{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T13:03:59Z","timestamp":1780664639363,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T00:00:00Z","timestamp":1777161600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Hong Kong RGC TRS","award":["T41-603\/20R"],"award-info":[{"award-number":["T41-603\/20R"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,27]]},"DOI":"10.1145\/3767295.3803588","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:20:04Z","timestamp":1777062004000},"page":"693-709","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Enabling Packet Spraying over Commodity RNICs with In-Network Support"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2156-9683","authenticated-orcid":false,"given":"Xiangzhou","family":"Liu","sequence":"first","affiliation":[{"name":"CSE department, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8228-2552","authenticated-orcid":false,"given":"Wenxue","family":"Li","sequence":"additional","affiliation":[{"name":"CSE department, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1077-6611","authenticated-orcid":false,"given":"Zihao","family":"Wang","sequence":"additional","affiliation":[{"name":"CSE department, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2587-6028","authenticated-orcid":false,"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"CSE department, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,26]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2021. Mellanox ConnectX-7 Product Brief. https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/networking\/ethernet-adapters\/connectx-7-datasheet-Final.pdf."},{"key":"e_1_3_2_1_2_1","unstructured":"2021. OFED Perftest. https:\/\/github.com\/linux-rdma\/perftest\/."},{"key":"e_1_3_2_1_3_1","unstructured":"2024. Mellanox userland tools and scripts. https:\/\/github.com\/Mellanox\/mlnx-tools."},{"key":"e_1_3_2_1_4_1","unstructured":"2025. AMD Pensando Pollara 400 AI NIC. https:\/\/www.amd.com\/en\/products\/network-interface-cards\/pensando.html."},{"key":"e_1_3_2_1_5_1","unstructured":"2025. DOCA PCC. https:\/\/docs.nvidia.com\/doca\/sdk\/doca+pcc\/index.html."},{"key":"e_1_3_2_1_6_1","unstructured":"2025. Mellanox BlueField-2 Product Brief. https:\/\/resources.nvidia.com\/en-us-accelerated-networking-resource-library\/bluefield-2-dpu-datasheet."},{"key":"e_1_3_2_1_7_1","unstructured":"2025. Mellanox BlueField-3 Product Brief. https:\/\/resources.nvidia.com\/en-us-accelerated-networking-resource-library\/datasheet-nvidia-bluefield."},{"key":"e_1_3_2_1_8_1","unstructured":"2025. Mellanox ConnectX-6 Product Brief. https:\/\/www.nvidia.com\/en-sg\/networking\/ethernet\/connectx-6\/."},{"key":"e_1_3_2_1_9_1","unstructured":"2025. Mellanox ConnectX-7 Adaptive Routing Mode. https:\/\/www.nvidia.com\/en-us\/networking\/spectrumx\/."},{"key":"e_1_3_2_1_10_1","unstructured":"2025. Zero touch RoCE enables RoCE to operate on fabrics where no PFC nor ECN are configured. https:\/\/docs.nvidia.com\/networking\/display\/winof2v25150020\/ethernet+network."},{"key":"e_1_3_2_1_11_1","unstructured":"RFC 4296. 2005. The Architecture of Direct Data Placement (DDP) and Remote Direct Memory Access (RDMA) on Internet Protocols."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/HCS49909.2020.9220636"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1402958.1402967"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626316"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1851182.1851192"},{"key":"e_1_3_2_1_16_1","volume-title":"Enabling Programmable Transport Protocols in High-Speed NICs. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","author":"Arashloo Mina Tahmasbi","year":"2020","unstructured":"Mina Tahmasbi Arashloo, Alexey Lavrov, Manya Ghobadi, Jennifer Rexford, David Walker, and David Wentzlaff. 2020. Enabling Programmable Transport Protocols in High-Speed NICs. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20). USENIX Association, Santa Clara, CA, 93\u2013109. https:\/\/www.usenix.org\/conference\/nsdi20\/presentation\/arashloo"},{"key":"e_1_3_2_1_17_1","volume-title":"Information-Agnostic Flow Scheduling for Commodity Data Centers. In 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI 15)","author":"Bai Wei","year":"2015","unstructured":"Wei Bai, Li Chen, Kai Chen, Dongsu Han, Chen Tian, and Hao Wang. 2015. Information-Agnostic Flow Scheduling for Commodity Data Centers. In 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI 15). USENIX Association, Oakland, CA, 455\u2013468. https:\/\/www.usenix.org\/conference\/nsdi15\/technical-sessions\/presentation\/bai"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672239"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230551"},{"key":"e_1_3_2_1_20_1","unstructured":"DeepSeek-AI and Aixin Liu et al. 2024. DeepSeek-V3 Technical Report. arXiv:2412.19437 [cs.CL] https:\/\/arxiv.org\/abs\/2412.19437"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2013.6567015"},{"key":"e_1_3_2_1_22_1","volume-title":"Beyond A Single AI Cluster: A Survey of Decentralized LLM Training. arXiv preprint arXiv:2503.11023","author":"Dong Haotian","year":"2025","unstructured":"Haotian Dong, Jingyan Jiang, Rongwei Lu, Jiajun Luo, Jiajun Song, Bowen Li, Ying Shen, and Zhi Wang. 2025. Beyond A Single AI Cluster: A Survey of Decentralized LLM Training. arXiv preprint arXiv:2503.11023 (2025)."