation in integrated photonics[J]. Journal of Applied Physics, 130, 010901(2021).

[43] Xu M Y, Cai X L. Advances in integrated ultra-wideband electro-optic modulators[J]. Optics Express, 30, 7253-7274(2022).

[44] Tan M, Xu J, Liu S Y et al. Co-packaged optics (CPO): status, challenges, and solutions[J]. Frontiers of Optoelectronics, 16, 1(2023).

[45] Tian W C, Hou H H, Dang H J et al. Progress in research on co-packaged optics[J]. Micromachines, 15, 1211(2024).

[46] Minkenberg C, Krishnaswamy R, Zilkie A et al. Co-packaged datacenter optics: opportunities and challenges[J]. IET Optoelectronics, 15, 77-91(2021).

[47] Fathololoumi S, Malouin C, Hui D et al. Highly integrated 4 Tbps silicon photonic IC for compute fabric connectivity[C], 1-4(2022).

[48] Chang P H, Samanta A, Yan P et al. A 3D integrated energy-efficient transceiver realized by direct bond interconnect of co-designed 12 nm FinFET and silicon photonic integrated circuits[J]. Journal of Lightwave Technology, 41, 6741-6755(2023).

[49] Daudlin S, Rizzo A, Lee S et al. Three-dimensional photonic integration for ultra-low-energy, high-bandwidth interchip data links[J]. Nature Photonics, 19, 502-509(2025).

[50] de Valicourt G, Pupalaikis P, Giles R et al. 1.6-Tbps low-power linear-drive high-density optical interface for machine learning/artificial intelligence[J]. Optics Express, 33, 15338-15354(2025).

[51] Pezeshki B, Tselikov A, Kalman R et al. Parallel microLED-based optical links with record data rates and low power consumption[C], AM1R.2-12(2023).

[52] Kuchta D M. Developments of VCSEL-based transceivers for co-packaging[C], 1-3(2023).

[54] Urata R, Liu H, Yasumura K et al. Mission Apollo: landing optical circuit switching at datacenter scale[EB/OL]. https:∥arxiv.org/abs/2208.10041

[55] Liu H, Urata R, Yasumura K et al. Lightwave fabrics: at-scale optical circuit switching for datacenter and machine learning systems[C], 156-161(2024).

[56] Jouppi N, Kurian G, Li S et al. TPU v4: an optically reconfigurable supercomputer for machine learning with hardware support for embeddings[C], 1-14(2023).

[57] Hong C Y. Optical switch devices using the magnetic fluid thin films[J]. Journal of Magnetism and Magnetic Materials, 201, 178-181(1999).

[58] Yang X, Nisar M S, Yuan W et al. Phase change material enabled 2×2 silicon nonvolatile optical switch[J]. Optics Letters, 46, 4224-4227(2021).

[59] Nashimoto K, Tanaka N, LaBuda M et al. High-speed PLZT optical switches for burst and packet switching[C], 1118-1123(2005).

[60] Hu G H, Qi Z P, Yun B F et al. Compact, integrated PLZT optical switch array[J]. Chinese Optics Letters, 13, 111301(2015).

[61] CALIENT introduces edge|. optical circuit switch for increased connectivity demand from network virtualization[EB/OL]. https:∥www.lightwaveonline.com/network-design/article/16675531/calient-introduces-edge 640-optical-circuit-switch-for-increased-connectivity-demand-from-network-virtualization

[64] Series. port software defined opticsl circuit switch[EB/OL]. -port-software-controlled-optical-circuit-switch-sdn-enabled, -384(384). https:∥www.polatis.com/series-7000-384

[65] Chu T, Chen N, Tang W J et al. Large-scale high-speed photonic switches fabricated on silicon-based photonic platforms[C], 1-3(2023).

[66] Qiao L, Tang W J, Chu T. Ultra-large-scale silicon optical switches[C], 1-2(2016).

[67] Seok T J, Kwon K, Henriksson J et al. Wafer-scale silicon photonic switches beyond die size limit[J]. Optica, 6, 490-494(2019).

[68] Seok T J, Quack N, Han S et al. Large-scale broadband digital silicon photonic switches with vertical adiabatic couplers[J]. Optica, 3, 64-70(2016).

[69] Feng X L, Wu T W, Gao Z H et al. Non-Hermitian hybrid silicon photonic switching[J]. Nature Photonics, 19, 264-270(2025).

