{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T19:27:39Z","timestamp":1786476459368,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":87,"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-nc-nd\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472451"],"award-info":[{"award-number":["62472451"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Innovation Program of Hunan Province","award":["2023RC3047"],"award-info":[{"award-number":["2023RC3047"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,17]]},"DOI":"10.1145\/3789240.3829164","type":"proceedings-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:33:22Z","timestamp":1786473202000},"page":"1246-1263","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Odin: Rethinking Congestion Control under All-to-All Traffic"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5067-321X","authenticated-orcid":false,"given":"Wanchun","family":"Jiang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1914-0140","authenticated-orcid":false,"given":"Yujie","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8775-6210","authenticated-orcid":false,"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7895-1775","authenticated-orcid":false,"given":"Xiao","family":"Han","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4093-3187","authenticated-orcid":false,"given":"Haoran","family":"Wei","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8353-9768","authenticated-orcid":false,"given":"Yong","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3395-3624","authenticated-orcid":false,"given":"Jianxi","family":"Ye","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9171-9990","authenticated-orcid":false,"given":"Huichen","family":"Dai","sequence":"additional","affiliation":[{"name":"ByteDance, 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","first-page":"5569","volume-title":"Proceedings of the 39th International Conference on Machine Learning, volume 162 of Proceedings of Machine Learning Research","author":"Du Nan","year":"2022","unstructured":"Nan Du, Yanping Huang, Andrew M. Dai, Simon Tong, Dmitry Lepikhin, Yuanzhong Xu, Maxim Krikun, Yanqi Zhou, Adams Wei Yu, Orhan Firat, Barret Zoph, Liam Fedus, Maarten P. Bosma, Zongwei Zhou, Tao Wang, Yu Emma Wang, Kellie Webster, Marie Pellat, Kevin Robinson, Kathleen Meier-Hellstern, Toju Duke, Lucas Dixon, Kun Zhang, Quoc V. Le, Yonghui Wu, Zhifeng Chen, and Claire Cui. GLaM: Efficient scaling of language models with mixture-of-experts. In Proceedings of the 39th International Conference on Machine Learning, volume 162 of Proceedings of Machine Learning Research, pages 5547\u20135569, Baltimore, MD, USA, July 2022."},{"key":"e_1_3_2_1_2_1","volume-title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. https:\/\/arxiv.org\/abs\/1701.06538","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, and Jeff Dean. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. https:\/\/arxiv.org\/abs\/1701.06538, 2017. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_3_1","volume-title":"MoESys: A Distributed and Efficient Mixture-of-Experts Training and Inference System for Internet Services. https:\/\/arxiv.org\/abs\/2205.10034","author":"Yu Dianhai","year":"2024","unstructured":"Dianhai Yu, Liang Shen, Hongxiang Hao, Weibao Gong, Huachao Wu, Jiang Bian, Lirong Dai, and Haoyi Xiong. MoESys: A Distributed and Efficient Mixture-of-Experts Training and Inference System for Internet Services. https:\/\/arxiv.org\/abs\/2205.10034, 2024. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604869"},{"key":"e_1_3_2_1_6_1","first-page":"959","volume-title":"Proceedings of the 2023 USENIX Annual Technical Conference, ATC '23","author":"Li Jiamin","year":"2023","unstructured":"Jiamin Li, Yimin Jiang, Yibo Zhu, Cong Wang, and Hong Xu. Accelerating distributed MoE training and inference with Lina. In Proceedings of the 2023 USENIX Annual Technical Conference, ATC '23, pages 945\u2013959, Boston, MA, USA, July 2023."