},{"key":"e_1_3_2_1_23_1","volume-title":"Azure Accelerated Networking: SmartNICs in the Public Cloud. In 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18)","author":"Firestone Daniel","unstructured":"Daniel Firestone and Andrew Putnam et al. 2018. Azure Accelerated Networking: SmartNICs in the Public Cloud. In 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18). USENIX Association, Renton, WA, 51\u201366. https:\/\/www.usenix.org\/conference\/nsdi18\/presentation\/firestone"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672233"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934908"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"C. Hopps. 2000. RFC2992: Analysis of an Equal-Cost Multi-Path Algorithm.","DOI":"10.17487\/rfc2992"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486354"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 2025 USENIX Conference on Usenix Annual Technical Conference (Boston, MA, USA) (USENIX ATC '25). USENIX Association, USA, Article 22","author":"Hu Jinbin","year":"2025","unstructured":"Jinbin Hu, Wenxue Li, Xiangzhou Liu, Junfeng Wang, Bowen Liu, Ping Yin, Jianxin Wang, Jiawei Huang, and Kai Chen. 2025. FLB: finegrained load balancing for lossless datacenter networks. In Proceedings of the 2025 USENIX Conference on Usenix Annual Technical Conference (Boston, MA, USA) (USENIX ATC '25). USENIX Association, USA, Article 22, 16 pages."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP59255.2023.10355615"},{"key":"e_1_3_2_1_30_1","volume-title":"Characterization of Large Language Model Development in the Datacenter. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Hu Qinghao","year":"2024","unstructured":"Qinghao Hu, Zhisheng Ye, Zerui Wang, Guoteng Wang, Meng Zhang, Qiaoling Chen, Peng Sun, Dahua Lin, Xiaolin Wang, Yingwei Luo, et al. 2024. Characterization of Large Language Model Development in the Datacenter. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). USENIX Association, Santa Clara, CA, 709\u2013729. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/hu"},{"key":"e_1_3_2_1_31_1","unstructured":"Zhiyi Hu Siyuan Shen Tommaso Bonato Sylvain Jeaugey Cedell Alexander Eric Spada James Dinan Jeff Hammond and Torsten Hoefler. 2025. Demystifying NCCL: An In-depth Analysis of GPU Communication Protocols and Algorithms. arXiv:2507.04786 [cs.DC] https:\/\/arxiv.org\/abs\/2507.04786"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP.2018.00017"},{"key":"e_1_3_2_1_33_1","volume-title":"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, et al. 2024. MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). USENIX Association, Santa Clara, CA, 745\u2013760. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/jiang-ziheng"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2890955.2890968"},{"key":"e_1_3_2_1_35_1","unstructured":"Yanfang Le Rong Pan Peter Newman Jeremias Blendin Abdul Kabbani Vipin Jain Raghava Sivaramu and Francis Matus. 2024. STrack: A Reliable Multipath Transport for AI\/ML Clusters. arXiv:2407.15266 [cs.NI] https:\/\/arxiv.org\/abs\/2407.15266"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750480"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342085"},{"key":"e_1_3_2_1_38_1","volume-title":"Unlocking ECMP Programmability for Precise Traffic Control. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25)","author":"Liu Yadong","year":"2025","unstructured":"Yadong Liu, Yunming Xiao, Xuan Zhang, Weizhen Dang, Huihui Liu, Xiang Li, Zekun He, Jilong Wang, Aleksandar Kuzmanovic, Ang Chen, et al. 2025. Unlocking ECMP Programmability for Precise Traffic Control. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25). USENIX Association, Philadelphia, PA, 87\u2013106. https:\/\/www.usenix.org\/conference\/nsdi25\/presentation\/liuyadong"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750539"},{"key":"e_1_3_2_1_40_1","volume-title":"Multi-Path Transport for RDMA in Datacenters. In 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18)","author":"Lu Yuanwei","year":"2018","unstructured":"Yuanwei Lu, Guo Chen, Bojie Li, Kun Tan, Yongqiang Xiong, Peng Cheng, Jiansong Zhang, Enhong Chen, and Thomas Moscibroda. 2018. Multi-Path Transport for RDMA in Datacenters. In 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18). USENIX Association, Renton, WA, 357\u2013371. https:\/\/www.usenix.org\/conference\/nsdi18\/presentation\/lu"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544238"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230557"},{"key":"e_1_3_2_1_43_1","unstructured":"OpenAI and Josh Achiam et al. 2024. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL] https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_1_44_1","volume-title":"LuoShen: A Hyper-Converged Programmable Gateway for Multi-Tenant Multi-Service Edge Clouds. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Pan Tian","year":"2024","unstructured":"Tian Pan, Kun Liu, Xionglie Wei, Yisong Qiao, Jun Hu, Zhiguo Li, Jun Liang, Tiesheng Cheng, Wenqiang Su, Jie Lu, et al. 2024. LuoShen: A Hyper-Converged Programmable Gateway for Multi-Tenant Multi-Service Edge Clouds. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). USENIX Association, Santa Clara, CA, 877\u2013892. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/pan"},{"key":"e_1_3_2_1_45_1","volume-title":"Barre: Empowering Simplified and Versatile Programmable Congestion Control in High-Speed AI Clusters. In Proceedings of the 2025 USENIX Annual Technical Conference (USENIX ATC '25)","author":"Peng Yajuan","year":"2025","unstructured":"Yajuan Peng, Zicheng Wang, Yang Bai, Zhuo Jiang, Jianxi Ye, Xiaoliang Wang, Haoran Wei, Xiaolong Zhong, Junkai Huang, Haohan Xu, et al. 2025. Barre: Empowering Simplified and Versatile Programmable Congestion Control in High-Speed AI Clusters. In Proceedings of the 2025 USENIX Annual Technical Conference (USENIX ATC '25). USENIX Association, Boston, MA, USA. https:\/\/www.usenix.org\/conference\/atc25\/presentation\/peng-yajuan Open access; co-located with OSDI '25."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672265"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787472"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.3016891"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787508"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604849"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3642970.3655843"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2009.5061931"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3482898.3483363"},{"key":"e_1_3_2_1_54_1","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Vanini Erico","year":"2017","unstructured":"Erico Vanini, Rong Pan, Mohammad Alizadeh, Parvin Taheri, and Tom Edsall. 2017. Let it flow: Resilient asymmetric load balancing with flowlet switching. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17). 407\u2013420."},{"key":"e_1_3_2_1_55_1","volume-title":"Towards Domain-Specific Network Transport for Distributed DNN Training. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Wang Hao","year":"2024","unstructured":"Hao Wang, Han Tian, Jingrong Chen, Xinchen Wan, Jiacheng Xia, Gaoxiong Zeng, Wei Bai, Junchen Jiang, Yong Wang, and Kai Chen. 2024. Towards Domain-Specific Network Transport for Distributed DNN Training. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). USENIX Association, Santa Clara, CA, 1421\u20131443. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/wang-hao"},{"key":"e_1_3_2_1_56_1","volume-title":"SRNIC: A Scalable Architecture for RDMA NICs. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Wang Zilong","year":"2023","unstructured":"Zilong Wang, Layong Luo, Qingsong Ning, Chaoliang Zeng, Wenxue Li, Xinchen Wan, Peng Xie, Tao Feng, Ke Cheng, Xiongfei Geng, et al. 2023. SRNIC: A Scalable Architecture for RDMA NICs. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). USENIX Association, Boston, MA, 1\u201314. https:\/\/www.usenix.org\/conference\/nsdi23\/presentation\/wang-zilong"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098841"},{"key":"e_1_3_2_1_58_1","volume-title":"Hashing Linearity Enables Relative Path Control in Data Centers. In 2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Zhang Zhehui","year":"2021","unstructured":"Zhehui Zhang, Haiyang Zheng, Jiayao Hu, Xiangning Yu, Chenchen Qi, Xuemei Shi, and Guohui Wang. 2021. Hashing Linearity Enables Relative Path Control in Data Centers. In 2021 USENIX Annual Technical Conference (USENIX ATC 21). USENIX Association, 855\u2013862. https:\/\/www.usenix.org\/conference\/atc21\/presentation\/zhang-zhehui"},{"key":"e_1_3_2_1_59_1","unstructured":"Chenggang Zhao Chengqi Deng Chong Ruan Damai Dai Huazuo Gao Jiashi Li Liyue Zhang Panpan Huang Shangyan Zhou Shirong Ma et al. 2025. Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures. arXiv:2505.09343 [cs.DC] https:\/\/arxiv.org\/abs\/2505.09343"},{"key":"e_1_3_2_1_60_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, et al. 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_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787484"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098849"}],"event":{"name":"EUROSYS '26: 21st European Conference on Computer Systems","location":"McEwan Hall\/The University of Edinburgh Edinburgh Scotland UK","acronym":"EUROSYS '26","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 21st European Conference on Computer Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3767295.3803588","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T12:09:24Z","timestamp":1780661364000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767295.3803588"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,26]]},"references-count":62,"alternative-id":["10.1145\/3767295.3803588","10.1145\/3767295"],"URL":"https:\/\/doi.org\/10.1145\/3767295.3803588","relation":{},"subject":[],"published":{"date-parts":[[2026,4,26]]},"assertion":[{"value":"2026-04-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}