{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:26:31Z","timestamp":1783095991497,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T00:00:00Z","timestamp":1713312000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,27]]},"DOI":"10.1145\/3617232.3624863","type":"proceedings-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T20:10:56Z","timestamp":1713384656000},"page":"420-434","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Training Job Placement in Clusters with Statistical In-Network Aggregation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3722-8493","authenticated-orcid":false,"given":"Bohan","family":"Zhao","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9271-0223","authenticated-orcid":false,"given":"Wei","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3546-4070","authenticated-orcid":false,"given":"Shuo","family":"Liu","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd., Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2492-6719","authenticated-orcid":false,"given":"Yang","family":"Tian","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd., Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5788-6082","authenticated-orcid":false,"given":"Qiaoling","family":"Wang","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd., Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1357-3137","authenticated-orcid":false,"given":"Wenfei","family":"Wu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"A scalable, commodity data center network architecture. ACM SIGCOMM computer communication review 38, 4","author":"Al-Fares Mohammad","year":"2008","unstructured":"Mohammad Al-Fares, Alexander Loukissas, and Amin Vahdat. 2008. A scalable, commodity data center network architecture. ACM SIGCOMM computer communication review 38, 4 (2008), 63--74."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1851182.1851192"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737460"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486422"},{"key":"e_1_3_2_1_5_1","volume-title":"Max-min flow control. Data Networks","author":"Bertsekas D","year":"1987","unstructured":"D Bertsekas and R Gallager. 1987. Max-min flow control. Data Networks (1987), 448--455."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446760"},{"key":"e_1_3_2_1_7_1","first-page":"3","article-title":"Camdoop: Exploiting In-network Aggregation for Big Data Applications","volume":"12","author":"Costa Paolo","year":"2012","unstructured":"Paolo Costa, Austin Donnelly, Antony IT Rowstron, and Greg O'Shea. 2012. Camdoop: Exploiting In-network Aggregation for Big Data Applications.. In NSDI, Vol. 12. 3--3.","journal-title":"NSDI"},{"key":"e_1_3_2_1_8_1","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Crankshaw Daniel","year":"2017","unstructured":"Daniel Crankshaw, Xin Wang, Guilio Zhou, Michael J Franklin, Joseph E Gonzalez, and Ion Stoica. 2017. Clipper: A {Low-Latency} online prediction serving system. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17). 613--627."},{"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","DOI":"10.1109\/TNET.2023.3244794"},{"key":"e_1_3_2_1_11_1","volume-title":"PANAMA: In-network Aggregation for Shared Machine Learning Clusters. In Conference on Machine Learning and Systems (MLSys)","author":"Gebara Nadeen","year":"2021","unstructured":"Nadeen Gebara, Paolo Costa, and Manya Ghobadi. 2021. PANAMA: In-network Aggregation for Shared Machine Learning Clusters. In Conference on Machine Learning and Systems (MLSys) 2021. https:\/\/www.microsoft.com\/en-us\/research\/publication\/panama-in-network-aggregation-for-shared-machine-learning-clusters\/"},{"key":"e_1_3_2_1_12_1","first-page":"829","article-title":"In-network Aggregation for Shared Machine Learning Clusters","volume":"3","author":"Gebara Nadeen","year":"2021","unstructured":"Nadeen Gebara, Manya Ghobadi, and Paolo Costa. 2021. In-network Aggregation for Shared Machine Learning Clusters. Proceedings of Machine Learning and Systems 3 (2021), 829--844.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMHPC.2016.006"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2626334"},{"key":"e_1_3_2_1_15_1","volume-title":"Gurobi: The Fastest Solver. https:\/\/www.gurobi.com\/.","year":"2022","unstructured":"Gurobi. 2022. Gurobi: The Fastest Solver. https:\/\/www.gurobi.com\/."},{"key":"e_1_3_2_1_16_1","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Han Mingcong","year":"2022","unstructured":"Mingcong Han, Hanze Zhang, Rong Chen, and Haibo Chen. 2022. Microsecond-scale preemption for concurrent {GPU-accelerated}{DNN} inferences. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). 539--558."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575708"},{"key":"e_1_3_2_1_18_1","volume-title":"Elastic Resource Sharing for Distributed Deep Learning. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Hwang Changho","year":"2021","unstructured":"Changho Hwang, Taehyun Kim, Sunghyun Kim, Jinwoo Shin, and KyoungSoo Park. 2021. Elastic Resource Sharing for Distributed Deep Learning. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21). USENIX Association, 721--739. https:\/\/www.usenix.org\/conference\/nsdi21\/presentation\/hwang"},{"key":"e_1_3_2_1_19_1","volume-title":"2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Jeon Myeongjae","year":"2019","unstructured":"Myeongjae Jeon, Shivaram Venkataraman, Amar Phanishayee, Junjie Qian, Wencong Xiao, and Fan Yang. 2019. Analysis of large-scale multi-tenant GPU clusters for DNN training workloads. In 2019 USENIX Annual Technical Conference (USENIX ATC 19). 