{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T23:19:41Z","timestamp":1768519181827,"version":"3.49.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"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":"publisher","award":["62402141"],"award-info":[{"award-number":["62402141"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2025A1515011785,2023A1515110271"],"award-info":[{"award-number":["2025A1515011785,2023A1515110271"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,14]]},"DOI":"10.1109\/icpads67057.2025.11323192","type":"proceedings-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:36:54Z","timestamp":1768423014000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["DynGPU: A Dynamic GPU Sharing Framework for Enhanced Resource Utilization and Task Scheduling in Concurrent DNN Training"],"prefix":"10.1109","author":[{"given":"Zhiji","family":"Yu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology,Shenzhen,China"}]},{"given":"Desheng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology,Shenzhen,China"}]},{"given":"Weizhe","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology,Shenzhen,China"}]},{"given":"Sichao","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science, Harbin Institute of Technology,Harbin,China"}]},{"given":"Meng","family":"Hao","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science, Harbin Institute of Technology,Harbin,China"}]},{"given":"Yu-Chu","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Queensland University of Technology,Brisbane,Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref3","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref4","first-page":"4189","article-title":"Recurrent highway networks","volume-title":"International conference on machine learning","author":"Zilly","year":"2017"},{"issue":"59","key":"ref5","first-page":"1","article-title":"Kernel approximation methods for speech recognition","volume":"20","author":"May","year":"2019","journal-title":"Journal of Machine Learning Research"},{"key":"ref6","first-page":"945","article-title":"Mlaas in the wild: Workload analysis and scheduling in large-scale heterogeneous gpu clusters","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Weng","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3097287"},{"key":"ref8","first-page":"533","article-title":"Antman: Dynamic scaling on gpu clusters for deep learning","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Xiao","year":"2020"},{"key":"ref9","volume-title":"Cuda multi-process service"},{"key":"ref10","first-page":"69","article-title":"Transparent gpu sharing in container clouds for deep learning workloads","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Wu","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629578"},{"key":"ref12","first-page":"539","article-title":"Microsecond-scale preemption for concurrent gpu-accelerated dnn inferences","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Han","year":"2022"},{"key":"ref13","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Xiao","year":"2018"},{"key":"ref14","article-title":"Salus: Fine-grained gpu sharing primitives for deep learning applications","author":"Yu","year":"2019","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"443","article-title":"Serving dnns like clockwork: Performance predictability from the bottom up","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Gujarati","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330351"},{"key":"ref17","volume-title":"Nvidia multi-instance gpu (mig)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3617995"},{"key":"ref19","first-page":"199","article-title":"Serving heterogeneous machine learning models on multi-gpu servers with spatio-temporal sharing","volume-title":"2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Choi","year":"2022"},{"key":"ref20","first-page":"995","article-title":"Beware of fragmentation: Scheduling gpu-sharing workloads with fragmentation gradient descent","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Weng","year":"2023"},{"key":"ref21","article-title":"Muxflow: Efficient and safe gpu sharing in large-scale production deep learning clusters","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS60453.2023.00410"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS53394.2021.00086"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-6168-2_6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"}],"event":{"name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","location":"Hefei, China","start":{"date-parts":[[2025,12,14]]},"end":{"date-parts":[[2025,12,18]]}},"container-title":["2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11322805\/11322871\/11323192.pdf?arnumber=11323192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:28:28Z","timestamp":1768462108000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11323192\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icpads67057.2025.11323192","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]}}}