[70] Cheung S, Su T H, Okamoto K et al. Ultra-compact silicon photonic 512×512 25 GHz arrayed waveguide grating router[J]. IEEE Journal of Selected Topics in Quantum Electronics, 20, 8202207(2014).

[71] Barbarin Y, Leijtens X J M, Bente E A J M et al. Extremely small AWG demultiplexer fabricated on InP by using a double-etch process[J]. IEEE Photonics Technology Letters, 16, 2478-2480(2004).

[72] Raja A S, Lange S, Karpov M et al. Ultrafast optical circuit switching for data centers using integrated soliton microcombs[J]. Nature Communications, 12, 5867(2021).

[73] Fan Z P, Guo J, Zhang S J et al. Monolithically integrated 8×8 transmitter-router based on tunable V-cavity laser array and cyclic arrayed waveguide grating router[J]. IEEE Photonics Journal, 14, 6642508(2022).

[74] Yu B, Gao Y S, Chen G X. LCOS-based 3×3 folded wavelength selective switch with high-resolution spectral[J]. IEEE Photonics Journal, 15, 7200205(2023).

[75] Ye T, Chen K. Modular WSS-based OXCs for large-scale optical networks[EB/OL]. https:∥arxiv.org/abs/2005.12751

[76] Li H J, Wang D, Ye B. Development and application of all-optical crossover technology[EB/OL]. https:∥www.zte.com.cn/china/about/magazine/zte-technologies/2023/1-cn/5/2.html

[78] Lin X, Rivenson Y, Yardimci N T et al. All-optical machine learning using diffractive deep neural networks[J]. Science, 361, 1004-1008(2018).

[79] Yan T, Wu J M, Zhou T K et al. Fourier-space diffractive deep neural network[J]. Physical Review Letters, 123, 023901(2019).

[80] Zhou T K, Lin X, Wu J M et al. Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit[J]. Nature Photonics, 15, 367-373(2021).

[81] Chang J L, Sitzmann V, Dun X et al. Hybrid optical-electronic convolutional neural networks with optimized diffractive optics for image classification[J]. Scientific Reports, 8, 12324(2018).

[82] Zuo Y, Li B H, Zhao Y J et al. All-optical neural network with nonlinear activation functions[J]. Optica, 6, 1132-1137(2019).

[83] Kalinin K P, Mourgias-Alexandris G, Ballani H et al. Analog iterative machine (AIM): using light to solve quadratic optimization problems with mixed variables[EB/OL]. https:∥arxiv.org/abs/2304.12594

[84] Song A, Murty Kottapalli S N, Goyal R et al. Low-power scalable multilayer optoelectronic neural networks enabled with incoherent light[J]. Nature Communications, 15, 10692(2024).

[85] Brunner D, Fischer I. Reconfigurable semiconductor laser networks based on diffractive coupling[J]. Optics Letters, 40, 3854-3857(2015).

[86] Dong J, Gigan S, Krzakala F et al. Scaling up echo-state networks with multiple light scattering[C], 448-452(2018).

[87] Ding C X, Shao R J, Li J W et al. Optoelectronic reservoir computing based on complex-value encoding[J]. Advanced Photonics Nexus, 3, 066006(2024).

[88] Cheng J L, Li C, Dai J et al. Direct optical convolution computing based on arrayed waveguide grating router[J]. Laser & Photonics Reviews, 18, 2301221(2024).

[89] Zhang S J, Zhou H J, Wu B et al. Redundancy-free integrated optical convolver for optical neural networks based on arrayed waveguide grating[J]. Nanophotonics, 13, 19-28(2024).

[90] Park Y, Azaña J. Optical signal processors based on a time-spectrum convolution[J]. Optics Letters, 35, 796-798(2010).

[91] Zhang X, Huo T C, Wang C M et al. Optical computing for optical coherence tomography[J]. Scientific Reports, 6, 37286(2016).

[92] Babashah H, Kavehvash Z, Khavasi A et al. Temporal analog optical computing using an on-chip fully reconfigurable photonic signal processor[J]. Optics & Laser Technology, 111, 66-74(2019).

[93] Huang Y Y, Zhang W J, Yang F et al. Programmable matrix operation with reconfigurable time-wavelength plane manipulation and dispersed time delay[J]. Optics Express, 27, 20456-20467(2019).

[94] Xu X Y, Tan M X, Corcoran B et al. 11 TOPS photonic convolutional accelerator for optical neural networks[J]. Nature, 589, 44-51(2021).