947--960."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00085"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2006.879410"},{"key":"e_1_3_2_1_22_1","volume-title":"ATP: In-network Aggregation for Multi-tenant Learning. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","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 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21). USENIX Association, 741--761. https:\/\/www.usenix.org\/conference\/nsdi21\/presentation\/lao"},{"key":"e_1_3_2_1_23_1","volume-title":"Fat-trees: universal networks for hardware-efficient supercomputing","author":"Leiserson Charles E","year":"1985","unstructured":"Charles E Leiserson. 1985. Fat-trees: universal networks for hardware-efficient supercomputing. IEEE transactions on Computers 100, 10 (1985), 892--901."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"e_1_3_2_1_25_1","volume-title":"Alexander J Smola, Amr Ahmed, Vanja Josifovski, James Long, Eugene J Shekita, and Bor-Yiing Su.","author":"Li Mu","year":"2014","unstructured":"Mu Li, David G Andersen, Jun Woo Park, Alexander J Smola, Amr Ahmed, Vanja Josifovski, James Long, Eugene J Shekita, and Bor-Yiing Su. 2014. Scaling distributed machine learning with the parameter server. In 11th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 14). 583--598."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322259"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582037"},{"key":"e_1_3_2_1_28_1","volume-title":"Themis: Fair and Efficient GPU Cluster Scheduling. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","author":"Mahajan Kshiteej","year":"2020","unstructured":"Kshiteej Mahajan, Arjun Balasubramanian, Arjun Singhvi, Shivaram Venkataraman, Aditya Akella, Amar Phanishayee, and Shuchi Chawla. 2020. Themis: Fair and Efficient GPU Cluster Scheduling. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20). 289--304."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2674005.2674996"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"e_1_3_2_1_31_1","unstructured":"Netsack. 2021. NetPack Source Code. https:\/\/anonymous.4open.science\/r\/ATP-Controller-35D4."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"e_1_3_2_1_34_1","unstructured":"David Pisinger. 1995. Algorithms for knapsack problems. (1995)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSAI.2012.6223460"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152461"},{"key":"e_1_3_2_1_37_1","volume-title":"Dan RK Ports, and Peter Richt\u00e1rik","author":"Sapio Amedeo","year":"2019","unstructured":"Amedeo Sapio, Marco Canini, Chen-Yu Ho, Jacob Nelson, Panos Kalnis, Changhoon Kim, Arvind Krishnamurthy, Masoud Moshref, Dan RK Ports, and Peter Richt\u00e1rik. 2019. Scaling distributed machine learning with in-network aggregation. arXiv preprint arXiv:1903.06701 (2019)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2009.2013894"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTCOMP.2017.7947053"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421296"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3127490"},{"key":"e_1_3_2_1_43_1","volume-title":"Dynamic Pricing and Placement for Distributed Machine Learning Jobs. In 2020 6th International Conference on Big Data Computing and Communications (BIGCOM). IEEE, 152--160","author":"Zhang Xueying","year":"2020","unstructured":"Xueying Zhang, Ruiting Zhou, John CS Lui, and Zongpeng Li. 2020. Dynamic Pricing and Placement for Distributed Machine Learning Jobs. In 2020 6th International Conference on Big Data Computing and Communications (BIGCOM). IEEE, 152--160."},{"key":"e_1_3_2_1_44_1","volume-title":"Enabling Switch Memory Management for Distributed Training with In-Network Aggregation. In IEEE INFOCOM 2023-IEEE conference on computer communications. IEEE.","author":"Zhao Bohan","year":"2023","unstructured":"Bohan Zhao, Chang Liu, Jianbo Dong, Zheng Cao, Wei Nie, and Wenfei Wu. 2023. Enabling Switch Memory Management for Distributed Training with In-Network Aggregation. In IEEE INFOCOM 2023-IEEE conference on computer communications. IEEE."},{"key":"e_1_3_2_1_45_1","volume-title":"NetRPC: Enabling In-Network Computation in Remote Procedure Calls. arXiv preprint arXiv:2212.08362","author":"Zhao Bohan","year":"2022","unstructured":"Bohan Zhao, Wenfei Wu, and Wei Xu. 2022. NetRPC: Enabling In-Network Computation in Remote Procedure Calls. arXiv preprint arXiv:2212.08362 (2022)."}],"event":{"name":"ASPLOS '24: 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","location":"La Jolla CA USA","acronym":"ASPLOS '24","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","SIGOPS ACM Special Interest Group on Operating Systems","SIGPLAN ACM Special Interest Group on Programming Languages","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3617232.3624863","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3617232.3624863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:14Z","timestamp":1750178774000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3617232.3624863"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,17]]},"references-count":45,"alternative-id":["10.1145\/3617232.3624863","10.1145\/3617232"],"URL":"https:\/\/doi.org\/10.1145\/3617232.3624863","relation":{},"subject":[],"published":{"date-parts":[[2024,4,17]]},"assertion":[{"value":"2024-04-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}