{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:40:08Z","timestamp":1750297208954,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,27]]},"DOI":"10.1145\/3676536.3697132","type":"proceedings-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T13:26:26Z","timestamp":1744205186000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Co-designing 2.5D Silicon Photonic Accelerators for Distributed Transformer at the Edge"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3802-381X","authenticated-orcid":false,"given":"Dharanidhar","family":"Dang","sequence":"first","affiliation":[{"name":"Electrical & Computer Engineering, University of Texas at San Antonio, San Antonio, TX, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8044-7413","authenticated-orcid":false,"given":"Priyabrata","family":"Dash","sequence":"additional","affiliation":[{"name":"Department of ECE, University of Texas at San Antonio, San Antonio, Texas, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2916-2727","authenticated-orcid":false,"given":"Luqi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of ECE, Purdue University, West Lafayette, IN, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3393-9252","authenticated-orcid":false,"given":"Haitong","family":"Li","sequence":"additional","affiliation":[{"name":"Department of ECE, Purdue University, West Lafayette, IN, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,4,9]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro Greg S. Corrado Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Ian Goodfellow Andrew Harp Geoffrey Irving Michael Isard Yangqing Jia Rafal Jozefowicz Lukasz Kaiser Manjunath Kudlur Josh Levenberg Dandelion Man\u00e9 Rajat Monga Sherry Moore Derek Murray Chris Olah Mike Schuster Jonathon Shlens Benoit Steiner Ilya Sutskever Kunal Talwar Paul Tucker Vincent Vanhoucke Vijay Vasudevan Fernanda Vi\u00e9gas Oriol Vinyals Pete Warden Martin Wattenberg Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. https:\/\/www.tensorflow.org\/ Software available from tensorflow.org."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583781.3590259"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1364\/OE.20.002911"},{"key":"e_1_3_2_1_4_1","volume-title":"Optical Transformers. Transactions on Machine Learning Research","author":"Anderson Maxwell","year":"2024","unstructured":"Maxwell Anderson, Shi-Yuan Ma, Tianyu Wang, Logan Wright, and Peter McMahon. 2024. Optical Transformers. Transactions on Machine Learning Research (2024). https:\/\/openreview.net\/forum?id=Xxw0edFFQC"},{"key":"e_1_3_2_1_5_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E. Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E. Hinton. 2016. Layer Normalization. arXiv:1607.06450 [stat.ML] https:\/\/arxiv.org\/abs\/1607.06450"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/GROUP4.2012.6324076"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/VLSICircuits18222.2020.9162776"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1137\/1012082"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/355626.355631"},{"key":"e_1_3_2_1_10_1","first-page":"1","article-title":"Survey on Activation Functions for Optical Neural","volume":"56","author":"Destras Oc\u00e9ane","year":"2023","unstructured":"Oc\u00e9ane Destras, S\u00e9bastien Le Beux, Felipe Gohring de Magalh\u00e3es, and Gabriela Nicolescu. 2023. Survey on Activation Functions for Optical Neural Networks. Comput. Surveys 56 (2023), 1--30. https:\/\/api.semanticscholar.org\/CorpusID:259502618","journal-title":"Networks. Comput. Surveys"},{"key":"e_1_3_2_1_11_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR abs\/1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR abs\/1810.04805 (2018). arXiv:1810.04805 http:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41566-023-01313-x"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1364\/OE.18.020298"},{"key":"e_1_3_2_1_14_1","volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR abs\/2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR abs\/2010.11929 (2020). arXiv:2010.11929 https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_2_1_15_1","unstructured":"Gokul Yenduri et. al. 2023. Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies Potential Applications Emerging Challenges and Future Directions. arXiv:2305.10435 [cs.CL] https:\/\/arxiv.org\/abs\/2305.10435"},{"key":"e_1_3_2_1_16_1","volume-title":"Brown et. al","author":"Tom","year":"2020","unstructured":"Tom B. Brown et. al. 2020. Language Models are Few-Shot Learners. arXiv:2005.14165 [cs.CL] https:\/\/arxiv.org\/abs\/2005.14165"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03070-1"},{"key":"e_1_3_2_1_18_1","volume-title":"Pan","author":"Gu Jiaqi","year":"2023","unstructured":"Jiaqi Gu, Hanqing Zhu, Chenghao Feng, Zixuan Jiang, Ray T. Chen, and David Z. Pan. 2023. M3ICRO: Machine Learning-Enabled Compact Photonic Tensor Core based on PRogrammable Multi-Operand Multimode Interference. arXiv:2305.19505 [cs.ET] https:\/\/arxiv.org\/abs\/2305.19505"},{"key":"e_1_3_2_1_19_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. arXiv:1512.03385 [cs.CV] https:\/\/arxiv.org\/abs\/1512.03385"},{"key":"e_1_3_2_1_20_1","unstructured":"Dan Hendrycks and Kevin Gimpel. 