{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:33:22Z","timestamp":1787013202523,"version":"build-2736575974"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tkde.2022.3221426","type":"journal-article","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T15:36:03Z","timestamp":1668180963000},"page":"1-14","source":"Crossref","is-referenced-by-count":3,"title":["TENSILE: A Tensor Granularity Dynamic GPU Memory Scheduling Method Toward Multiple Dynamic Workloads System"],"prefix":"10.1109","author":[{"given":"Kaixin","family":"Zhang","sequence":"first","affiliation":[{"name":"Computer Science and Technology, Harbin Institute of Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7521-2871","authenticated-orcid":false,"given":"Hongzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Harbin Institute of Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Hu","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Harbin Institute of Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songling","family":"Zou","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Harbin Institute of Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiye","family":"Qiu","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Harbin Institute of Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tongxin","family":"Li","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Harbin Institute of Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhishun","family":"Wang","sequence":"additional","affiliation":[{"name":"School of engineering, The Chinese University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452838"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.14778\/3342263.3342644"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378505"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196909"},{"key":"ref30","article-title":"Densely connected convolutional networks","author":"huang","year":"2016"},{"key":"ref11","first-page":"481","article-title":"Heterogeneity-aware cluster scheduling policies for deep learning workloads","author":"narayanan","year":"2020","journal-title":"Proc 14th USENIX Conf Oper Syst Des Implementation"},{"key":"ref10","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","author":"xiao","year":"2018","journal-title":"Proc 13th USENIX Conf Oper Syst Des Implementation"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref1","first-page":"1071","article-title":"A survey of deep learning and its applications: A new paradigm to machine learning","volume":"7","author":"dargan","year":"2019","journal-title":"Arch Comput Methods Eng"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3200691.3178491"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"ref19","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref24","article-title":"Efficient memory management for GPU-based deep learning systems","author":"zhang","year":"2019"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref26","article-title":"The exponentially weighted moving average","author":"perry","year":"2010","journal-title":"Wiley Encyclopedia in Operational Research and Management Science"},{"key":"ref25","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc 12th USENIX Symp Oper Syst Des Implementation"},{"key":"ref20","first-page":"200","article-title":"Dynamic memory management for GPU-based training of deep neural networks","author":"shrirams","year":"2019","journal-title":"Proc IEEE Int Parallel Distrib Process Symp"},{"key":"ref22","first-page":"3859","article-title":"Dynamic routing between capsules","author":"sabour","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref21","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref27","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.14778\/3229863.3236258"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3187009.3177737"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/DSN-W.2018.00022"},{"key":"ref4","article-title":"Language models are few-shot learners","author":"brown","year":"2020"},{"key":"ref3","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.14778\/2752939.2752942"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3369583.3392684"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/4358933\/09946405.pdf?arnumber=9946405","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,7]],"date-time":"2023-07-07T18:13:40Z","timestamp":1688753620000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9946405\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/tkde.2022.3221426","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}