},{"key":"e_1_3_2_1_7_1","first-page":"18346","volume-title":"Proceedings of the 39th International Conference on Machine Learning, volume 162 of ICML '22","author":"Rajbhandari Samyam","year":"2022","unstructured":"Samyam Rajbhandari, Conglong Li, Zhewei Yao, Minjia Zhang, Reza Yazdani Aminabadi, Ammar Ahmad Awan, Jeff Rasley, and Yuxiong He. DeepSpeed-MoE: Advancing mixture-of-experts inference and training to power next-generation AI scale. In Proceedings of the 39th International Conference on Machine Learning, volume 162 of ICML '22, pages 18332\u201318346, Baltimore, MD, USA, July 2022."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1592681.1592693"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1012998604387"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672233"},{"key":"e_1_3_2_1_11_1","volume-title":"IEEE Standard IEEE Std 802.1Qbb-2011","author":"IEEE.","year":"2008","unstructured":"IEEE. 802.1 qbb\u2014priority-based flow control. IEEE Standard IEEE Std 802.1Qbb-2011, Institute of Electrical and Electronics Engineers, 2008."},{"key":"e_1_3_2_1_12_1","volume-title":"Infiniband Architecture Specification","author":"InfiniBand Trade Association","year":"2004","unstructured":"InfiniBand Trade Association. Infiniband Architecture Specification Volume 2 Release 1.2. https:\/\/www.cs.kent.edu\/~farrell\/cc05\/reference\/infiniband\/specs\/vol2r1_2.pdf, 2004. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787484"},{"key":"e_1_3_2_1_14_1","first-page":"58","volume-title":"Proceedings of the ACM SIGCOMM 2019 Conference, SIGCOMM '19","author":"Li Yuliang","year":"2019","unstructured":"Yuliang Li, Rui Miao, Hongqiang Harry Liu, Yan Zhuang, Fei Feng, Lingbo Tang, Zheng Cao, Ming Zhang, Frank Kelly, Mohammad Alizadeh, and Minlan Yu. HPCC: High precision congestion control. In Proceedings of the ACM SIGCOMM 2019 Conference, SIGCOMM '19, pages 44\u201358, Beijing, China, August 2019."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787510"},{"key":"e_1_3_2_1_16_1","first-page":"70","volume-title":"Proceedings of the 19th USENIX Symposium on Networked Systems Design and Implementation, NSDI '22","author":"Addanki Vamsi","year":"2022","unstructured":"Vamsi Addanki, Oliver Michel, and Stefan Schmid. PowerTCP: Pushing the performance limits of datacenter networks. In Proceedings of the 19th USENIX Symposium on Networked Systems Design and Implementation, NSDI '22, pages 51\u201370, Renton, WA, April 2022."},{"key":"e_1_3_2_1_17_1","first-page":"274","volume-title":"Proceedings of the 20th USENIX Symposium on Networked Systems Design and Implementation, NSDI '23","author":"Wang Weitao","year":"2023","unstructured":"Weitao Wang, Masoud Moshref, Yuliang Li, Gautam Kumar, T. S. Eugene Ng, Neal Cardwell, and Nandita Dukkipati. Poseidon: Efficient, robust, and practical datacenter CC via deployable INT. In Proceedings of the 20th USENIX Symposium on Networked Systems Design and Implementation, NSDI '23, pages 255\u2013274, Boston, MA, USA, April 2023."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_1_19_1","volume-title":"Conditional Computation in Neural Networks for faster models. https:\/\/arxiv.org\/abs\/1511.06297","author":"Bengio Emmanuel","year":"2016","unstructured":"Emmanuel Bengio, Pierre-Luc Bacon, Joelle Pineau, and Doina Precup. Conditional Computation in Neural Networks for faster models. https:\/\/arxiv.org\/abs\/1511.06297, 2016. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_20_1","volume-title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation. https:\/\/arxiv.org\/abs\/1308.3432","author":"Bengio Yoshua","year":"2013","unstructured":"Yoshua Bengio, Nicholas L\u00e9onard, and Aaron Courville. Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation. https:\/\/arxiv.org\/abs\/1308.3432, 2013. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_21_1","volume-title":"Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient. https:\/\/arxiv.org\/abs\/2502.05172","author":"Ludziejewski Jan","year":"2025","unstructured":"Jan Ludziejewski, Maciej Pi\u00f3ro, Jakub Krajewski, Maciej Stefaniak, Micha\u0142 Krutul, Jan Mala\u015bnicki, Marek Cygan, Piotr Sankowski, Kamil Adamczewski, Piotr Mi\u0142o\u015b, and Sebastian Jaszczur. Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient. https:\/\/arxiv.org\/abs\/2502.05172, 2025. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_22_1","volume-title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity. https:\/\/arxiv.org\/abs\/2101.03961","author":"Fedus William","year":"2022","unstructured":"William Fedus, Barret Zoph, and Noam Shazeer. Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity. https:\/\/arxiv.org\/abs\/2101.03961, 2022. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_23_1","unstructured":"Young Jin Kim Ammar Ahmad Awan Alexandre Muzio Andres Felipe Cruz Salinas Liyang Lu Amr Hendy Samyam Rajbhandari Yuxiong He and Hany Hassan Awadalla. Scalable and Efficient MoE Training for Multitask Multilingual Models. https:\/\/arxiv.org\/abs\/2109.10465 2021. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1006\/jcph.1995.1039"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1021\/ct700301q"},{"key":"e_1_3_2_1_26_1","first-page":"1034","volume-title":"Proceedings of the 22nd USENIX Symposium on Networked Systems Design and Implementation, NSDI '25","author":"Du Xinle","year":"2025","unstructured":"Xinle Du, Tong Li, Guangmeng Zhou, Zhuotao Liu, Hanlin Huang, Jiaming Zhang, Zhaohui Zhang, and Ke Xu. PRED: Performance-oriented random early detection for consistently stable performance in datacenters. In Proceedings of the 22nd USENIX Symposium on Networked Systems Design and Implementation, NSDI '25, pages 1019\u20131034, Philadelphia, PA, USA, April 2025."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934908"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005760"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3143361.3143382"},{"key":"e_1_3_2_1_30_1","first-page":"533","volume-title":"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. When cloud storage meets RDMA. In 18th USENIX Symposium on Networked Systems Design and Implementation, NSDI '21, pages 519\u2013533, Boston, MA, USA, April 2021."},{"key":"e_1_3_2_1_31_1","unstructured":"The ns-3 Project. ns-3: Network simulator. https:\/\/www.nsnam.org\/. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/90.664262"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682942"},{"key":"e_1_3_2_1_34_1","first-page":"471","volume-title":"Proceedings of the 22nd USENIX Symposium on Networked Systems Design and Implementation, NSDI '25","author":"Prasopoulos Konstantinos","year":"2025","unstructured":"Konstantinos Prasopoulos, Ryan Kosta, Edouard Bugnion, and Marios Kogias. SIRD: A sender-informed, receiver-driven datacenter transport protocol. In Proceedings of the 22nd USENIX Symposium on Networked Systems Design and Implementation, NSDI '25, pages 451\u2013471, Philadelphia, PA, USA, April 2025."},{"key":"e_1_3_2_1_35_1","volume-title":"January","author":"Hall Philip","year":"1935","unstructured":"Philip Hall. On Representatives of Subsets. Journal of the London Mathematical Society, s1-10(1):26\u201330, January 1935."},{"key":"e_1_3_2_1_36_1","volume-title":"Data plane development kit (DPDK)","author":"Foundation Linux","unstructured":"Linux Foundation. Data plane development kit (DPDK). http:\/\/www.dpdk.org. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_37_1","unstructured":"P4 Language Consortium. p4lang\/p4-spec: P4 programming language specification repository. https:\/\/github.com\/p4lang\/p4-spec. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_38_1","volume-title":"Overview of SiFive 7 Series Microarchitecture in RISC-V GCC. https:\/\/www.rt-rk.com\/overview-of-sifive-7-series-microarchitecture-in-risc-v-gcc\/","author":"RK.","year":"2024","unstructured":"RT-RK. Overview of SiFive 7 Series Microarchitecture in RISC-V GCC. https:\/\/www.rt-rk.com\/overview-of-sifive-7-series-microarchitecture-in-risc-v-gcc\/, 2024. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_39_1","volume-title":"DOCA-PCC: Doca programmable congestion control documentation. https:\/\/docs.nvidia.com\/doca\/sdk\/DOCA-PCC\/index.html","author":"NVIDIA Corporation","year":"2026","unstructured":"NVIDIA Corporation. DOCA-PCC: Doca programmable congestion control documentation. https:\/\/docs.nvidia.com\/doca\/sdk\/DOCA-PCC\/index.html, 2026. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_40_1","volume-title":"NVIDIA ConnectX-8 SuperNIC Datasheet. https:\/\/resources.nvidia.com\/en-us-accelerated-networking-resource-library\/connectx-datasheet","author":"NVIDIA Corporation","year":"2025","unstructured":"NVIDIA Corporation. NVIDIA ConnectX-8 SuperNIC Datasheet. https:\/\/resources.nvidia.com\/en-us-accelerated-networking-resource-library\/connectx-datasheet, 2025. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_41_1","volume-title":"June","author":"Broadcom Inc.","year":"2017","unstructured":"Broadcom Inc. In-band Telemetry Product Brief. https:\/\/docs.broadcom.com\/doc\/IBT-PB100, June 2017. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_42_1","volume-title":"NVIDIA Spectrum SN4000 Open Ethernet Switches. https:\/\/www.nvidia.com\/en-in\/networking\/ethernet-switching\/spectrum-sn4000\/","author":"NVIDIA Corporation","year":"2026","unstructured":"NVIDIA Corporation. NVIDIA Spectrum SN4000 Open Ethernet Switches. https:\/\/www.nvidia.com\/en-in\/networking\/ethernet-switching\/spectrum-sn4000\/, 2026. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_43_1","volume-title":"Internet Engineering Task Force","author":"Kumar Jai","year":"2020","unstructured":"Jai Kumar, Surendra Anubolu, John Lemon, Rajeev Manur, Hugh Holbrook, Anoop Ghanwani, Dezhong Cai, Heidi Ou, Yizhou Li, and Xiaojun Wang. Inband Flow Analyzer. Internet-Draft draft-kumar-ippm-ifa-02, Internet Engineering Task Force, April 2020."},{"key":"e_1_3_2_1_44_1","volume-title":"November","author":"The P4.org Applications Working Group","year":"2020","unstructured":"The P4.org Applications Working Group. In-band Network Telemetry (INT) Dataplane Specification v2.1. https:\/\/p4.org\/wp-content\/uploads\/sites\/53\/p4-spec\/docs\/INT_v2_1.pdf, November 2020. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.17487\/RFC9197"},{"key":"e_1_3_2_1_46_1","first-page":"558","volume-title":"Proceedings of the 22nd USENIX Symposium on Networked Systems Design and Implementation, NSDI '25","author":"Wang Xizheng","year":"2025","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. SimAI: Unifying architecture design and performance tuning for Large-Scale large language model training with scalability and precision. In Proceedings of the 22nd USENIX Symposium on Networked Systems Design and Implementation, NSDI '25, pages 541\u2013558, Philadelphia, PA, USA, April 2025."},{"key":"e_1_3_2_1_47_1","unstructured":"David Bruce Yoffie and Sarah von Bargen. Nvidia Inc. in 2024 and the Future of AI. https:\/\/store.hbr.org\/product\/nvidia-inc-in-2024-and-the-future-of-ai\/725360 September 2024. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_48_1","article-title":"A KVCachecentric Disaggregated Architecture for LLM Serving","volume":"22","author":"Qin Ruoyu","year":"2026","unstructured":"Ruoyu Qin, Zheming Li, Weiran He, Jialei Cui, Heyi Tang, Feng Ren, Mingxing Zhang, Yongwei Wu, Weimin Zheng, and Xinran Xu. Mooncake: A KVCachecentric Disaggregated Architecture for LLM Serving. ACM Transactions on Storage, 22, March 2026.","journal-title":"ACM Transactions on Storage"},{"key":"e_1_3_2_1_49_1","first-page":"1022","volume-title":"Proceedings of the 23rd USENIX Symposium on Networked Systems Design and Implementation, NSDI '26","author":"Jiang Wanchun","year":"2026","unstructured":"Wanchun Jiang, Haoyang Li, Kai Wang, Yujie Hu, Xiao Han, Danfeng Shan, Fengyuan Ren, Jiawei Huang, and Jianxin Wang. CCC: Re-architecting delay-based congestion control in datacenter networks. In Proceedings of the 23rd USENIX Symposium on Networked Systems Design and Implementation, NSDI '26, pages 1007\u20131022, Renton, WA, USA, May 2026."