{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:47:44Z","timestamp":1783439264755,"version":"3.54.6"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702254"],"award-info":[{"award-number":["61702254"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61832005"],"award-info":[{"award-number":["61832005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072230"],"award-info":[{"award-number":["62072230"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1811461"],"award-info":[{"award-number":["U1811461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"},{"name":"Alibaba Innovative Research Program","award":["Alibaba Group"],"award-info":[{"award-number":["Alibaba Group"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tpds.2021.3138825","type":"journal-article","created":{"date-parts":[[2021,12,28]],"date-time":"2021-12-28T21:04:51Z","timestamp":1640725491000},"page":"1-1","source":"Crossref","is-referenced-by-count":56,"title":["Liquid: Intelligent Resource Estimation and Network-Efficient Scheduling for Deep Learning Jobs on Distributed GPU Clusters"],"prefix":"10.1109","author":[{"given":"Rong","family":"Gu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuquan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haipeng","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guihai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Che","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihua","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"CIFAR-10","year":"2009"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref31","article-title":"ml-20m","year":"2015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/447"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"ref36","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref34","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref10","article-title":"OpenPAI","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2017.4451224"},{"key":"ref12","first-page":"499","article-title":"PipeSwitch: Fast pipelined context switching for deep learning applications","author":"bai","year":"2020","journal-title":"Proc 14th USENIX Symp Oper Syst Des Implementation"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2038916.2038921"},{"key":"ref14","first-page":"1","article-title":"Pollux: Co-adaptive cluster scheduling for goodput-optimized deep learning","author":"qiao","year":"2021","journal-title":"Proc 15th USENIX Symp Oper Syst Des Implementation"},{"key":"ref15","first-page":"721","article-title":"Elastic resource sharing for distributed deep learning","author":"hwang","year":"2021","journal-title":"Proc 18th USENIX Symp Netw Syst Des Implementation"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref17","first-page":"515","article-title":"HiveD: Sharing a GPU cluster for deep learning with guarantees","author":"zhao","year":"2020","journal-title":"Proc 14th USENIX Symp Oper Syst Des Implementation"},{"key":"ref18","first-page":"1","article-title":"Salus: Fine-grained GPU sharing primitives for deep learning applications","author":"yu","year":"2020","journal-title":"Proc 3rd Conf Mach Learn Syst"},{"key":"ref19","first-page":"1","article-title":"Plink: Discovering and exploiting datacenter network locality for efficient cloud-based distributed training","author":"luo","year":"2020","journal-title":"Proc 3rd Conf Mach Learn Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF00226291"},{"key":"ref4","article-title":"TensorFlow","year":"2015"},{"key":"ref27","first-page":"481","article-title":"Heterogeneity-aware cluster scheduling policies for deep learning workloads","author":"narayanan","year":"2020","journal-title":"Proc 14th USENIX Symp Oper Syst Des Implementation"},{"key":"ref3","first-page":"947","article-title":"Analysis of large-scale multi-tenant GPU clusters for DNN training workloads","author":"jeon","year":"2019","journal-title":"Proc 28th USENIX Annu Tech Conf"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"ref29","article-title":"Notes on convolutional neural networks","author":"bouvrie","year":"2006"},{"key":"ref5","article-title":"PyTorch","year":"2016"},{"key":"ref8","article-title":"Bringing HPC Techniques to Deep Learning","year":"2021"},{"key":"ref7","first-page":"463","article-title":"A unified architecture for accelerating distributed DNN training in heterogeneous GPU\/CPU clusters","author":"jiang","year":"2020","journal-title":"Proc 14th USENIX Symp Oper Syst Des Implementation"},{"key":"ref2","article-title":"MNIST","year":"1998"},{"key":"ref9","first-page":"1","article-title":"Accelerated training for CNN distributed deep learning through automatic resource-aware layer placement","volume":"58","author":"park","year":"2019","journal-title":"Comput Res Repository"},{"key":"ref1","first-page":"1","article-title":"Theano: A CPU and GPU math expression compiler","author":"bergstra","year":"2010","journal-title":"Proc 9th Python Sci Comput Conf"},{"key":"ref20","article-title":"Kubernetes","year":"2014"},{"key":"ref22","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","author":"xiao","year":"2018","journal-title":"Proc 13th USENIX Symp Oper Syst Des Implementation"},{"key":"ref21","article-title":"Kubeflow","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3361525.3361538"},{"key":"ref23","first-page":"533","article-title":"Antman: Dynamic scaling on GPU clusters for deep learning","author":"xiao","year":"2020","journal-title":"Proc 14th USENIX Symp Oper Syst Des Implementation"},{"key":"ref26","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","author":"gu","year":"2019","journal-title":"Proc 16th USENIX Symp Netw Syst Des Implementation"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737460"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/4359390\/09664375.pdf?arnumber=9664375","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,26]],"date-time":"2022-05-26T16:03:27Z","timestamp":1653581007000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9664375\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/tpds.2021.3138825","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}