{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:53:05Z","timestamp":1781715185052,"version":"3.54.5"},"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-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-223866"],"award-info":[{"award-number":["CNS-223866"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,4]]},"DOI":"10.1145\/3651890.3672252","type":"proceedings-article","created":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T13:11:43Z","timestamp":1722431503000},"page":"679-690","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["MCCS: A Service-based Approach to Collective Communication for Multi-Tenant Cloud"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6297-1599","authenticated-orcid":false,"given":"Yongji","family":"Wu","sequence":"first","affiliation":[{"name":"Duke University, Durham, NC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7390-1153","authenticated-orcid":false,"given":"Yechen","family":"Xu","sequence":"additional","affiliation":[{"name":"Duke University, Durham, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1546-9587","authenticated-orcid":false,"given":"Jingrong","family":"Chen","sequence":"additional","affiliation":[{"name":"Duke University, Durham, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2816-9946","authenticated-orcid":false,"given":"Zhaodong","family":"Wang","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2736-5694","authenticated-orcid":false,"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1034-2736","authenticated-orcid":false,"given":"Matthew","family":"Lentz","sequence":"additional","affiliation":[{"name":"Duke University, Durham, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0611-3941","authenticated-orcid":false,"given":"Danyang","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Duke University, Durham, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,4]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Hedera: Dynamic Flow Scheduling for Data Center Networks. In NSDI.","author":"Al-Fares Mohammad","year":"2010","unstructured":"Mohammad Al-Fares, Sivasankar Radhakrishnan, Barath Raghavan, Nelson Huang, and Amin Vahdat. 2010. Hedera: Dynamic Flow Scheduling for Data Center Networks. In NSDI."},{"key":"e_1_3_2_1_2_1","volume-title":"Francis Matus, Rong Pan, Navindra Yadav, and George Varghese.","author":"Alizadeh Mohammad","year":"2014","unstructured":"Mohammad Alizadeh, Tom Edsall, Sarang Dharmapurikar, Ramanan Vaidyanathan, Kevin Chu, Andy Fingerhut, Vinh The Lam, Francis Matus, Rong Pan, Navindra Yadav, and George Varghese. 2014. CONGA: Distributed Congestion-Aware Load Balancing for Datacenters. In SIGCOMM."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Mohammad Alizadeh Albert Greenberg David A. Maltz Jitendra Padhye Parveen Patel Balaji Prabhakar Sudipta Sengupta and Murari Sridharan. 2010. Data Center TCP (DCTCP). In SIGCOMM.","DOI":"10.1145\/1851182.1851192"},{"key":"e_1_3_2_1_4_1","unstructured":"Sebastian Angel Hitesh Ballani Thomas Karagiannis Greg O'Shea and Eno Thereska. 2014. End-to-end Performance Isolation Through Virtual Datacenters. In OSDI."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Hitesh Ballani Paolo Costa Thomas Karagiannis and Ant Rowstron. 2011. Towards Predictable Datacenter Networks. In SIGCOMM.","DOI":"10.1145\/2018436.2018465"},{"key":"e_1_3_2_1_6_1","first-page":"1877","article-title":"2020. Language Models are Few-shot Learners","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language Models are Few-shot Learners. Advances in Neural Information Processing Systems 33 (2020), 1877--1901.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_7_1","unstructured":"Zixian Cai Zhengyang Liu Saeed Maleki Madanlal Musuvathi Todd Mytkowicz Jacob Nelson and Olli Saarikivi. 2021. Synthesizing Optimal Collective Algorithms. In PPoPP."},{"key":"e_1_3_2_1_8_1","unstructured":"Jingrong Chen Hong Zhang Wei Zhang Liang Luo Jeffrey Chase Ion Stoica and Danyang Zhuo. 2022. NetHint: White-Box Networking for Multi-Tenant Data Centers. In NSDI."},{"key":"e_1_3_2_1_9_1","volume-title":"Balanced Multicasting: High-Throughput Communication for Grid Applications. In ACM\/IEEE Conference on Supercomputing (SC).","author":"Burger Mathijs Den","year":"2005","unstructured":"Mathijs Den Burger, Thilo Kielmann, and Henri E Bal. 2005. Balanced Multicasting: High-Throughput Communication for Grid Applications. In ACM\/IEEE Conference on Supercomputing (SC)."},{"key":"e_1_3_2_1_10_1","unstructured":"Nadeen Gebara Manya Ghobadi and Paolo Costa. 