{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T18:04:08Z","timestamp":1768068248324,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,4]],"date-time":"2024-08-04T00:00:00Z","timestamp":1722729600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"King Abdullah University of Science and Technology (KAUST) Office of Research Administration (ORA)","award":["ORA-CRG2020-4382"],"award-info":[{"award-number":["ORA-CRG2020-4382"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,4]]},"DOI":"10.1145\/3672198.3673804","type":"proceedings-article","created":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T12:24:10Z","timestamp":1721132650000},"page":"75-83","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["OmNICCL: Zero-cost Sparse AllReduce with Direct Cache Access and SmartNICs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1401-9170","authenticated-orcid":false,"given":"Tongzhou","family":"Gu","sequence":"first","affiliation":[{"name":"KAUST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9325-0516","authenticated-orcid":false,"given":"Jiawei","family":"Fei","sequence":"additional","affiliation":[{"name":"NUDT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5051-4283","authenticated-orcid":false,"given":"Marco","family":"Canini","sequence":"additional","affiliation":[{"name":"KAUST"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","unstructured":"1993. MPI: A message passing interface. In SC. https:\/\/doi.org\/10.1145\/169627.169855","DOI":"10.1145\/169627.169855"},{"key":"e_1_3_2_1_2_1","unstructured":"2021. P4com: In-network computation with programmable switches. arXiv:2107.13694 [cs.NI] https:\/\/arxiv.org\/abs\/2107.13694"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3145836"},{"key":"e_1_3_2_1_4_1","unstructured":"2023. Open Fabrics Enterprise Distribution (OFED) Performance Tests. https:\/\/github.com\/linux-rdma\/perftest"},{"key":"e_1_3_2_1_5_1","unstructured":"2023. RDMA Core Userspace Libraries and Daemons. https:\/\/github.com\/linux-rdma\/rdma-core"},{"key":"e_1_3_2_1_6_1","unstructured":"Arm. 2023. Arm DynamIQ Shared Unit Technical Reference Manual r3p0. https:\/\/developer.arm.com\/documentation\/100453\/0300\/functional-description\/l3-cache\/cache-stashing"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78713-4_2"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2011.3"},{"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","doi-asserted-by":"publisher","unstructured":"Jiawei Fei Chen-Yu Ho Atal N. Sahu Marco Canini and Amedeo Sapio. 2021. Efficient Sparse Collective Communication and its application to Accelerate Distributed Deep Learning. In SIGCOMM. https:\/\/doi.org\/10.1145\/3452296.3472904","DOI":"10.1145\/3452296.3472904"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30218-6_19"},{"key":"e_1_3_2_1_12_1","unstructured":"Nadeen Gebara Paolo Costa and Manya Ghobadi. 2021. In-network Aggregation for Shared Machine Learning Clusters. In MLSys."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","unstructured":"Richard Graham George Bosilca Yong Qin Bradley Settlemyer Gilad Shainer Craig Stunkel Geoffroy Vallee Brody Williams Gerardo Cisneros-Stoianowski Sebastian Ohlmann and Markus Rampp. 2024. Optimizing Application Performance with BlueField: Accelerating Large-Message Blocking and Nonblocking Collective Operations. In ISC. https:\/\/doi.org\/10.23919\/ISC.2024.10528935","DOI":"10.23919\/ISC.2024.10528935"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","unstructured":"Richard L. Graham Devendar Bureddy Pak Lui Hal Rosenstock Gilad Shainer Gil Bloch Dror Goldenerg Mike Dubman Sasha Kotchubievsky Vladimir Koushnir Lion Levi Alex Margolin Tamir Ronen Alexander Shpiner Oded Wertheim and Eitan Zahavi. 2016. Scalable Hierarchical Aggregation Protocol (SHArP): A Hardware Architecture for Efficient Data Reduction. In COMHPC. https:\/\/doi.org\/10.1109\/COMHPC.2016.006","DOI":"10.1109\/COMHPC.2016.006"},{"key":"e_1_3_2_1_15_1","unstructured":"Intel. 2023. Intel Data Direct I\/O Technology (Intel DDIO): Technology Brief. https:\/\/www.intel.com\/content\/www\/us\/en\/io\/data-direct-i-o-technology-brief.html"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","unstructured":"Alexander Ishii and Ryan Wells. 