2023. Gaussian Error Linear Units (GELUs). arXiv:1606.08415 [cs.LG] https:\/\/arxiv.org\/abs\/1606.08415"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1364\/OPTICA.3.000793"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1364\/OL.398234"},{"key":"e_1_3_2_1_23_1","unstructured":"Norman P. Jouppi Cliff Young and Nishant Patil et. al. 2017. In-Datacenter Performance Analysis of a Tensor Processing Unit. arXiv:1704.04760 [cs.AR] https:\/\/arxiv.org\/abs\/1704.04760"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3196924"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/lpor.201800275"},{"key":"e_1_3_2_1_27_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. https:\/\/api.semanticscholar.org\/CorpusID:160025533"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Michal Rakowski Yu Ban Peter De Heyn Nicolas Pantano Brad Snyder Sadhishkumar Balakrishnan Stefaan Van Huylenbroeck Lieve Bogaerts Caroline Demeurisse F. Inoue Kenneth June Rebibis Philip Nolmans X. Sun Pieter Bex Ashwyn Srinivasan Jeroen De Coster Sebastien Lardenois A. Miller Philippe P. Absil Peter Verheyen Dimitrios Velenis Marianna Pantouvaki and Joris Van Campenhout. 2018. Hybrid 14 nm FinFET-Silicon Photonics Technology for Low-Power Tb \/ s \/ mm 2 Optical I \/. https:\/\/api.semanticscholar.org\/CorpusID:197412240","DOI":"10.1109\/VLSIT.2018.8510668"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1364\/OE.16.015741"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","unstructured":"Linghao Song Xuehai Qian Hai Li and Yiran Chen. 2017. PipeLayer: A Pipelined ReRAM-Based Accelerator for Deep Learning. 541--552 pages. 10.1109\/HPCA.2017.55","DOI":"10.1109\/HPCA.2017.55"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2023.3282046"},{"key":"e_1_3_2_1_32_1","volume-title":"Softermax: Hardware\/Software Co-Design of an Efficient Softmax for Transformers. arXiv:2103.09301 [cs.AR] https:\/\/arxiv.org\/abs\/2103.09301","author":"Stevens Jacob R.","year":"2021","unstructured":"Jacob R. Stevens, Rangharajan Venkatesan, Steve Dai, Brucek Khailany, and Anand Raghunathan. 2021. Softermax: Hardware\/Software Co-Design of an Efficient Softmax for Transformers. arXiv:2103.09301 [cs.AR] https:\/\/arxiv.org\/abs\/2103.09301"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1364\/OE.21.030350"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1103\/physrevapplied.11.064043"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-07754-z"},{"key":"e_1_3_2_1_36_1","volume-title":"Aleksandr Biberman, and Michael Robert Watts.","author":"Timurdogan Erman","year":"2014","unstructured":"Erman Timurdogan, Cheryl M. Sorace-Agaskar, Jie Sun, Ehsan Shah Hosseini, Aleksandr Biberman, and Michael Robert Watts. 2014. An ultralow power athermal silicon modulator. Nature Communications 5 (2014). https:\/\/api.semanticscholar.org\/CorpusID:1437097"},{"key":"e_1_3_2_1_37_1","unstructured":"Hugo Touvron Matthieu Cord Matthijs Douze Francisco Massa Alexandre Sablayrolles and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers distillation through attention. arXiv:2012.12877 [cs.CV] https:\/\/arxiv.org\/abs\/2012.12877"},{"key":"e_1_3_2_1_38_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2023. Attention Is All You Need. arXiv:1706.03762 [cs.CL] https:\/\/arxiv.org\/abs\/1706.03762"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01386215"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Hao Wang Ruikang Zhang Qiang Kan Dan Lu Wei Wang and Lingjuan Zhao. 2019. High-Power Wide-Bandwidth 1.55-\u03bcm Directly Modulated DFB Lasers for Free Space Optical Communications. JTu2A.72 pages. https:\/\/opg.optica.org\/abstract.cfm?URI=CLEO_SI-2019-JTu2A.72","DOI":"10.1364\/CLEO_AT.2019.JTu2A.72"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03063-0"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2020.2973663"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","unstructured":"Hanqing Zhu Jiaqi Gu Hanrui Wang Zixuan Jiang Zhekai Zhang Rongxing Tang Chenghao Feng Song Han Ray Chen and David Pan. 2024. Lightening-Transformer: A Dynamically-Operated Optically-Interconnected Photonic Transformer Accelerator. 686--703 pages. 10.1109\/HPCA57654.2024.00059","DOI":"10.1109\/HPCA57654.2024.00059"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","unstructured":"H. Zhu J. Gu H. Wang Z. Jiang Z. Zhang R. Tang C. Feng S. Han R. T. Chen and D. Z. Pan. 2024. Lightening-Transformer: A Dynamically-Operated Optically-Interconnected Photonic Transformer Accelerator. In 2024 IEEE International Symposium on High-Performance Computer Architecture (HPCA). IEEE Computer Society Los Alamitos CA USA 686--703. 10.1109\/HPCA57654.2024.00059","DOI":"10.1109\/HPCA57654.2024.00059"}],"event":{"name":"ICCAD '24: 43rd IEEE\/ACM International Conference on Computer-Aided Design","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CAS","IEEE CEDA","IEEE EDS"],"location":"Newark Liberty International Airport Marriott New York NY USA","acronym":"ICCAD '24"},"container-title":["Proceedings of the 43rd IEEE\/ACM International Conference on Computer-Aided Design"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676536.3697132","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3676536.3697132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:45Z","timestamp":1750295925000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676536.3697132"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":43,"alternative-id":["10.1145\/3676536.3697132","10.1145\/3676536"],"URL":"https:\/\/doi.org\/10.1145\/3676536.3697132","relation":{},"subject":[],"published":{"date-parts":[[2024,10,27]]},"assertion":[{"value":"2025-04-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}