{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T15:53:06Z","timestamp":1781193186310,"version":"3.54.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62372426"],"award-info":[{"award-number":["62372426"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62132019"],"award-info":[{"award-number":["62132019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"China Mobile \u201cJoint Innovation+\u201d Research Program"},{"DOI":"10.13039\/501100001809","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["2023481"],"award-info":[{"award-number":["2023481"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/ton.2025.3635222","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T18:47:33Z","timestamp":1764701253000},"page":"1865-1881","source":"Crossref","is-referenced-by-count":1,"title":["Resource-Aware Distributed Training Job Placement for GPU Cluster Defragmentation"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1311-8908","authenticated-orcid":false,"given":"Gongming","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8312-8409","authenticated-orcid":false,"given":"Yichen","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3831-4577","authenticated-orcid":false,"given":"Hongli","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4222-1971","authenticated-orcid":false,"given":"Jin","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Yao","sequence":"additional","affiliation":[{"name":"Huawei Technologies Company Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9471-5223","authenticated-orcid":false,"given":"Baoyi","family":"An","sequence":"additional","affiliation":[{"name":"Huawei Technologies Company Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7329-5291","authenticated-orcid":false,"given":"Gangyi","family":"Luo","sequence":"additional","affiliation":[{"name":"China Mobile (Suzhou) Software Technology Company Ltd., Suzhou, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chu","family":"Xu","sequence":"additional","affiliation":[{"name":"China Mobile (Suzhou) Software Technology Company Ltd., Suzhou, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016","journal-title":"arXiv:1609.08144"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113679"},{"key":"ref3","article-title":"LaMDA: Language models for dialog applications","author":"Thoppilan","year":"2022","journal-title":"arXiv:2201.08239"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3003307"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508399"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488678"},{"key":"ref7","article-title":"MegaScale: Scaling large language model training to more than 10,000 GPUs","author":"Jiang","year":"2024","journal-title":"arXiv:2402.15627"},{"key":"ref8","first-page":"945","article-title":"MLaaS in the wild: Workload analysis and scheduling in large-scale heterogeneous GPU clusters","volume-title":"Proc. 19th USENIX Symp. Netw. Syst. Design Implement. (NSDI)","author":"Weng"},{"key":"ref9","first-page":"1","article-title":"Pollux: Co-adaptive cluster scheduling for goodput-optimized deep learning","volume-title":"Proc. 15th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Qiao"},{"key":"ref10","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","volume-title":"Proc. 16th USENIX Symp. Netw. Syst. Design Implement. (NSDI 19)","author":"Gu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575721"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3305753"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796910"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00056"},{"key":"ref15","volume-title":"Maximize System Throughput With NVIDIA NVLink","year":"2025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1402946.1402967"},{"key":"ref17","first-page":"995","article-title":"Beware of fragmentation: Scheduling GPU-sharing workloads with fragmentation gradient descent","volume-title":"Proc. USENIX Annu. Tech. Conf. (USENIX ATC)","author":"Weng"},{"key":"ref18","first-page":"579","article-title":"Looking beyond GPUs for DNN scheduling on multi-tenant clusters","volume-title":"Proc. 16th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Mohan"},{"key":"ref19","first-page":"1","article-title":"Characterization and prediction of deep learning workloads in large-scale GPU datacenters","volume-title":"Proc. SC21: Int. Conf. High Perform. Comput., Netw., Storage Anal.","author":"Hu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3587445"},{"key":"ref21","first-page":"515","article-title":"HiveD: Sharing a GPU cluster for deep learning with guarantees","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Zhao"},{"key":"ref22","first-page":"721","article-title":"Elastic resource sharing for distributed deep learning","volume-title":"Proc. 18th USENIX Symp. Netw. Syst. Design Implement. (NSDI)","author":"Hwang"},{"key":"ref23","article-title":"Bandwidth reduction using importance weighted pruning on ring AllReduce","author":"Cheng","year":"2019","journal-title":"arXiv:1901.01544"},{"key":"ref24","volume-title":"NVIDIA Collective Communications Library (NCCL)","year":"2025"},{"key":"ref25","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv:1706.02677"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3091475"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539700382820"},{"issue":"2","key":"ref28","first-page":"159","article-title":"The gurobi optimizer","volume":"41","author":"Bixby","year":"2007","journal-title":"Transp. Res. B"},{"key":"ref29","first-page":"719","article-title":"HeteroSketch: Coordinating network-wide monitoring in heterogeneous and dynamic networks","volume-title":"Proc. 19th USENIX Symp. Netw. Syst. Design Implement. (NSDI)","author":"Agarwal"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/0201010"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796938"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139177801.004"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1287\/moor.3.3.177"},{"key":"ref34","first-page":"709","article-title":"Characterization of large language model development in the datacenter","volume-title":"Proc. 21st USENIX Symp. Netw. Syst. Design Implement. (NSDI)","author":"Hu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672239"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/PDSW-DISCS.2018.00011"},{"key":"ref37","first-page":"1421","article-title":"Towards domain-specific network transport for distributed DNN training","volume-title":"Proc. 21st USENIX Symp. Netw. Syst. Design Implement. (NSDI)","author":"Wang"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","volume-title":"CIFAR-100 (Canadian Institute for Advanced Research)","author":"Krizhevsky","year":"2025"},{"key":"ref40","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"arXiv:1409.1556"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3244794"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref43","volume-title":"Index of Algorithms Provided by Gloo and Their Semantics","year":"2025"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-023-04098-4"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3219261"},{"key":"ref46","first-page":"785","article-title":"Scaling distributed machine learning with in-network aggregation","volume-title":"Proc. 18th USENIX Symp. Netw. Syst. Design Implement. (NSDI)","author":"Sapio"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267840"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-021-05553-3"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9014110"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155445"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544224"},{"key":"ref52","first-page":"1403","article-title":"CASSINI: Network-aware job scheduling in machine learning clusters","volume-title":"Proc. 21st USENIX Symp. Netw. Syst. Design Implement. (NSDI)","author":"Rajasekaran"},{"key":"ref53","article-title":"Themis: Fair and efficient GPU cluster scheduling","author":"Mahajan","year":"2019","journal-title":"arXiv:1907.01484"},{"key":"ref54","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Xiao"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2023.3336540"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11317935\/11271823.pdf?arnumber=11271823","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T21:59:53Z","timestamp":1768255193000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11271823\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/ton.2025.3635222","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}