{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T19:27:33Z","timestamp":1786476453577,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":92,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T00:00:00Z","timestamp":1786406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62472009"],"award-info":[{"award-number":["62472009"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,17]]},"DOI":"10.1145\/3789240.3829196","type":"proceedings-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:33:22Z","timestamp":1786473202000},"page":"368-395","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["EPIC: Abstraction and Polymorphism of In-Network Collectives on Ethernet"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5427-4829","authenticated-orcid":false,"given":"Yitao","family":"Yuan","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8492-7983","authenticated-orcid":false,"given":"Jianglong","family":"Nie","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8300-9921","authenticated-orcid":false,"given":"Tianyu","family":"Bai","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4486-3177","authenticated-orcid":false,"given":"Ruizhe","family":"Zhou","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3203-9868","authenticated-orcid":false,"given":"Siyuan","family":"Cao","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6728-6939","authenticated-orcid":false,"given":"Xujie","family":"Fan","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5765-3825","authenticated-orcid":false,"given":"Yuchen","family":"Xu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9981-8616","authenticated-orcid":false,"given":"Junkai","family":"Chen","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9540-1940","authenticated-orcid":false,"given":"Chenqi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6108-2046","authenticated-orcid":false,"given":"Nengyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9757-1031","authenticated-orcid":false,"given":"Shaoke","family":"Fang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1328-9424","authenticated-orcid":false,"given":"Jiangyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7543-7076","authenticated-orcid":false,"given":"Yuanfeng","family":"Chen","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2496-6782","authenticated-orcid":false,"given":"Jiaqi","family":"Sun","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4274-7671","authenticated-orcid":false,"given":"Zhan","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7770-803X","authenticated-orcid":false,"given":"Xiaohua","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0135-8915","authenticated-orcid":false,"given":"Yuchao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0667-6813","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8041-9957","authenticated-orcid":false,"given":"Xiangrui","family":"Yang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9301-5533","authenticated-orcid":false,"given":"Jing","family":"Lin","sequence":"additional","affiliation":[{"name":"Infrawaves, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1487-2419","authenticated-orcid":false,"given":"Xiaohe","family":"Hu","sequence":"additional","affiliation":[{"name":"Infrawaves, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7024-4659","authenticated-orcid":false,"given":"Yang","family":"Li","sequence":"additional","affiliation":[{"name":"Lenovo Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2543-3277","authenticated-orcid":false,"given":"Chao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Lenovo Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9438-9181","authenticated-orcid":false,"given":"Limin","family":"Xiao","sequence":"additional","affiliation":[{"name":"Lenovo Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4529-1679","authenticated-orcid":false,"given":"Weifeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Lenovo Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2598-2012","authenticated-orcid":false,"given":"Junjie","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Centec