},{"key":"e_1_3_2_1_50_1","first-page":"612","volume-title":"Proceedings of the 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. TACCL: Guiding collective algorithm synthesis using communication sketches. In Proceedings of the 20th USENIX Symposium on Networked Systems Design and Implementation, NSDI '23, pages 593\u2013612, Boston, MA, USA, April 2023."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672249"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621327"},{"key":"e_1_3_2_1_53_1","volume-title":"Ultra Ethernet Specification v1.0.1. Industry Specification UE-Specification-1.0.1","author":"Ultra Ethernet Consortium","year":"2025","unstructured":"Ultra Ethernet Consortium. Ultra Ethernet Specification v1.0.1. Industry Specification UE-Specification-1.0.1, Ultra Ethernet Consortium, September 2025."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3754353"},{"key":"e_1_3_2_1_55_1","volume-title":"July","author":"Addanki Vamsi","year":"2024","unstructured":"Vamsi Addanki, Prateesh Goyal, Ilias Marinos, and Stefan Schmid. Ethereal: Divide and conquer network load balancing in large-scale distributed training. https:\/\/arxiv.org\/abs\/2407.00550, July 2024. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3767295.3769320"},{"key":"e_1_3_2_1_57_1","unstructured":"Tommaso Bonato Abdul Kabbani Daniele De Sensi Rong Pan Yanfang Le Costin Raiciu Mark Handley Mihai Brodschi Timo Schneider Nils Blach Ahmad Ghalayini Anup Agarwal Daniel Santos Ferreira Alves Michael Papamichael and Torsten Hoefler. SMaRTT: Sender-based Marked Rapidly-adapting Trimmed & Timed Transport. https:\/\/arxiv.org\/abs\/2404.01630 April 2024. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_58_1","volume-title":"May","author":"Araujo Joao","year":"2026","unstructured":"Joao Araujo, Alex Chow, Mark Handley, Ryder Lewis, Christoph Paasch, Jitendra Padhye, Michael Papamichael, Greg Steinbrecher, Amin Tootoonchian, Lihua Yuan, Sreevatsa Anantharamu, Abhishek Dosi, Mohit Garg, Mahdieh Ghazimirsaeed, Torsten Hoefler, Deepal Jayasinghe, Jithin Jose, Abdul Kabbani, Guohan Lu, Yang Wang, K. Doddapaneni, Murali Garimella, Vipin Jain, Yanfang Le, H. Nagulapalli, S. Narayanan, Rong Pan, Rathina Sabesan, Raghava Sivaramu, Rip Sohan, Eric Davis, Dragos Dumitrescu, Mohan Kalkunte, Bhaswar Mitra, Guglielmo Morandin, Adrian Popa, Costin Raiciu, Eric Spada, John Spillane, Niranjan Vaidya, Aviv Barnea, Idan Burstein, Elazar Cohen, Yamin Friedman, Noam Katz, Masoud Moshref, Yuval Shpigelman, Shahaf Shuler, Shy Shyman, and Sayantan Sur. Resilient AI Supercomputer Networking Using MRC and SRv6. https:\/\/arxiv.org\/abs\/2605.04333, May 2026. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_59_1","first-page":"322","volume-title":"Proceedings of the ACM SIGCOMM 2020 Conference, SIGCOMM '20","author":"Kumar Gautam","year":"2020","unstructured":"Gautam Kumar, Nandita Dukkipati, Keon Jang, Hassan M. G. Wassel, Xian Wu, Behnam Montazeri, Yaogong Wang, Kevin Springborn, Christopher Alfeld, Michael Ryan, David Wetherall, and Amin Vahdat. Swift: Delay is simple and effective for congestion control in the datacenter. In Proceedings of the ACM SIGCOMM 2020 Conference, SIGCOMM '20, pages 309\u2013322, Virtual Event, USA, August 2020."},{"key":"e_1_3_2_1_60_1","first-page":"1056","volume-title":"2025 USENIX Annual Technical Conference, ATC '25","author":"Peng Yajuan","year":"2025","unstructured":"Yajuan Peng, Haoran Wei, Xiaolong Zhong, Junkai Huang, Haohan Xu, Zicheng Wang, Yang Bai, Zhuo Jiang, Jianxi Ye, Xiaoliang Wang, Xiaoming Fu, and Huichen Dai. Barre: empowering simplified and versatile programmable congestion control in high-speed ai clusters. In 2025 USENIX Annual Technical Conference, ATC '25, pages 1041\u20131056, Boston, MA, USA, July 2025."