[95] Paquot Y, Duport F, Smerieri A et al. Optoelectronic reservoir computing[J]. Scientific Reports, 2, 287(2012).

[96] Duport F, Schneider B, Smerieri A et al. All-optical reservoir computing[J]. Optics Express, 20, 22783-22795(2012).

[97] Borghi M, Biasi S, Pavesi L. Reservoir computing based on a silicon microring and time multiplexing for binary and analog operations[J]. Scientific Reports, 11, 15642(2021).

[98] Nakajima M, Tanaka K, Hashimoto T. Scalable reservoir computing on coherent linear photonic processor[J]. Communications Physics, 4, 20(2021).

[99] Takesue H, Inagaki T. 10 GHz clock time-multiplexed degenerate optical parametric oscillators for a photonic Ising spin network[J]. Optics Letters, 41, 4273-4276(2016).

[100] McMahon P L, Marandi A, Haribara Y et al. A fully programmable 100-spin coherent Ising machine with all-to-all connections[J]. Science, 354, 614-617(2016).

[101] Marandi A, Wang Z, Takata K et al. Network of time-multiplexed optical parametric oscillators as a coherent Ising machine[J]. Nature Photonics, 8, 937-942(2014).

[102] Takata K, Marandi A, Hamerly R et al. A 16-bit coherent Ising machine for one-dimensional ring and cubic graph problems[J]. Scientific Reports, 6, 34089(2016).

[103] Inagaki T, Inaba K, Hamerly R et al. Large-scale Ising spin network based on degenerate optical parametric oscillators[J]. Nature Photonics, 10, 415-419(2016).

[104] Inagaki T, Haribara Y, Igarashi K et al. A coherent Ising machine for 2000-node optimization problems[J]. Science, 354, 603-606(2016).

[105] Böhm F, Verschaffelt G, Van der Sande G. A poor man’s coherent Ising machine based on opto-electronic feedback systems for solving optimization problems[J]. Nature Communications, 10, 3538(2019).

[106] Cen Q Z, Ding H, Hao T F et al. Large-scale coherent Ising machine based on optoelectronic parametric oscillator[J]. Light: Science & Applications, 11, 333(2022).

[107] Babaeian M, Nguyen D T, Demir V et al. A single shot coherent Ising machine based on a network of injection-locked multicore fiber lasers[J]. Nature Communications, 10, 3516(2019).

[108] Redding B, Murray J B, Hart J D et al. Fiber optic computing using distributed feedback[J]. Communications Physics, 7, 75(2024).

[109] Brückerhoff-Plückelmann F, Borras H, Klein B et al. Probabilistic photonic computing with chaotic light[J]. Nature Communications, 15, 10445(2024).

[110] Lu K H, Chen Z Q, Chen H et al. Empowering high-dimensional optical fiber communications with integrated photonic processors[J]. Nature Communications, 15, 3515(2024).

[111] Wen F, Yong J, Li J J et al. Reservoir computing-based signal compensation for laser inter-satellite communications[J]. Scientific Reports, 15, 5622(2025).

[112] Shen Y C, Harris N C, Skirlo S et al. Deep learning with coherent nanophotonic circuits[J]. Nature Photonics, 11, 441-446(2017).

[113] Reck M, Zeilinger A, Bernstein H J et al. Experimental realization of any discrete unitary operator[J]. Physical Review Letters, 73, 58-61(1994).

[114] Roques-Carmes C, Shen Y C, Zanoci C et al. Heuristic recurrent algorithms for photonic Ising machines[J]. Nature Communications, 11, 249(2020).

[115] Prabhu M, Roques-Carmes C, Shen Y C et al. Accelerating recurrent Ising machines in photonic integrated circuits[J]. Optica, 7, 551-558(2020).

[116] Zhang H, Gu M, Jiang X D et al. An optical neural chip for implementing complex-valued neural network[J]. Nature Communications, 12, 457(2021).

[117] Fang M Y, Manipatruni S, Wierzynski C et al. Design of optical neural networks with component imprecisions[J]. Optics Express, 27, 14009-14029(2019).

[118] Tian Y, Zhao Y, Liu S P et al. Scalable and compact photonic neural chip with low learning-capability-loss[J]. Nanophotonics, 11, 329-344(2021).

[119] Ouyang J Y, Liu S P, Yang Z Y et al. 16-channel photonic solver for optimization problems on a silicon chip[J]. Chip, 4, 100117(2025).