2022. The Nvlink-Network Switch: Nvidia's Switch Chip for High Communication-Bandwidth Superpods. In HCS. https:\/\/doi.org\/10.1109\/HCS55958.2022.9895480","DOI":"10.1109\/HCS55958.2022.9895480"},{"key":"e_1_3_2_1_17_1","unstructured":"Yimin Jiang Yibo Zhu Chang Lan Bairen Yi Yong Cui and Chuanxiong Guo. 2020. A Unified Architecture for Accelerating Distributed DNN Training in Heterogeneous GPU\/CPU Clusters. In OSDI. https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/jiang"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","unstructured":"Ignacio Laguna Ryan Marshall Kathryn Mohror Martin Ruefenacht Anthony Skjellum and Nawrin Sultana. 2019. A large-scale study of MPI usage in open-source HPC applications. In SC. https:\/\/doi.org\/10.1145\/3295500.3356176","DOI":"10.1145\/3295500.3356176"},{"key":"e_1_3_2_1_19_1","volume-title":"ATP: In-network Aggregation for Multi-tenant Learning. In NSDI. https:\/\/www.usenix.org\/conference\/nsdi21\/presentation\/lao","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 NSDI. https:\/\/www.usenix.org\/conference\/nsdi21\/presentation\/lao"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"Youjie Li Iou-Jen Liu Yifan Yuan Deming Chen Alexander Schwing and Jian Huang. 2019. Accelerating Distributed Reinforcement learning with In-Switch Computing. In ISCA. https:\/\/doi.org\/10.1109\/ISCA.2019.00034","DOI":"10.1109\/ISCA.2019.00034"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","unstructured":"Zhaoyi Li Jiawei Huang Yijun Li Aikun Xu Shengwen Zhou Jingling Liu and Jianxin Wang. 2023. A2TP: Aggregator-Aware In-Network Aggregation for Multi-Tenant Learning. In EuroSys. https:\/\/doi.org\/10.1145\/3552326.3587436","DOI":"10.1145\/3552326.3587436"},{"key":"e_1_3_2_1_23_1","unstructured":"Linux Foundation. 2015. Data Plane Development Kit (DPDK). http:\/\/www.dpdk.org"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","unstructured":"Ming Liu Tianyi Cui Henry Schuh Arvind Krishnamurthy Simon Peter and Karan Gupta. 2019. Offloading Distributed Applications onto SmartNICs Using IPipe. In SIGCOMM. https:\/\/doi.org\/10.1145\/3341302.3342079","DOI":"10.1145\/3341302.3342079"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","unstructured":"Shuo Liu Qiaoling Wang Junyi Zhang Wenfei Wu Qinliang Lin Yao Liu Meng Xu Marco Canini Ray C. C. Cheung and Jianfei He. 2023. In-Network Aggregation with Transport Transparency for Distributed Training. In ASPLOS. https:\/\/doi.org\/10.1145\/3582016.3582037","DOI":"10.1145\/3582016.3582037"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2021.3098841"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267840"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2674005.2674996"},{"key":"e_1_3_2_1_29_1","unstructured":"John D. McCalpin. 1991--2007. STREAM: Sustainable Memory Bandwidth in High Performance Computers. http:\/\/www.cs.virginia.edu\/stream\/"},{"key":"e_1_3_2_1_30_1","unstructured":"Mellanox. 2021. Scalable Hierarchical Aggregation and Reduction Protocol (SHARP). https:\/\/www.mellanox.com\/products\/sharp."},{"key":"e_1_3_2_1_31_1","unstructured":"Nvidia. 2015. Nvidia Collective Communications Library (NCCL). https:\/\/developer.nvidia.com\/nccl"},{"key":"e_1_3_2_1_32_1","unstructured":"Nvidia. 2023. Nvidia BlueField-2 DPU. https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/Data-Center\/documents\/datasheet-nvidia-bluefield-2-dpu.pdf"},{"key":"e_1_3_2_1_33_1","unstructured":"Nvidia. 2023. Nvidia BlueField-3 DPU. https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/Data-Center\/documents\/datasheet-nvidia-bluefield-3-dpu.pdf"},{"key":"e_1_3_2_1_34_1","volume-title":"Ru Jia, Penghao Zhang, Leilei Zhang, Ye Yang, Jiahao Wu, Jianbo Dong, Zheng Cao, Qiang Li, Hongqiang Harry Liu, Mathy Laurent, and Gaogang Xie.","author":"Pan Heng","year":"2022","unstructured":"Heng Pan, Penglai Cui, Zhenyu li, Ru Jia, Penghao Zhang, Leilei Zhang, Ye Yang, Jiahao Wu, Jianbo Dong, Zheng Cao, Qiang Li, Hongqiang Harry Liu, Mathy Laurent, and Gaogang Xie. 2022. Enabling Fast and Flexible Distributed Deep Learning with Programmable Switches. arXiv:2205.05243 [cs.NI] https:\/\/arxiv.org\/abs\/2205.05243"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2020.101208"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","unstructured":"Pitch Patarasuk and Xin Yuan. 2009. Bandwidth optimal all-reduce algorithms for clusters of workstations. J. Parallel Distributed Comput. (2009). https:\/\/doi.org\/10.1016\/j.jpdc.2008.08.008","DOI":"10.1016\/j.jpdc.2008.08.008"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","unstructured":"Rolf Rabenseifner. 