{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T17:03:08Z","timestamp":1778605388895,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T00:00:00Z","timestamp":1629676800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"DARPA","award":["FastNICs"],"award-info":[{"award-number":["FastNICs"]}]},{"name":"ARPA-E","award":["ENLITENED PINE"],"award-info":[{"award-number":["ENLITENED PINE"]}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["ASCENT-2023468"],"award-info":[{"award-number":["ASCENT-2023468"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,8,23]]},"DOI":"10.1145\/3473938.3474508","type":"proceedings-article","created":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T13:03:56Z","timestamp":1629205436000},"page":"18-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["IOI"],"prefix":"10.1145","author":[{"given":"Zhizhen","family":"Zhong","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manya","family":"Ghobadi","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Sludds","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryan","family":"Hamerly","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liane","family":"Bernstein","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dirk","family":"Englund","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,8,23]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Juniper MX Series Universal Routing Platforms. https:\/\/www.juniper.net\/us\/en\/products-services\/routing\/mx-series\/datasheets\/1000597.page.  Juniper MX Series Universal Routing Platforms. https:\/\/www.juniper.net\/us\/en\/products-services\/routing\/mx-series\/datasheets\/1000597.page."},{"key":"e_1_3_2_1_2_1","first-page":"1","volume-title":"2020 IEEE Hot Chips 32 Symposium (HCS)","author":"Agrawal Anurag","year":"2020","unstructured":"Anurag Agrawal and Changhoon Kim . Intel tofino2-a 12.9 tbps p4-programmable ethernet switch. In 2020 IEEE Hot Chips 32 Symposium (HCS) , pages 1 -- 32 . IEEE Computer Society , 2020 . Anurag Agrawal and Changhoon Kim. Intel tofino2-a 12.9 tbps p4-programmable ethernet switch. In 2020 IEEE Hot Chips 32 Symposium (HCS), pages 1--32. IEEE Computer Society, 2020."},{"key":"e_1_3_2_1_3_1","volume-title":"Chauffeurnet: Learning to drive by imitating the best and synthesizing the worst. arXiv preprint arXiv:1812.03079","author":"Bansal Mayank","year":"2018","unstructured":"Mayank Bansal , Alex Krizhevsky , and Abhijit Ogale . Chauffeurnet: Learning to drive by imitating the best and synthesizing the worst. arXiv preprint arXiv:1812.03079 , 2018 . Mayank Bansal, Alex Krizhevsky, and Abhijit Ogale. Chauffeurnet: Learning to drive by imitating the best and synthesizing the worst. arXiv preprint arXiv:1812.03079, 2018."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422604.3425928"},{"key":"e_1_3_2_1_6_1","volume-title":"NetCast Note-15","author":"Hamerly Ryan","year":"2020","unstructured":"Ryan Hamerly . Netcast:Low-power edge computing with optical neural networks via wdm weight broadcasting . NetCast Note-15 , 2020 . Ryan Hamerly. Netcast:Low-power edge computing with optical neural networks via wdm weight broadcasting. NetCast Note-15, 2020."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.9.021032"},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Learning Representations","author":"Han Song","year":"2015","unstructured":"Song Han , Huizi Mao , and William J Dally . Deep compression : Compressing deep neural networks with pruning, trained quantization and huffman coding . International Conference on Learning Representations , 2015 . Song Han, Huizi Mao, and William J Dally. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. International Conference on Learning Representations, 2015."},{"key":"e_1_3_2_1_9_1","volume-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and &lt","author":"Iandola Forrest N","year":"2016","unstructured":"Forrest N Iandola , Song Han , Matthew W Moskewicz , Khalid Ashraf , William J Dally , and Kurt Keutzer . Squeezenet: Alexnet-level accuracy with 50x fewer parameters and &lt ; 0.5 mb model size. arXiv preprint arXiv:1602.07360, 2016 . Forrest N Iandola, Song Han, Matthew W Moskewicz, Khalid Ashraf, William J Dally, and Kurt Keutzer. Squeezenet: Alexnet-level accuracy with 50x fewer parameters and < 0.5 mb model size. arXiv preprint arXiv:1602.07360, 2016."