{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T12:07:54Z","timestamp":1763381274056,"version":"3.45.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2313164"],"award-info":[{"award-number":["2313164"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Meta faculty research award"},{"name":"Intel Fast Forward award"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,17]]},"DOI":"10.1145\/3772356.3772425","type":"proceedings-article","created":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T12:02:48Z","timestamp":1763380968000},"page":"160-167","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["One to Many: Closing the Bandwidth Gap in AI Datacenters with Scalable Multicast"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4443-3863","authenticated-orcid":false,"given":"Sepehr","family":"Abdous","sequence":"first","affiliation":[{"name":"Johns Hopkins University, Baltimore, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5156-3825","authenticated-orcid":false,"given":"Jinqi","family":"Lu","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4875-1104","authenticated-orcid":false,"given":"Jiacheng","family":"Wan","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2529-5381","authenticated-orcid":false,"given":"Erfan","family":"Sharafzadeh","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, USA"},{"name":"Meta, New York, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2736-5694","authenticated-orcid":false,"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meta, San Francisco, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1331-1372","authenticated-orcid":false,"given":"Soudeh","family":"Ghorbani","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, USA"},{"name":"Meta, New York, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,11,17]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2020. OMNeT++ Simulator. https:\/\/omnetpp.org\/."},{"key":"e_1_3_2_1_2_1","unstructured":"2022. Multicast Group Capacity: Extreme Comes Out on Top. https:\/\/bit.ly\/2H5sQ1n."},{"key":"e_1_3_2_1_3_1","unstructured":"2024. Double Binary Tree Documentation. https:\/\/developer.nvidia.com\/blog\/massively-scale-deep-learning-training-nccl-2-4\/."},{"key":"e_1_3_2_1_4_1","unstructured":"2024. NVIDIA Collective Communications Library (NCCL). https:\/\/developer.nvidia.com\/nccl."},{"key":"e_1_3_2_1_5_1","unstructured":"2024. NVLink and NVLink Switch. https:\/\/www.nvidia.com\/en-us\/data-center\/nvlink\/."},{"key":"e_1_3_2_1_6_1","unstructured":"2025. State of AI Infrastructure Report. https:\/\/www.flexential.com\/resources\/report\/2025-state-ai-infrastructure."},{"key":"e_1_3_2_1_7_1","volume-title":"Tempus: Probabilistic Network Latency Verification","author":"Abdous Sepehr","year":"2024","unstructured":"Sepehr Abdous, Senapati Diwangkara, and Soudeh Ghorbani. 2024. Tempus: Probabilistic Network Latency Verification. IEEE Access (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"Practical Packet Deflection in Datacenters. PACMNET","author":"Abdous Sepehr","year":"2023","unstructured":"Sepehr Abdous, Erfan Sharafzadeh, and Soudeh Ghorbani. 2023. Practical Packet Deflection in Datacenters. PACMNET (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"MEB: An Efficient and Accurate Multicast using Bloom Filter with Customized Hash Function. In APNeT.","author":"Chen Zihao","year":"2023","unstructured":"Zihao Chen, Jiawei Huang, Qile Wang, Jingling Liu, Zhaoyi Li, Shengwen Zhou, and Zhidong He. 2023. MEB: An Efficient and Accurate Multicast using Bloom Filter with Customized Hash Function. In APNeT."},{"key":"e_1_3_2_1_10_1","volume-title":"Multicast Routing in Datagram Internetworks and Extended LANs. TOCS","author":"Deering Stephen E","year":"1990","unstructured":"Stephen E Deering and David R Cheriton. 1990. Multicast Routing in Datagram Internetworks and Extended LANs. TOCS (1990)."},{"key":"e_1_3_2_1_11_1","volume-title":"Yeti: Stateless and Generalized Multicast Forwarding. In NSDI.","author":"Diab Khaled","year":"2022","unstructured":"Khaled Diab and Mohamed Hefeeda. 2022. Yeti: Stateless and Generalized Multicast Forwarding. In NSDI."},{"key":"e_1_3_2_1_12_1","volume-title":"Orca: Server-assisted Multicast for Datacenter Networks. In NSDI.","author":"Diab Khaled","year":"2022","unstructured":"Khaled Diab, Parham Yassini, and Mohamed Hefeeda. 2022. Orca: Server-assisted Multicast for Datacenter Networks. In NSDI."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Vince Fuller Tony Li Jessica Yu and Kannan Varadhan. 1993. Classless Inter-Domain Routing (CIDR): An Address Assignment and Aggregation Strategy. Technical Report.","DOI":"10.17487\/rfc1519"},{"key":"e_1_3_2_1_14_1","volume-title":"Guilherme Goes, Hany Morsy, Rohit Puri, Mohammad Riftadi, Ashmitha Jeevaraj Shetty, Jingyi Yang, et al.","author":"Gangidi Adithya","year":"2024","unstructured":"Adithya Gangidi, Rui Miao, Shengbao Zheng, Sai Jayesh Bondu, Guilherme Goes, Hany Morsy, Rohit Puri, Mohammad Riftadi, Ashmitha Jeevaraj Shetty, Jingyi Yang, et al. 2024. RDMA over Ethernet for Distributed Training at Meta Scale. In SIGCOMM."},{"key":"e_1_3_2_1_15_1","volume-title":"AI and Memory Wall","author":"Gholami Amir","unstructured":"Amir Gholami, Zhewei Yao, Sehoon Kim, Coleman Hooper, Michael W Mahoney, and Kurt Keutzer. 2024. AI and Memory Wall. In IEEE Micro."},{"key":"e_1_3_2_1_16_1","volume-title":"Li Erran Li, and Marina Thottan","author":"He Keqiang","year":"2015","unstructured":"Keqiang He, Junaid Khalid, Sourav Das, Aaron Gember-Jacobson, Chaithan Prakash, Aditya Akella, Li Erran Li, and Marina Thottan. 2015. Latency in Software Defined Networks: Measurements and Mitigation Techniques. In SIGMETRICS."},{"key":"e_1_3_2_1_17_1","volume-title":"Li Erran Li, and Marina Thottan","author":"He Keqiang","year":"2015","unstructured":"Keqiang He, Junaid Khalid, Aaron Gember-Jacobson, Sourav Das, Chaithan Prakash, Aditya Akella, Li Erran Li, and Marina Thottan. 2015. Measuring Control Plane Latency in SDN-enabled Switches. In SOSR."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Jiawei Huang Zihao Chen Yiting Wang Hui Li Zhaoyi Li Qile Wang Sitan Li Zhidong He and Wanchun Jiang. 2024. Achieving High Efficiency for Datacenter Multicast using Skewed Bloom Filter. In ICPP.","DOI":"10.1145\/3673038.3673126"},{"key":"e_1_3_2_1_19_1","volume-title":"Steiner Tree Problems. Networks","author":"Hwang Frank K","year":"1992","unstructured":"Frank K Hwang and Dana S Richards. 1992. Steiner Tree Problems. Networks (1992)."},{"key":"e_1_3_2_1_20_1","volume-title":"Somaya Arianfar, and Pekka Nikander.","author":"Jokela Petri","year":"2009","unstructured":"Petri Jokela, Andr\u00e1s Zahemszky, Christian Esteve Rothenberg, Somaya Arianfar, and Pekka Nikander. 2009. LIPSIN: Line Speed Publish\/Subscribe Inter-Networking. SIGCOMM Computer Communication Review (2009)."},{"key":"e_1_3_2_1_21_1","volume-title":"A Survey: Control Plane Scalability Issues and Approaches in Software-Defined Networking (SDN). Computer Networks","author":"Karakus Murat","year":"2017","unstructured":"Murat Karakus and Arjan Durresi. 2017. A Survey: Control Plane Scalability Issues and Approaches in Software-Defined Networking (SDN). Computer Networks (2017)."},{"key":"e_1_3_2_1_22_1","volume-title":"Flow Setup Latency in SDN Networks. JSAC","author":"Khalili Ramin","year":"2018","unstructured":"Ramin Khalili, Zoran Despotovic, and Artur Hecker. 2018. Flow Setup Latency in SDN Networks. JSAC (2018)."},{"key":"e_1_3_2_1_23_1","volume-title":"Marcin Chrapek, Rami Nudelman, Gil Bloch, and Torsten Hoefler.","author":"Khalilov Mikhail","year":"2024","unstructured":"Mikhail Khalilov, Salvatore Di Girolamo, Marcin Chrapek, Rami Nudelman, Gil Bloch, and Torsten Hoefler. 