{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T23:46:12Z","timestamp":1783035972686,"version":"3.54.6"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T00:00:00Z","timestamp":1763164800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T00:00:00Z","timestamp":1763164800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2336886"],"award-info":[{"award-number":["CNS-2336886"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,15]]},"DOI":"10.1109\/ipccc66453.2025.11304653","type":"proceedings-article","created":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T18:36:35Z","timestamp":1767033395000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["Exploiting ML Task Correlation in the Minimization of Capital Expense for GPU Data Centers"],"prefix":"10.1109","author":[{"given":"Srinivasan","family":"Subramaniyan","sequence":"first","affiliation":[{"name":"The Ohio State University,Department of Electrical and Computer Engineering,Columbus,Ohio,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaorui","family":"Wang","sequence":"additional","affiliation":[{"name":"The Ohio State University,Department of Electrical and Computer Engineering,Columbus,Ohio,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2015.152"},{"key":"ref2","article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","author":"Abadi","year":"2016","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1452"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC47752.2019.9042047"},{"key":"ref8","article-title":"Analysis of large-scale multi-tenant gpu clusters for dnn training workloads","author":"Jeon","year":"2019","journal-title":"ATC"},{"key":"ref9","article-title":"Deep learning workload scheduling in gpu datacenters: Taxonomy, challenges and vision","author":"Gao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Synergy: Resource sensitive dnn scheduling in multitenant clusters","author":"Mohan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421284"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605609"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737460"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS54860.2022.00039"},{"key":"ref15","article-title":"Characterization and prediction of deep learning workloads in large-scale gpu datacenters","author":"Hu","year":"2021","journal-title":"SC"},{"key":"ref16","article-title":"Pipeswitch: Fast pipelined context switching for deep learning applications","author":"Bai","year":"2020","journal-title":"OSDI"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS60910.2024.00051"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3754598.3754670"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCS48705.2020.9074444"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tpds.2015.2421492"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2014.6848207"},{"key":"ref22","article-title":"Pulp: a linear programming toolkit for python","volume-title":"The University of Auckland","volume":"65","author":"Mitchell","year":"2011"},{"key":"ref23","volume-title":"NVIDIA System Management Interface","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546769"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"ref27","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref29","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688232"},{"key":"ref32","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Characterizing power management opportunities for 11 ms in the cloud","author":"Patel","year":"2024","journal-title":"ASPLOS"},{"key":"ref34","article-title":"Beware of fragmentation: Scheduling {GPU-Sharing} workloads with fragmentation gradient descent","author":"Weng","year":"2023","journal-title":"(ATC)"},{"key":"ref35","volume-title":"Amazon","year":"2024"},{"key":"ref36","article-title":"Towards {GPU} utilization prediction for cloud deep learning","author":"Yeung","year":"2020","journal-title":"HotCloud"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486978"},{"key":"ref38","article-title":"Mlaas in the wild: Workload analysis and scheduling in large-scale heterogeneous gpu clusters","author":"Weng","year":"2022","journal-title":"NSDI 2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3326285.3329074"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0022289"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155445"},{"key":"ref42","article-title":"Gandiva: Introspective cluster scheduling for deep learning","author":"Xiao","year":"2018","journal-title":"OSDI"},{"key":"ref43","article-title":"Heterogeneity-aware cluster scheduling policies for deep learning workloads","author":"Narayanan","year":"2020","journal-title":"OSDI"}],"event":{"name":"2025 IEEE International Performance, Computing, and Communications Conference (IPCCC)","location":"Austin, TX, USA","start":{"date-parts":[[2025,11,15]]},"end":{"date-parts":[[2025,11,23]]}},"container-title":["2025 IEEE International Performance, Computing, and Communications Conference (IPCCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11304598\/11304625\/11304653.pdf?arnumber=11304653","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T06:40:51Z","timestamp":1767076851000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11304653\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/ipccc66453.2025.11304653","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]}}}