Communications Co., Ltd., Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2021-1522","authenticated-orcid":false,"given":"Wei","family":"Cheng","sequence":"additional","affiliation":[{"name":"Beijing Centec Communications Co., Ltd., Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9212-5424","authenticated-orcid":false,"given":"Yazhu","family":"Lan","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0939-8943","authenticated-orcid":false,"given":"Jianbo","family":"Dong","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1213-0554","authenticated-orcid":false,"given":"Binzhang","family":"Fu","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1357-3137","authenticated-orcid":false,"given":"Wenfei","family":"Wu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"https:\/\/github.com\/ROCm\/rccl","author":"AMD.","year":"2024","unstructured":"AMD. 2024. RCCL. (2024). https:\/\/github.com\/ROCm\/rccl."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519584"},{"key":"e_1_3_2_1_3_1","unstructured":"Tianyu Bai Ying Zhang Xiaoxi Zhang and Wenfei Wu. 2026. Verifying In-Network Computing Systems for Design Risks. (2026). arXiv:cs.DC\/2604.10186 https:\/\/arxiv.org\/abs\/2604.10186"},{"key":"e_1_3_2_1_4_1","volume-title":"Empowering Azure Storage with RDMA. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Bai Wei","year":"2023","unstructured":"Wei Bai, Shanim Sainul Abdeen, Ankit Agrawal, Krishan Kumar Attre, Paramvir Bahl, Ameya Bhagat, Gowri Bhaskara, Tanya Brokhman, Lei Cao, Ahmad Cheema, Rebecca Chow, Jeff Cohen, Mahmoud Elhaddad, Vivek Ette, Igal Figlin, Daniel Firestone, Mathew George, Ilya German, Lakhmeet Ghai, Eric Green, Albert Greenberg, Manish Gupta, Randy Haagens, Matthew Hendel, Ridwan Howlader, Neetha John, Julia Johnstone, Tom Jolly, Greg Kramer, David Kruse, Ankit Kumar, Erica Lan, Ivan Lee, Avi Levy, Marina Lipshteyn, Xin Liu, Chen Liu, Guohan Lu, Yuemin Lu, Xiakun Lu, Vadim Makhervaks, Ulad Malashanka, David A. Maltz, Ilias Marinos, Rohan Mehta, Sharda Murthi, Anup Namdhari, Aaron Ogus, Jitendra Padhye, Madhav Pandya, Douglas Phillips, Adrian Power, Suraj Puri, Shachar Raindel, Jordan Rhee, Anthony Russo, Maneesh Sah, Ali Sheriff, Chris Sparacino, Ashutosh Srivastava, Weixiang Sun, Nick Swanson, Fuhou Tian, Lukasz Tomczyk, Vamsi Vadlamuri, Alec Wolman, Ying Xie, Joyce Yom, Lihua Yuan, Yanzhao Zhang, and Brian Zill. 2023. Empowering Azure Storage with RDMA. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). USENIX Association, Boston, MA, 49\u201367. https:\/\/www.usenix.org\/conference\/nsdi23\/presentation\/bai"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446760"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2656877.2656890"},{"key":"e_1_3_2_1_7_1","unstructured":"Broadcom Inc. 2026. StrataXGS Tomahawk 5 Series: 51.2 Tb\/s Ethernet Switch ASIC Family. https:\/\/www.broadcom.com\/products\/ethernet-connectivity\/switching\/strataxgs\/bcm78920-series. (2026). Accessed: 2026-02-06."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672239"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476178"},{"key":"e_1_3_2_1_10_1","unstructured":"DeepSeek-AI Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan Damai Dai Daya Guo Dejian Yang Deli Chen Dongjie Ji Erhang Li Fangyun Lin Fucong Dai Fuli Luo Guangbo Hao Guanting Chen Guowei Li H. Zhang Han Bao Hanwei Xu Haocheng Wang Haowei Zhang Honghui Ding Huajian Xin Huazuo Gao Hui Li Hui Qu J. L. Cai Jian Liang Jianzhong Guo Jiaqi Ni Jiashi Li Jiawei Wang Jin Chen Jingchang Chen Jingyang Yuan Junjie Qiu Junlong Li Junxiao Song Kai Dong Kai Hu Kaige Gao Kang Guan Kexin Huang Kuai Yu Lean Wang Lecong Zhang Lei Xu Leyi Xia Liang Zhao Litong Wang Liyue Zhang Meng Li Miaojun Wang Mingchuan Zhang Minghua Zhang Minghui Tang Mingming Li Ning Tian Panpan Huang Peiyi Wang Peng Zhang Qiancheng Wang Qihao Zhu Qinyu Chen Qiushi Du R. J. Chen R. L. Jin Ruiqi Ge Ruisong Zhang Ruizhe Pan Runji Wang Runxin Xu Ruoyu Zhang Ruyi Chen S. S. Li Shanghao Lu Shangyan Zhou Shanhuang Chen Shaoqing Wu Shengfeng Ye Shengfeng Ye Shirong Ma Shiyu Wang Shuang Zhou Shuiping Yu Shunfeng Zhou Shuting Pan T. Wang Tao Yun Tian Pei Tianyu Sun W. L. Xiao Wangding Zeng Wanjia Zhao Wei An Wen Liu Wenfeng Liang Wenjun Gao Wenqin Yu Wentao Zhang X. Q. Li Xiangyue Jin Xianzu Wang Xiao Bi Xiaodong Liu Xiaohan Wang Xiaojin Shen Xiaokang Chen Xiaokang Zhang Xiaosha Chen Xiaotao Nie Xiaowen Sun Xiaoxiang Wang Xin Cheng Xin Liu Xin Xie Xingchao Liu Xingkai Yu Xinnan Song Xinxia Shan Xinyi Zhou Xinyu Yang Xinyuan Li Xuecheng Su Xuheng Lin Y. K. Li Y. Q. Wang Y. X. Wei Y. X. Zhu Yang Zhang Yanhong Xu Yanhong Xu Yanping Huang Yao Li Yao Zhao Yaofeng Sun Yaohui Li Yaohui Wang Yi Yu Yi Zheng Yichao Zhang Yifan Shi Yiliang Xiong Ying He Ying Tang Yishi Piao Yisong Wang Yixuan Tan Yiyang Ma Yiyuan Liu Yongqiang Guo Yu Wu Yuan Ou Yuchen Zhu Yuduan Wang Yue Gong Yuheng Zou Yujia He Yukun Zha Yunfan Xiong Yunxian Ma Yuting Yan Yuxiang Luo Yuxiang You Yuxuan Liu Yuyang Zhou Z. F. Wu Z. Z. Ren Zehui Ren Zhangli Sha Zhe Fu Zhean Xu Zhen Huang Zhen Zhang Zhenda Xie Zhengyan Zhang Zhewen Hao Zhibin Gou Zhicheng Ma Zhigang Yan Zhihong Shao Zhipeng Xu Zhiyu Wu Zhongyu Zhang Zhuoshu Li Zihui Gu Zijia Zhu Zijun Liu Zilin Li Ziwei Xie Ziyang Song Ziyi Gao and Zizheng Pan. 2025. DeepSeek-V3 Technical Report. (2025). arXiv:cs.CL\/2412.19437 https:\/\/arxiv.org\/abs\/2412.19437"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00079"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1629575.1629578"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Jianbo Dong Bin Luo Jun Zhang Pengcheng Zhang Fei Feng Yikai Zhu Ang Liu Zian Chen Yi Shi Hairong Jiao Gang Lu Yu Guan Ennan Zhai Wencong Xiao Hanyu Zhao Man Yuan Siran Yang Xiang Li Jiamang Wang Rui Men Jianwei Zhang Chang Zhou Dennis Cai Yuan Xie and Binzhang Fu. 2025. Enhancing Large-Scale AI Training Efficiency: The C4 Solution for Real-Time Anomaly Detection and Communication Optimization. (2025). arXiv:cs.DC\/2406.04594 https:\/\/arxiv.org\/abs\/2406.04594","DOI":"10.1109\/HPCA61900.2025.00095"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3091475"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044657"},{"key":"e_1_3_2_1_16_1","first-page":"249","article-title":"A Modular Network Layer for Sensornets","volume":"6","author":"Ee Cheng Tien","year":"2006","unstructured":"Cheng Tien Ee, Rodrigo Fonseca, Sukun Kim, Daekyeong Moon, Arsalan Tavakoli, David E Culler, Scott Shenker, and Ion Stoica. 2006. A Modular Network Layer for Sensornets.. In OSDI, Vol. 6. 249\u2013262.","journal-title":"OSDI"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3244794"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 11th European PVM\/MPI Users' Group Meeting","author":"Gabriel Edgar","unstructured":"Edgar Gabriel, Graham E. Fagg, George Bosilca, Thara Angskun, Jack J. Dongarra, Jeffrey M. Squyres, Vishal Sahay, Prabhanjan Kambadur, Brian Barrett, Andrew Lumsdaine, Ralph H. Castain, David J. Daniel, Richard L. Graham, and Timothy S. Woodall. 2004. Open MPI: Goals, Concept, and Design of a Next Generation MPI Implementation. In Proceedings of the 11th European PVM\/MPI Users' Group Meeting. Budapest, Hungary."},{"key":"e_1_3_2_1_19_1","volume-title":"2018 USENIX Annual Technical Conference (USENIX ATC 18)","author":"Gallo Massimo","year":"2018","unstructured":"Massimo Gallo and Rafael Laufer. 2018. ClickNF: a Modular Stack for Custom Network Functions. In 2018 USENIX Annual Technical Conference (USENIX ATC 18). 745\u2013757."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672233"},{"key":"e_1_3_2_1_21_1","volume-title":"When Cloud Storage Meets RDMA. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Gao Yixiao","year":"2021","unstructured":"Yixiao Gao, Qiang Li, Lingbo Tang, Yongqing Xi, Pengcheng Zhang, Wenwen Peng, Bo Li, Yaohui Wu, Shaozong Liu, Lei Yan, Fei Feng, Yan Zhuang, Fan Liu, Pan Liu, Xingkui Liu, Zhongjie Wu, Junping Wu, Zheng Cao, Chen Tian, Jinbo Wu, Jiaji Zhu, Haiyong Wang, Dennis Cai, and Jiesheng Wu. 2021. When Cloud Storage Meets RDMA. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21). USENIX Association, 519\u2013533. https:\/\/www.usenix.org\/conference\/nsdi21\/presentation\/gao"},{"key":"e_1_3_2_1_22_1","first-page":"829","article-title":"In-network aggregation for shared machine learning clusters","volume":"3","author":"Gebara Nadeen","year":"2021","unstructured":"Nadeen Gebara, Manya Ghobadi, and Paolo Costa. 2021. In-network aggregation for shared machine learning clusters. Proceedings of Machine Learning and Systems 3 (2021), 829\u2013844.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMHPC.2016.006"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50743-5_3"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575708"},{"key":"e_1_3_2_1_26_1","volume-title":"Elliott Slaughter, Pinku Surana, Wen-mei Hwu, William Gropp, and Alex Aiken.","author":"Hidayetoglu Mert","year":"2024","unstructured":"Mert Hidayetoglu, Simon Garcia de Gonzalo, Elliott Slaughter, Pinku Surana, Wen-mei Hwu, William Gropp, and Alex Aiken. 2024. HiCCL: A Hierarchical Collective Communication Library. arXiv preprint arXiv:2408.05962 (2024)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3623490"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2025.3616048"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1362622.1362692"},{"key":"e_1_3_2_1_30_1","volume-title":"Energy, memory, and runtime tradeoffs for implementing collective communication operations. Supercomputing frontiers and innovations 1, 2","author":"Hoefler Torsten","year":"2014","unstructured":"Torsten Hoefler and Dmitry Moor. 2014. Energy, memory, and runtime tradeoffs for implementing collective communication operations. Supercomputing frontiers and innovations 1, 2 (2014), 58\u201375."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP59255.2023.10355619"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731105"},{"key":"e_1_3_2_1_33_1","volume-title":"d.]. Supplement to InfiniBandTM Architecture Specification","author":"InfiniBand Trade Association","unstructured":"InfiniBand Trade Association. [n. d.]. Supplement to InfiniBandTM Architecture Specification Volume 1 Release 1.2.1: Annex A17: RoCEv2. Technical Specification Supplement Release 1.2.1, Annex A17. InfiniBand Trade Association. Proprietary document; available via InfiniBand Trade Association membership."},{"key":"e_1_3_2_1_34_1","volume-title":"https:\/\/www.intel.com\/content\/www\/us\/en\/products\/details\/network-io\/intelligent-fabric-processors\/tofino-2.html","author":"Intel Tofino","year":"2024","unstructured":"Intel. 2024. Intel Tofino 2. (2024). https:\/\/www.intel.com\/content\/www\/us\/en\/products\/details\/network-io\/intelligent-fabric-processors\/tofino-2.html"},{"key":"e_1_3_2_1_35_1","unstructured":"Intel. 2024. oneAPI Collective Communications Library (oneCCL). (2024). https:\/\/github.com\/oneapi-src\/oneCCL."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00109"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651362"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00085"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/354871.354874"},{"key":"e_1_3_2_1_41_1","volume-title":"Specifying systems: The TLA+ language and tools for hardware and software engineers","author":"Lamport Leslie","unstructured":"Leslie Lamport. 2002. Specifying systems: The TLA+ language and tools for hardware and software engineers. Addison-Wesley."},{"key":"e_1_3_2_1_42_1","volume-title":"Continuum: An Interruption-Resilient Runtime for ML Training. In OSDI.","author":"Lao ChonLam","year":"2026","unstructured":"ChonLam Lao, Jiaqi Gao, Jiamin Cao, Zhipeng Zhang, Pengcheng Zhang, Jiangfei Duan, Minlan Yu, Aditya Akella, Zhilong Zheng, Yu Guan, Yichi Xu, Yong Li, Ennan Zhai, Dennis Cai, Zhengping Qian, and Jingren Zhou. 2026. Continuum: An Interruption-Resilient Runtime for ML Training. In OSDI."},{"key":"e_1_3_2_1_43_1","volume-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Lao ChonLam","year":"2021","unstructured":"ChonLam Lao, Yanfang Le, Kshiteej Mahajan, Yixi Chen, Wenfei Wu, Aditya Akella, and Michael Swift. 2021. ATP: In-network aggregation for multi-tenant learning. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21). 741\u2013761."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3663408.3663409"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750480"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00074"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322259"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3587436"},{"key":"e_1_3_2_1_49_1","volume-title":"PA-ATP: Progress-Aware Transmission Protocol for In-Network Aggregation. In 2023 IEEE 31st International Conference on Network Protocols (ICNP). IEEE, 1\u201311","author":"Li Zhaoyi","year":"2023","unstructured":"Zhaoyi Li, Jiawei Huang, Tao Zhang, Shengwen Zhou, Qile Wang, Yijun Li, Jingling Liu, Wanchun Jiang, and Jianxin Wang. 2023. PA-ATP: Progress-Aware Transmission Protocol for In-Network Aggregation. In 2023 IEEE 31st International Conference on Network Protocols (ICNP). IEEE, 1\u201311."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672228"},{"key":"e_1_3_2_1_51_1","unstructured":"Linux man-pages project. [n. d.]. rxe(7): Software RDMA over Ethernet (RoCE) driver. ([n. d.]). https:\/\/man7.org\/linux\/man-pages\/man7\/rxe.7.html Documents Linux kernel module rdma_rxe (Soft-RoCE\/RXE)."},{"key":"e_1_3_2_1_52_1","volume-title":"libibverbs: Userspace InfiniBand Verbs Library. https:\/\/github.com\/linux-rdma\/rdma-core\/tree\/master\/libibverbs. (2024). Part of rdma-core","author":"Community Linux RDMA","unstructured":"Linux RDMA Community. 2024. libibverbs: Userspace InfiniBand Verbs Library. https:\/\/github.com\/linux-rdma\/rdma-core\/tree\/master\/libibverbs. (2024). Part of rdma-core; provides the ibv_* API for RDMA device management, QP\/CQ\/MR operations, and data transfer."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582037"},{"key":"e_1_3_2_1_54_1","volume-title":"How to Train a Model on a Cheap Cluster with Low Cost using Block Coordinate Descent. arXiv e-prints","author":"Liu Zeyu","year":"2025","unstructured":"Zeyu Liu, Yunquan Zhang, Boyang Zhang, Guoyong Jiang, and Daning Cheng. 2025. How to Train a Model on a Cheap Cluster with Low Cost using Block Coordinate Descent. arXiv e-prints (2025), arXiv-2506."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750521"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2927069"},{"key":"e_1_3_2_1_57_1","volume-title":"https:\/\/github.com\/microsoft\/msccl","author":"MSCCL.","year":"2023","unstructured":"Microsoft. 2023. MSCCL. (2023). https:\/\/github.com\/microsoft\/msccl."},{"key":"e_1_3_2_1_58_1","unstructured":"nsnam. 2024. ns-3 Network Simulator. https:\/\/www.nsnam.org. (2024). Version 3.42."},{"key":"e_1_3_2_1_59_1","volume-title":"https:\/\/github.com\/NVIDIA\/nccl","author":"NVIDIA.","year":"2024","unstructured":"NVIDIA. 2024. NCCL. (2024). https:\/\/github.com\/NVIDIA\/nccl."},{"key":"e_1_3_2_1_60_1","volume-title":"d.]. NVIDIA NVLink High-Speed Interconnect: Application Performance. Whitepaper","author":"NVIDIACorporation","unstructured":"NVIDIACorporation. [n. d.]. NVIDIA NVLink High-Speed Interconnect: Application Performance. Whitepaper. NVIDIA Corporation."},{"key":"e_1_3_2_1_61_1","unstructured":"OMNeT++ Community. 2024. OMNeT++ Discrete Event Simulator. https:\/\/omnetpp.org. (2024). Version 6.2."},{"key":"e_1_3_2_1_62_1","unstructured":"OpenInfra Foundation. [n. d.]. OpenStack: Open source cloud computing infrastructure. ([n. d.]). https:\/\/www.openstack.org\/"},{"key":"e_1_3_2_1_63_1","volume-title":"12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)","author":"Panda Aurojit","year":"2016","unstructured":"Aurojit Panda, Sangjin Han, Keon Jang, Melvin Walls, Sylvia Ratnasamy, and Scott Shenker. 2016. NetBricks: Taking the V out of NFV. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16). 203\u2013216."},{"key":"e_1_3_2_1_64_1","volume-title":"12th USENIX Symposium on Networked Systems Design and Implementation (NSDI '15)","author":"Pfaff Ben","year":"2015","unstructured":"Ben Pfaff, Justin Pettit, Teemu Koponen, Ethan J. Jackson, Andy Zhou, Jarno Rajahalme, Jesse Gross, Alex Wang, Jonathan Stringer, Pravin Shelar, Keith Amidon, and Martin Casado. 2015. The Design and Implementation of Open vSwitch. In 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI '15). USENIX Association, 117\u2013130. https:\/\/www.usenix.org\/system\/files\/conference\/nsdi15\/nsdi15-paper-pfaff.pdf"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750527"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672265"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3364173"},{"key":"e_1_3_2_1_69_1","volume-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Sapio Amedeo","year":"2021","unstructured":"Amedeo Sapio, Marco Canini, Chen-Yu Ho, Jacob Nelson, Panos Kalnis, Changhoon Kim, Arvind Krishnamurthy, Masoud Moshref, Dan Ports, and Peter Richt\u00e1rik. 2021. Scaling distributed machine learning with In-Network aggregation. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21). 785\u2013808."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485983.3494853"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796980"},{"key":"e_1_3_2_1_72_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Shah Aashaka","year":"2023","unstructured":"Aashaka Shah, Vijay Chidambaram, Meghan Cowan, Saeed Maleki, Madan Musuvathi, Todd Mytkowicz, Jacob Nelson, Olli Saarikivi, and Rachee Singh. 2023. TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 593\u2013612."},{"key":"e_1_3_2_1_73_1","volume-title":"Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces.","author":"Sridharan Srinivas","year":"2023","unstructured":"Srinivas Sridharan, Taekyung Heo, Louis Feng, Zhaodong Wang, Matt Bergeron, Wenyin Fu, Shengbao Zheng, Brian Coutinho, Saeed Rashidi, Changhai Man, and Tushar Krishna. 2023. Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces. (2023). arXiv:cs.LG\/2305.14516 https:\/\/arxiv.org\/abs\/2305.14516"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3767295.3769344"},{"key":"e_1_3_2_1_75_1","unstructured":"The Tcpdump Group. [n. d.]. libpcap: Portable packet capture library. ([n. d.]). https:\/\/www.tcpdump.org\/"},{"key":"e_1_3_2_1_76_1","unstructured":"UAlink Consortium. 2024. UAlink Consortium. Online Consortium Website. (2024). https:\/\/ualinkconsortium.org\/"},{"key":"e_1_3_2_1_77_1","volume-title":"Ultra Ethernet Specification Update","author":"Ultra Ethernet Consortium","year":"2024","unstructured":"Ultra Ethernet Consortium. 2024. Ultra Ethernet Specification Update. Ultra Ethernet Consortium Blog. (29 August 2024). https:\/\/ultraethernet.org\/ultra-ethernet-specification-update\/ Accessed: 2026-02-06."},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044670"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577193.3593711"},{"key":"e_1_3_2_1_80_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Wang Weiyang","year":"2023","unstructured":"Weiyang Wang, Moein Khazraee, Zhizhen Zhong, Manya Ghobadi, Zhihao Jia, Dheevatsa Mudigere, Ying Zhang, and Anthony Kewitsch. 2023. TopoOpt: Co-optimizing network topology and parallelization strategy for distributed training jobs. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 739\u2013767."},{"key":"e_1_3_2_1_81_1","volume-title":"22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25)","author":"Wang Xizheng","unstructured":"Xizheng Wang, Qingxu Li, Yichi Xu, Gang Lu, Dan Li, Li Chen, Heyang Zhou, Linkang Zheng, Sen Zhang, Yikai Zhu, Yang Liu, Pengcheng Zhang, Kun Qian, Kunling He, Jiaqi Gao, Ennan Zhai, Dennis Cai, and Binzhang Fu. 2025. SimAI: Unifying Architecture Design and Performance Tuning for Large-Scale Large Language Model Training with Scalability and Precision. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25). USENIX Association, Philadelphia, PA, 541\u2013558. https:\/\/www.usenix.org\/conference\/nsdi25\/presentation\/wang-xizheng-simai"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672252"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS60910.2024.00070"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604835"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/3767295.3769330"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544262"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10228956"},{"key":"e_1_3_2_1_88_1","volume-title":"20th USENIX symposium on networked systems design and implementation (NSDI 23)","author":"Zhao Bohan","year":"2023","unstructured":"Bohan Zhao, Wenfei Wu, and Wei Xu. 2023. NetRPC: Enabling In-Network computation in remote procedure calls. In 20th USENIX symposium on networked systems design and implementation (NSDI 23). 199\u2013217."},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1145\/3617232.3624863"},{"key":"e_1_3_2_1_90_1","unstructured":"Yanli Zhao Andrew Gu Rohan Varma Liang Luo Chien-Chin Huang Min Xu Less Wright Hamid Shojanazeri Myle Ott Sam Shleifer Alban Desmaison Can Balioglu Pritam Damania Bernard Nguyen Geeta Chauhan Yuchen Hao Ajit Mathews and Shen Li. 2023. PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel. (2023). arXiv:cs.DC\/2304.11277 https:\/\/arxiv.org\/abs\/2304.11277"},{"key":"e_1_3_2_1_91_1","volume-title":"22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25)","author":"Zheng Hao","year":"2025","unstructured":"Hao Zheng, Xin Yan, Wenbo Li, Jiaqi Zheng, Xiaoliang Wang, Qingqing Zhao, Luyou He, Xiaofei Lai, Feng Gao, Fuguang Huang, Wanchun Dou, Guihai Chen, and Chen Tian. 2025. When P4 Meets Run-to-completion Architecture. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25). USENIX Association, Philadelphia, PA, 1487\u20131505. https:\/\/www.usenix.org\/conference\/nsdi25\/presentation\/zheng-hao"},{"key":"e_1_3_2_1_92_1","volume-title":"DINA: Toward Determined In-Network Aggregation for Distributed Machine Learning","author":"Zhu Haowen","year":"2025","unstructured":"Haowen Zhu, Zehua Guo, and Minghao Ye. 2025. DINA: Toward Determined In-Network Aggregation for Distributed Machine Learning. IEEE Transactions on Networking (2025)."}],"event":{"name":"SIGCOMM '26: ACM SIGCOMM 2026 Conference","location":"Colorado Convention Center Denver CO USA","acronym":"SIGCOMM '26","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the ACM SIGCOMM 2026 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3789240.3829196","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:33:56Z","timestamp":1786473236000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3789240.3829196"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":92,"alternative-id":["10.1145\/3789240.3829196","10.1145\/3789240"],"URL":"https:\/\/doi.org\/10.1145\/3789240.3829196","relation":{},"subject":[],"published":{"date-parts":[[2026,8,11]]},"assertion":[{"value":"2026-08-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}