},{"key":"e_1_3_2_1_10_1","volume-title":"Amazon Science","author":"Kim Young-Bum","year":"2018","unstructured":"Young-Bum Kim . The scalable neural architecture behind alexa's ability to select skills . Amazon Science , 2018 . https:\/\/www.amazon.science\/blog\/the-scalable-neural-architecture-behind-alexas-ability-to-select-skills. Young-Bum Kim. The scalable neural architecture behind alexa's ability to select skills. Amazon Science, 2018. https:\/\/www.amazon.science\/blog\/the-scalable-neural-architecture-behind-alexas-ability-to-select-skills."},{"key":"e_1_3_2_1_11_1","volume-title":"Facebook AI","author":"Kim Young-Bum","year":"2019","unstructured":"Young-Bum Kim . Powered by ai: Oculus insight . Facebook AI , 2019 . https:\/\/ai.facebook.com\/blog\/powered-by-ai-oculus-insight\/. Young-Bum Kim. Powered by ai: Oculus insight. Facebook AI, 2019. https:\/\/ai.facebook.com\/blog\/powered-by-ai-oculus-insight\/."},{"key":"e_1_3_2_1_12_1","unstructured":"Maxim Naumov Dheevatsa Mudigere Hao-Jun Michael Shi Jianyu Huang Narayanan Sundaraman Jongsoo Park Xiaodong Wang Udit Gupta Carole Jean Wu Alisson G Azzolini et al. Deep learning recommendation model for personalization and recommendation systems. arXiv preprint arXiv:1906.00091 2019.  Maxim Naumov Dheevatsa Mudigere Hao-Jun Michael Shi Jianyu Huang Narayanan Sundaraman Jongsoo Park Xiaodong Wang Udit Gupta Carole Jean Wu Alisson G Azzolini et al. Deep learning recommendation model for personalization and recommendation systems. arXiv preprint arXiv:1906.00091 2019."},{"key":"e_1_3_2_1_13_1","unstructured":"Kartik Pandit Bianny Bian Vishwa M Prasad Atul Kwatra Patrick Lu Mike Riess Wayne Willey Huawei Xie and Gen Xu. Modeling the impact of cpu properties to optimize and predict packet-processing performance. Intel Case Study. https:\/\/www.intel.com\/content\/dam\/www\/public\/us\/en\/documents\/case-studies\/att-cpu-impact-on-packet-processing-perfomance-paper.pdf.  Kartik Pandit Bianny Bian Vishwa M Prasad Atul Kwatra Patrick Lu Mike Riess Wayne Willey Huawei Xie and Gen Xu. Modeling the impact of cpu properties to optimize and predict packet-processing performance. Intel Case Study. https:\/\/www.intel.com\/content\/dam\/www\/public\/us\/en\/documents\/case-studies\/att-cpu-impact-on-packet-processing-perfomance-paper.pdf."},{"key":"e_1_3_2_1_14_1","volume-title":"Apple Machine Learning","author":"Team Siri","year":"2017","unstructured":"Siri Team . Hey siri : An on-device dnn-powered voice trigger for apple's personal assistant . Apple Machine Learning , 2017 . https:\/\/machinelearning.apple.com\/research\/hey-siri. Siri Team. Hey siri: An on-device dnn-powered voice trigger for apple's personal assistant. Apple Machine Learning, 2017. https:\/\/machinelearning.apple.com\/research\/hey-siri."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2973-6"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00048"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3365609.3365864"}],"event":{"name":"SIGCOMM '21: ACM SIGCOMM 2021 Conference","location":"Virtual Event USA","acronym":"SIGCOMM '21","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the ACM SIGCOMM 2021 Workshop on Optical Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3473938.3474508","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3473938.3474508","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3473938.3474508","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:46Z","timestamp":1750193326000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3473938.3474508"}},"subtitle":["In-network Optical Inference"],"short-title":[],"issued":{"date-parts":[[2021,8,23]]},"references-count":17,"alternative-id":["10.1145\/3473938.3474508","10.1145\/3473938"],"URL":"https:\/\/doi.org\/10.1145\/3473938.3474508","relation":{},"subject":[],"published":{"date-parts":[[2021,8,23]]},"assertion":[{"value":"2021-08-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}