2004. Optimization of Collective Reduction Operations. In ICCS. https:\/\/doi.org\/10.1007\/978-3-540-24685-5_1","DOI":"10.1007\/978-3-540-24685-5_1"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","unstructured":"Cedric Renggli Saleh Ashkboos Mehdi Aghagolzadeh Dan Alistarh and Torsten Hoefler. 2019. SparCML: High-Performance Sparse Communication for Machine Learning. In SC. https:\/\/doi.org\/10.1145\/3295500.3356222","DOI":"10.1145\/3295500.3356222"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","unstructured":"Amedeo Sapio Ibrahim Abdelaziz Abdulla Aldilaijan Marco Canini and Panos Kalnis. 2017. In-Network Computation is a Dumb Idea Whose Time Has Come. In HotNets. https:\/\/doi.org\/10.1145\/3152434.3152461","DOI":"10.1145\/3152434.3152461"},{"key":"e_1_3_2_1_40_1","unstructured":"Amedeo Sapio Marco Canini Chen-Yu Ho Jacob Nelson Panos Kalnis Changhoon Kim Arvind Krishnamurthy Masoud Moshref Dan Ports and Peter Richtarik. 2021. Scaling Distributed Machine Learning with In-Network Aggregation. In NSDI. https:\/\/www.usenix.org\/conference\/nsdi21\/presentation\/sapio"},{"key":"e_1_3_2_1_41_1","unstructured":"Hao Wang Yuxuan Qin ChonLam Lao Yanfang Le Wenfei Wu and Kai Chen. 2022. Efficient data-plane memory scheduling for in-network aggregation. arXiv:2201.06398 [cs.DC] https:\/\/arxiv.org\/abs\/2201.06398"},{"key":"e_1_3_2_1_42_1","volume-title":"Zen: Near-Optimal Sparse Tensor Synchronization for Distributed DNN Training. arXiv:2309.13254 [cs.LG] https:\/\/arxiv.org\/abs\/2309.13254","author":"Wang Zhuang","year":"2023","unstructured":"Zhuang Wang, Zhaozhuo Xu, Anshumali Shrivastava, and T. S. Eugene Ng. 2023. Zen: Near-Optimal Sparse Tensor Synchronization for Distributed DNN Training. arXiv:2309.13254 [cs.LG] https:\/\/arxiv.org\/abs\/2309.13254"},{"key":"e_1_3_2_1_43_1","volume-title":"GSPMD: General and Scalable Parallelization for ML Computation Graphs. arXiv:2105.04663 [cs.DC] https:\/\/arxiv.org\/abs\/2105.04663","author":"Xu Yuanzhong","year":"2021","unstructured":"Yuanzhong Xu, HyoukJoong Lee, Dehao Chen, Blake Hechtman, Yanping Huang, Rahul Joshi, Maxim Krikun, Dmitry Lepikhin, Andy Ly, Marcello Maggioni, Ruoming Pang, Noam Shazeer, Shibo Wang, Tao Wang, Yonghui Wu, and Zhifeng Chen. 2021. GSPMD: General and Scalable Parallelization for ML Computation Graphs. arXiv:2105.04663 [cs.DC] https:\/\/arxiv.org\/abs\/2105.04663"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","unstructured":"Fan Yang Zhan Wang Xiaoxiao Ma Guojun Yuan and Xuejun An. 2019. SwitchAgg: A further step towards in-network computing. In ISPA\/BDCloud\/SocialCom\/SustainCom. https:\/\/doi.org\/10.1109\/ISPA-BDCloud-SustainCom-SocialCom48970.2019.00017","DOI":"10.1109\/ISPA-BDCloud-SustainCom-SocialCom48970.2019.00017"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3135842"},{"key":"e_1_3_2_1_46_1","volume-title":"Alpa: Automating Inter-and Intra-Operator Parallelism for Distributed Deep Learning. In OSDI. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/zheng-lianmin","author":"Zheng Lianmin","year":"2022","unstructured":"Lianmin Zheng, Zhuohan Li, Hao Zhang, Yonghao Zhuang, Zhifeng Chen, Yanping Huang, Yida Wang, Yuanzhong Xu, Danyang Zhuo, Joseph E. Gonzalez, and Ion Stoica. 2022. Alpa: Automating Inter-and Intra-Operator Parallelism for Distributed Deep Learning. In OSDI. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/zheng-lianmin"}],"event":{"name":"ACM SIGCOMM '24: ACM SIGCOMM 2024 Conference","location":"Sydney NSW Australia","acronym":"ACM SIGCOMM '24","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the 2024 SIGCOMM Workshop on Networks for AI Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3672198.3673804","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3672198.3673804","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T18:15:28Z","timestamp":1755972928000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3672198.3673804"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,4]]},"references-count":46,"alternative-id":["10.1145\/3672198.3673804","10.1145\/3672198"],"URL":"https:\/\/doi.org\/10.1145\/3672198.3673804","relation":{},"subject":[],"published":{"date-parts":[[2024,8,4]]},"assertion":[{"value":"2024-08-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}