2021. In-Network Aggregation for Shared Machine Learning Clusters. In MLSys."},{"key":"e_1_3_2_1_11_1","unstructured":"Gloo 2023. Collective Communications Library with Various Primitives for Multi-Machine Training. https:\/\/github.com\/facebookincubator\/gloo. (2023)."},{"key":"e_1_3_2_1_12_1","volume-title":"Open MPI: A Flexible High Performance MPI. In International Conference on Parallel Processing and Applied Mathematics. Springer, 228--239","author":"Graham Richard L","year":"2005","unstructured":"Richard L Graham, Timothy S Woodall, and Jeffrey M Squyres. 2005. Open MPI: A Flexible High Performance MPI. In International Conference on Parallel Processing and Applied Mathematics. Springer, 228--239."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Mark Handley Costin Raiciu Alexandru Agache Andrei Voinescu Andrew W. Moore Gianni Antichi and Marcin W\u00f3jcik. 2017. Re-Architecting Datacenter Networks and Stacks for Low Latency and High Performance. In SIGCOMM.","DOI":"10.1145\/3098822.3098825"},{"key":"e_1_3_2_1_14_1","unstructured":"Olaf Hartmann Matthias K\u00fchnemann Thomas Rauber and Gudula R\u00fcnger. 2005. Adaptive Selection of Communication Methods to Optimize Collective MPI Operations. In PARCO."},{"key":"e_1_3_2_1_15_1","unstructured":"intelmpi 2024. Intel MPI Library. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/mpi-library.html. (2024)."},{"key":"e_1_3_2_1_16_1","unstructured":"Vimalkumar Jeyakumar Mohammad Alizadeh David Mazi\u00e8res Balaji Prabhakar Albert Greenberg and Changhoon Kim. 2013. EyeQ: Practical Network Performance Isolation at the Edge. In NSDI."},{"key":"e_1_3_2_1_17_1","volume-title":"Ian Foster, William Gropp, Ewing Lusk, and John Bresnahan.","author":"Karonis Nicholas T","year":"2000","unstructured":"Nicholas T Karonis, Bronis R De Supinski, Ian Foster, William Gropp, Ewing Lusk, and John Bresnahan. 2000. Exploiting Hierarchy in Parallel Computer Networks to Optimize Collective Operation Performance. In IPDPS."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3143361.3143401"},{"key":"e_1_3_2_1_19_1","unstructured":"Praveen Kumar Nandita Dukkipati Nathan Lewis Yi Cui Yaogong Wang Chonggang Li Valas Valancius Jake Adriaens Steve Gribble Nate Foster and Amin Vahdat. 2019. PicNIC: Predictable Virtualized NIC. In SIGCOMM."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2504730.2504744"},{"key":"e_1_3_2_1_21_1","volume-title":"ATP: In-Network Aggregation for Multi-tenant Learning. In NSDI.","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."},{"key":"e_1_3_2_1_22_1","unstructured":"Jeongkeun Lee Yoshio Turner Myungjin Lee Lucian Popa Sujata Banerjee Joon-Myung Kang and Puneet Sharma. 2014. Application-Driven Bandwidth Guarantees in Datacenters. In SIGCOMM."},{"key":"e_1_3_2_1_23_1","unstructured":"Liang Luo Peter West Jacob Nelson Arvind Krishnamurthy and Luis Ceze. 2020. PLink: Discovering and Exploiting Locality for Accelerated Distributed Training on the Public Cloud. In MLSys."},{"key":"e_1_3_2_1_24_1","unstructured":"nccl 2023. The NVIDIA Collective Communication Library (NCCL). https:\/\/developer.nvidia.com\/nccl. (2023)."},{"key":"e_1_3_2_1_25_1","unstructured":"NVIDIA. 2023. Performance Reported by NCCL Tests. https:\/\/github.com\/NVIDIA\/nccl-tests\/blob\/master\/doc\/PERFORMANCE.md. (2023)."},{"key":"e_1_3_2_1_26_1","unstructured":"nvidiasharp 2024. NVIDIA Scalable Hierarchical Aggregation and Reduction Protocol (SHARP). https:\/\/docs.nvidia.com\/networking\/display\/sharpv300. (2024)."},{"key":"e_1_3_2_1_27_1","unstructured":"Vladimir Olteanu Alexandru Agache Andrei Voinescu and Costin Raiciu. 2018. Stateless Datacenter Load-balancing with Beamer. In NSDI."},{"key":"e_1_3_2_1_28_1","unstructured":"oneccl 2023. oneAPI Collective Communications Library (oneCCL). https:\/\/github.com\/oneapi-src\/oneCCL. (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Efficient All-to-All Collective Communication Schedules for Direct-Connect Topologies. arXiv preprint arXiv:2309.13541","author":"Pal Siddharth","year":"2023","unstructured":"Siddharth Pal, Liangyu Zhao, Jason Fantl, Joud Khoury, Arvind Krishnamurthy, and Prithwish Basu. 2023. Efficient All-to-All Collective Communication Schedules for Direct-Connect Topologies. arXiv preprint arXiv:2309.13541 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"Pytorch: An Imperative Style","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An Imperative Style, High-Performance Deep Learning Library. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Y Peng Y Zhu Y Chen Y Bao B Yi C Lan C Wu and C Guo. 2019. A Generic Communication Scheduler for Distributed DNN Training Acceleration. In SOSP.","DOI":"10.1145\/3341301.3359642"},{"key":"e_1_3_2_1_32_1","volume-title":"Dongarra","author":"Pje\u0161ivac-Grbovi\u0107 Jelena","year":"2007","unstructured":"Jelena Pje\u0161ivac-Grbovi\u0107, George Bosilca, Graham E. Fagg, Thara Angskun, and Jack J. Dongarra. 2007. MPI Collective Algorithm Selection and Quadtree Encoding. Parallel Comput. (2007)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Lucian Popa Praveen Yalagandula Sujata Banerjee Jeffrey C. Mogul Yoshio Turner and Jose Renato Santos. 2013. ElasticSwitch: Practical Work-Conserving Bandwidth Guarantees for Cloud Computing. In SIGCOMM.","DOI":"10.1145\/2486001.2486027"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Costin Raiciu Sebastien Barre Christopher Pluntke Adam Greenhalgh Damon Wischik and Mark Handley. 2011. Improving Datacenter Performance and Robustness with Multipath TCP. In SIGCOMM.","DOI":"10.1145\/2018436.2018467"},{"key":"e_1_3_2_1_35_1","volume-title":"CASSINI: Network-Aware Job Scheduling in Machine Learning Clusters. In NSDI.","author":"Rajasekaran Sudarsanan","year":"2024","unstructured":"Sudarsanan Rajasekaran, Manya Ghobadi, and Aditya Akella. 2024. CASSINI: Network-Aware Job Scheduling in Machine Learning Clusters. In NSDI."},{"key":"e_1_3_2_1_36_1","volume-title":"Themis: A Network Bandwidth-Aware Collective Scheduling Policy for Distributed Training of DL Models. In ISCA.","author":"Rashidi Saeed","year":"2022","unstructured":"Saeed Rashidi, William Won, Sudarshan Srinivasan, Srinivas Sridharan, and Tushar Krishna. 2022. Themis: A Network Bandwidth-Aware Collective Scheduling Policy for Distributed Training of DL Models. In ISCA."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_2_1_38_1","unstructured":"rccl 2023. ROCm Communication Collectives Library (RCCL). https:\/\/github.com\/ROCm\/rccl. (2023)."},{"key":"e_1_3_2_1_39_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."},{"key":"e_1_3_2_1_40_1","volume-title":"Swing: Short-cutting Rings for Higher Bandwidth Allreduce. In NSDI.","author":"Sensi Daniele De","year":"2024","unstructured":"Daniele De Sensi, Tommaso Bonato, David Saam, and Torsten Hoefler. 2024. Swing: Short-cutting Rings for Higher Bandwidth Allreduce. In NSDI."},{"key":"e_1_3_2_1_41_1","volume-title":"TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches. In NSDI.","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 NSDI."},{"key":"e_1_3_2_1_42_1","volume-title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. arXiv preprint arXiv:1909.08053","author":"Shoeybi Mohammad","year":"2019","unstructured":"Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro. 2019. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. arXiv preprint arXiv:1909.08053 (2019)."},{"key":"e_1_3_2_1_43_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_44_1","volume-title":"Blink: Fast and Generic Collectives for Distributed ML. In MLSys.","author":"Wang Guanhua","year":"2020","unstructured":"Guanhua Wang, Shivaram Venkataraman, Amar Phanishayee, Nikhil Devanur, Jorgen Thelin, and Ion Stoica. 2020. Blink: Fast and Generic Collectives for Distributed ML. In MLSys."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Hong Zhang Junxue Zhang Wei Bai Kai Chen and Mosharaf Chowdhury. 2017. Resilient Datacenter Load Balancing in the Wild. In SIGCOMM.","DOI":"10.1145\/3098822.3098841"},{"key":"e_1_3_2_1_46_1","volume-title":"Mohamad Haj Yahia, and Ming Zhang","author":"Zhu Yibo","year":"2015","unstructured":"Yibo Zhu, Haggai Eran, Daniel Firestone, Chuanxiong Guo, Marina Lipshteyn, Yehonatan Liron, Jitendra Padhye, Shachar Raindel, Mohamad Haj Yahia, and Ming Zhang. 2015. Congestion Control for Large-Scale RDMA Deployments. In SIGCOMM."}],"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 ACM SIGCOMM 2024 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3651890.3672252","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3651890.3672252","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3651890.3672252","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3651890.3672252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:49:13Z","timestamp":1750268953000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3651890.3672252"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,4]]},"references-count":46,"alternative-id":["10.1145\/3651890.3672252","10.1145\/3651890"],"URL":"https:\/\/doi.org\/10.1145\/3651890.3672252","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"}}]}}