},{"key":"e_1_3_2_1_61_1","first-page":"570","volume-title":"Proceedings of the 23rd USENIX Symposium on Networked Systems Design and Implementation, NSDI '26","author":"Zhang Zhaochen","year":"2026","unstructured":"Zhaochen Zhang, Feiyang Xue, Rui Ning, Keqiang He, Gianni Antichi, Jiaqi Gao, Zhimeng Yin, Kexin Liu, Rui Li, Zhengqi Cui, Zhehao Lin, Peirui Cao, Guihai Chen, and Chen Tian. OSCAR: O(1)-Step convergence and readily-deployable congestion control. In Proceedings of the 23rd USENIX Symposium on Networked Systems Design and Implementation, NSDI '26, pages 543\u2013570, Renton, WA, May 2026."},{"key":"e_1_3_2_1_62_1","first-page":"1570","volume-title":"Proceedings of the 23rd USENIX Symposium on Networked Systems Design and Implementation, NSDI '26","author":"Jiang Wanchun","year":"2026","unstructured":"Wanchun Jiang, Haoyang Li, Kai Wang, Yujie Hu, Xiao Han, Danfeng Shan, Fengyuan Ren, Jiawei Huang, and Jianxin Wang. CCC: Re-architecting delay-based congestion control in datacenter networks. In Proceedings of the 23rd USENIX Symposium on Networked Systems Design and Implementation, NSDI '26, pages 1553\u20131570, Renton, WA, May 2026."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/2716281.2836086"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098840"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098825"},{"key":"e_1_3_2_1_66_1","first-page":"235","volume-title":"Proceedings of the ACM SIGCOMM 2018 Conference, SIGCOMM '18","author":"Montazeri Behnam","year":"2018","unstructured":"Behnam Montazeri, Yilong Li, Mohammad Alizadeh, and John Ousterhout. Homa: a receiver-driven low-latency transport protocol using network priorities. In Proceedings of the ACM SIGCOMM 2018 Conference, SIGCOMM '18, pages 221\u2013235, Budapest, Hungary, August 2018."},{"key":"e_1_3_2_1_67_1","first-page":"434","volume-title":"Proceedings of the ACM SIGCOMM 2020 Conference, SIGCOMM '20","author":"Hu Shuihai","year":"2020","unstructured":"Shuihai Hu, Wei Bai, Gaoxiong Zeng, Zilong Wang, Baochen Qiao, Kai Chen, Kun Tan, and Yi Wang. Aeolus: A building block for proactive transport in datacenters. In Proceedings of the ACM SIGCOMM 2020 Conference, SIGCOMM '20, pages 422\u2013434, Virtual Event, USA, July 2020."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696101"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512798.3512815"},{"key":"e_1_3_2_1_70_1","first-page":"397","volume-title":"Proceedings of the ACM SIGCOMM 2021 Conference, SIGCOMM '21","author":"Yan Siyu","year":"2021","unstructured":"Siyu Yan, Xiaoliang Wang, Xiaolong Zheng, Yinben Xia, Derui Liu, and Weishan Deng. ACC: automatic ecn tuning for high-speed datacenter networks. In Proceedings of the ACM SIGCOMM 2021 Conference, SIGCOMM '21, pages 384\u2013397, Virtual Event, USA, August 2021."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2022.3185253"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3650069"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696065"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/90.649568"},{"key":"e_1_3_2_1_75_1","first-page":"422","volume-title":"Proceedings of the 11th USENIX Symposium on Networked Systems Design and Implementation, NSDI '14","author":"Radhakrishnan Sivasankar","year":"2014","unstructured":"Sivasankar Radhakrishnan, Yilong Geng, Vimalkumar Jeyakumar, Abdul Kabbani, George Porter, and Amin Vahdat. SENIC: scalable nic for end-host rate limiting. In Proceedings of the 11th USENIX Symposium on Networked Systems Design and Implementation, NSDI '14, pages 409\u2013422, Seattle, WA, USA, April 2014."},{"key":"e_1_3_2_1_76_1","first-page":"417","volume-title":"Proceedings of the ACM SIGCOMM 2017 Conference, SIGCOMM '17","author":"Saeed Ahmed","year":"2017","unstructured":"Ahmed Saeed, Nandita Dukkipati, Vytautas Valancius, Vinh The Lam, Carlo Contavalli, and Amin Vahdat. Carousel: Scalable traffic shaping at end hosts. In Proceedings of the ACM SIGCOMM 2017 Conference, SIGCOMM '17, pages 404\u2013417, Los Angeles, CA, USA, August 2017."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672215"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2015.7218374"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544252"},{"key":"e_1_3_2_1_80_1","first-page":"778","volume-title":"Proceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation, NSDI '24","author":"Addanki Vamsi","year":"2024","unstructured":"Vamsi Addanki, Wei Bai, Stefan Schmid, and Maria Apostolaki. Reverie: Low pass Filter-Based switch buffer sharing for datacenters with RDMA and TCP traffic. In Proceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation, NSDI '24, pages 763\u2013778, Santa Clara, CA, USA, April 2024."},{"key":"e_1_3_2_1_81_1","volume-title":"July","author":"Gao Jiyang","year":"2017","unstructured":"Jiyang Gao, Zhenheng Yang, and Ram Nevatia. RED: Reinforced Encoder-Decoder Networks for Action Anticipation. https:\/\/arxiv.org\/abs\/1707.04818, July 2017. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/2209249.2209264"},{"key":"e_1_3_2_1_83_1","first-page":"1038","volume-title":"Proceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation, NSDI '24","author":"Jiang Ziheng","year":"2024","unstructured":"Ziheng Jiang, Haibin Lin, Yinmin Zhong, Qi Huang, Yangrui Chen, Zhi Zhang, Yanghua Peng, Xiang Li, Cong Xie, Shibiao Nong, Yulu Jia, Sun He, Hongmin Chen, Zhihao Bai, Qi Hou, Shipeng Yan, Ding Zhou, Yiyao Sheng, Zhuo Jiang, Haohan Xu, Haoran Wei, Zhang Zhang, Pengfei Nie, Leqi Zou, Sida Zhao, Liang Xiang, Zherui Liu, Zhe Li, Xiaoying Jia, Jianxi Ye, Xin Jin, and Xin Liu. MegaScale: Scaling large language model training to more than 10,000 gpus. In Proceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation, NSDI '24, pages 1021\u20131038, Santa Clara, CA, USA, April 2024."},{"key":"e_1_3_2_1_84_1","volume-title":"Doubling all2all performance with NVIDIA collective communication library 2.12. https:\/\/developer.nvidia.com\/blog\/doubling-all2all-performance-with-nvidia-collective-communication-library-2-12\/","author":"NVIDIA Corporation","year":"2022","unstructured":"NVIDIA Corporation. Doubling all2all performance with NVIDIA collective communication library 2.12. https:\/\/developer.nvidia.com\/blog\/doubling-all2all-performance-with-nvidia-collective-communication-library-2-12\/, 2022. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_85_1","volume-title":"NVIDIA Spectrum SN5000 Series Switches introduction. https:\/\/networking-docs.nvidia.com\/sn5000hw\/introduction","author":"NVIDIA Corporation","year":"2025","unstructured":"NVIDIA Corporation. NVIDIA Spectrum SN5000 Series Switches introduction. https:\/\/networking-docs.nvidia.com\/sn5000hw\/introduction, 2025. Accessed: 2026-07-03."},{"key":"e_1_3_2_1_86_1","volume-title":"NCCL Environment Variables. https:\/\/docs.nvidia.com\/deeplearning\/nccl\/user-guide\/docs\/env.html","author":"NVIDIA Corporation","year":"2026","unstructured":"NVIDIA Corporation. NCCL Environment Variables. https:\/\/docs.nvidia.com\/deeplearning\/nccl\/user-guide\/docs\/env.html, 2026. Accessed: 2026-06-12."},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3717495"}],"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\/3789240.3829164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:37:52Z","timestamp":1786473472000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3789240.3829164"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":87,"alternative-id":["10.1145\/3789240.3829164","10.1145\/3789240"],"URL":"https:\/\/doi.org\/10.1145\/3789240.3829164","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"}}]}}