2024. Network-Offloaded Bandwidth-Optimal Broadcast and Allgather for Distributed AI. In SC."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Dan Li Henggang Cui Yan Hu Yong Xia and Xin Wang. 2011. Scalable Datacenter Multicast using Multi-class Bloom Filter. In ICNP.","DOI":"10.1109\/ICNP.2011.6089061"},{"key":"e_1_3_2_1_25_1","volume-title":"ESM: Efficient and Scalable Datacenter Multicast Routing. ToN","author":"Li Dan","year":"2011","unstructured":"Dan Li, Yuanjie Li, Jianping Wu, Sen Su, and Jiangwei Yu. 2011. ESM: Efficient and Scalable Datacenter Multicast Routing. ToN (2011)."},{"key":"e_1_3_2_1_26_1","volume-title":"Cepheus: Accelerating Datacenter Applications with High-performance RoCE-capable Multicast. In HPCA.","author":"Li Wenxue","year":"2024","unstructured":"Wenxue Li, Junyi Zhang, Yufei Liu, Gaoxiong Zeng, Zilong Wang, Chaoliang Zeng, Pengpeng Zhou, Qiaoling Wang, and Kai Chen. 2024. Cepheus: Accelerating Datacenter Applications with High-performance RoCE-capable Multicast. In HPCA."},{"key":"e_1_3_2_1_27_1","volume-title":"Yan Zhuang, Fei Feng, Lingbo Tang, Zheng Cao, Ming Zhang, Frank Kelly, Mohammad Alizadeh, et al.","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, et al. 2019. HPCC: High Precision Congestion Control. In SIGCOMM."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Kun Qian Yongqing Xi Jiamin Cao Jiaqi Gao Yichi Xu Yu Guan Binzhang Fu Xuemei Shi Fangbo Zhu and Rui Miao. 2024. Alibaba HPN: A Datacenter Network for Large Language Model Training. In SIGCOMM.","DOI":"10.1145\/3651890.3672265"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342066"},{"key":"e_1_3_2_1_30_1","volume-title":"Han Wang, Rachit Agarwal, and Hakim Weatherspoon.","author":"Shrivastav Vishal","year":"2019","unstructured":"Vishal Shrivastav, Asaf Valadarsky, Hitesh Ballani, Paolo Costa, Ki Suh Lee, Han Wang, Rachit Agarwal, and Hakim Weatherspoon. 2019. Shoal: A Network Architecture for Disaggregated Racks. In NSDI."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Samuel Steffen Timon Gehr Petar Tsankov Laurent Vanbever and Martin Vechev. 2020. Probabilistic Verification of Network Configurations. In SIGCOMM.","DOI":"10.1145\/3387514.3405900"},{"key":"e_1_3_2_1_32_1","volume-title":"MCCS: A Service-based Approach to Collective Communication for Multi-Tenant Cloud. In SIGCOMM.","author":"Wu Yongji","year":"2024","unstructured":"Yongji Wu, Yechen Xu, Jingrong Chen, Zhaodong Wang, Ying Zhang, Matthew Lentz, and Danyang Zhuo. 2024. MCCS: A Service-based Approach to Collective Communication for Multi-Tenant Cloud. In SIGCOMM."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Zhen Zhang Chaokun Chang Haibin Lin Yida Wang Raman Arora and Xin Jin. 2020. Is Network the Bottleneck of Distributed Training?. In NetAI.","DOI":"10.1145\/3405671.3405810"},{"key":"e_1_3_2_1_34_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":"HotNets '25: 24th ACM Workshop on Hot Topics in Networks","location":"UMD Campus College Park MD USA","acronym":"HotNets '25","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the 24th ACM Workshop on Hot Topics in Networks"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772356.3772425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T12:03:11Z","timestamp":1763380991000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772356.3772425"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,17]]},"references-count":34,"alternative-id":["10.1145\/3772356.3772425","10.1145\/3772356"],"URL":"https:\/\/doi.org\/10.1145\/3772356.3772425","relation":{},"subject":[],"published":{"date-parts":[[2025,11,17]]},"assertion":[{"value":"2025-11-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}