[120] Zhu H H, Zou J, Zhang H et al. Space-efficient optical computing with an integrated chip diffractive neural network[J]. Nature Communications, 13, 1044(2022).

[121] Fu T Z, Zang Y B, Huang Y Y et al. Photonic machine learning with on-chip diffractive optics[J]. Nature Communications, 14, 70(2023).

[122] Feldmann J, Youngblood N, Wright C D et al. All-optical spiking neurosynaptic networks with self-learning capabilities[J]. Nature, 569, 208-214(2019).

[123] Feldmann J, Youngblood N, Karpov M et al. Parallel convolutional processing using an integrated photonic tensor core[J]. Nature, 589, 52-58(2021).

[124] Xu X Y, Huang X L, Li Z M et al. A scalable photonic computer solving the subset sum problem[J]. Science Advances, 6, eaay5853(2020).

[125] Tan X, Song H, Ji Y et al. Scalable and programmable three-dimensional photonic processor[J]. Physical Review Applied, 20, 044041(2023).

[126] Jiang X Y, He Z M, Wu B et al. Programmable photonic solver for computationally complex problems[J]. ACS Photonics, 10, 4340-4348(2023).

[127] Bandyopadhyay S, Sludds A, Krastanov S et al. Single-chip photonic deep neural network with forward-only training[J]. Nature Photonics, 18, 1335-1343(2024).

[128] Chen Y T, Nazhamaiti M, Xu H et al. All-analog photoelectronic chip for high-speed vision tasks[J]. Nature, 623, 48-57(2023).

[129] Xu Z H, Zhou T K, Ma M Z et al. Large-scale photonic chiplet Taichi empowers 160-TOPS/W artificial general intelligence[J]. Science, 384, 202-209(2024).

[130] Li C, Zhang X, Li J W et al. The challenges of modern computing and new opportunities for optics[J]. PhotoniX, 2, 20(2021).

[131] Meech J T, Tsoutsouras V, Stanley-Marbell P. The data conversion bottleneck in analog computing accelerators[EB/OL]. https:∥arxiv.org/abs/2308.01719

[132] McMahon P L. The physics of optical computing[J]. Nature Reviews Physics, 5, 717-734(2023).

[133] Anderson M, Ma S Y, Wang T et al. Optical transformers[EB/OL]. https:∥arxiv.org/abs/2302.10360

[134] Wu B, Zhou H J, Cheng J W et al. Monolithically integrated asynchronous optical recurrent accelerator[J]. eLight, 5, 7(2025).

[135] Hua S Y, Divita E, Yu S S et al. An integrated large-scale photonic accelerator with ultralow latency[J]. Nature, 640, 361-367(2025).

[136] Ahmed S R, Baghdadi R, Bernadskiy M et al. Universal photonic artificial intelligence acceleration[J]. Nature, 640, 368-374(2025).

[137] Zhou W, Farmakidis N, Feldmann J et al. Phase-change materials for energy-efficient photonic memory and computing[J]. MRS Bulletin, 47, 502-510(2022).

[138] Yang Z Y, Li C, Ran Y Q et al. SUANPAN: scalable photonic linear vector machine[EB/OL]. https:∥arxiv.org/abs/2410.23659

[139] Zhang N, Huang Z Q, Zhang Z A et al. Advances of optical computing and optoelectronic intelligent computing[J]. Chinese Journal of Lasers, 51, 1800001(2024).

[140] Liu Z X, Zeng C, Xia J S. Research progress on high-linearity electro-optical modulators[J]. Chinese Journal of Lasers, 49, 1206001(2022).

[141] Yu F H, Di K J, Chen W J et al. Time-wavelength multiplexed photonic neural network accelerator for distributed acoustic sensing systems[J]. Advanced Photonics, 7, 026008(2025).

[142] Zhang J L, Wu B, Zhang S J et al. Highly integrated all-optical nonlinear deep neural network for multi-thread processing[J]. Advanced Photonics, 7, 046003(2025).

Tools

Get Citation

Copy Citation Text

Xiang Zhang, Hao Zhang, Wenlin Cui, Anle Shen, Zhijun Liang, Chong Li, Tao Fang, Jingwei Li, Jiayi Ouyang, Xinxiang Niu, Qinghai Guo, Xiaowen Dong. Research Progress and Perspectives in Optoelectronic Computing Systems (Invited)[J]. Acta Optica Sinica, 2025, 45(17): 1720006

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites