{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T15:58:54Z","timestamp":1786463934928,"version":"build-2736575974"},"reference-count":48,"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":[{"name":"Ericsson\/ENCQOR-5G Senior Industrial Research Chair on Cloud and Edge Computing for 5G and Beyond"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw. Serv. Manage."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tnsm.2025.3635529","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T18:45:52Z","timestamp":1763577952000},"page":"1112-1127","source":"Crossref","is-referenced-by-count":2,"title":["Dynamic Task Scheduling and Adaptive GPU Resource Allocation in the Cloud"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6382-0796","authenticated-orcid":false,"given":"Hoda","family":"Sedighi","sequence":"first","affiliation":[{"name":"Concordia Institute of Information System Engineering, Concordia University, Montreal, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8394-9569","authenticated-orcid":false,"given":"Fetahi","family":"Wuhib","sequence":"additional","affiliation":[{"name":"Ericsson Research, Ericsson, Montreal, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7699-0296","authenticated-orcid":false,"given":"Roch H.","family":"Glitho","sequence":"additional","affiliation":[{"name":"Concordia Institute of Information System Engineering, Concordia University, Montreal, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","first-page":"515","article-title":"HiveD: Sharing a GPU cluster for deep learning with guarantees","volume-title":"Proc. 14th USENIX Symp. Oper. Syst. Design Implement. (OSDI)","author":"Zhao"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2024.3393114"},{"key":"ref4","first-page":"947","article-title":"{USHER}: Holistic interference avoidance for resource optimized {ML} inference","volume-title":"Proc. 18th USENIX Symp. Oper. Syst. Design Implement. (OSDI)","author":"Shubha"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3115630"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IC2E55432.2022.00030"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563510"},{"key":"ref8","article-title":"Serving DNN models with multi-instance GPUs: A case of the reconfigurable machine scheduling problem","author":"Tan","year":"2021","journal-title":"arXiv:2109.11067"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3136245"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/jos.75"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/NoF62948.2024.10741492"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2883906"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2018.00041"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2018.10.005"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2678373.2665702"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3093336.3037742"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2313342"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASPDAC.2014.6742976"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2014.6974717"},{"key":"ref20","volume-title":"Multi-process service","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2025.3553137"},{"key":"ref22","first-page":"161","article-title":"Zico: Efficient GPU memory sharing for concurrent DNN training","volume-title":"Proc. USENIX Annu. Tech. Conf. (USENIX ATC)","author":"Lim"},{"key":"ref23","article-title":"MuxFlow: Efficient and safe GPU sharing in large-scale production deep learning clusters","author":"Zhao","year":"2023","journal-title":"arXiv:2303.13803"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607054"},{"key":"ref25","first-page":"1","article-title":"Hardware compute partitioning on NVIDIA GPUs for composable systems","volume-title":"Proc. 37th Euromicro Conf. Real-Time Syst. (ECRTS)","author":"Bakita"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3652892.3654792"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2025.3570847"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3288702"},{"key":"ref29","first-page":"69","article-title":"Transparent GPU sharing in container clouds for deep learning workloads","volume-title":"Proc. 20th USENIX Symp. Netw. Syst. Design Implement. (NSDI)","author":"Wu"},{"key":"ref30","first-page":"323","article-title":"Dominant resource fairness: Fair allocation of multiple resource types","volume-title":"Proc. 8th USENIX Symp. Netw. Syst. Design Implement. (NSDI)","author":"Ghodsi"},{"key":"ref31","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)","author":"Gu"},{"key":"ref32","first-page":"289","article-title":"Themis: Fair and efficient GPU cluster scheduling","volume-title":"Proc. 17th USENIX Symp. Netw. Syst. Design Implement. (NSDI)","author":"Mahajan"},{"key":"ref33","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3696355.3696361"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3721145.3728488"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICUIS64676.2024.10866186"},{"key":"ref37","first-page":"1","article-title":"Pollux: Co-adaptive cluster scheduling for goodput-optimized deep learning","volume-title":"Proc. 15th USENIX Symp. Oper. Syst. Design Implement.","author":"Qiao"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2023.3264242"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3559690"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMSCS.2018.2795543"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607095"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3716845"},{"key":"ref43","volume-title":"Resource management for pods and containers","year":"2023"},{"key":"ref44","first-page":"681","article-title":"Baymax: QoS awareness and increased utilization for non-preemptive accelerators in warehouse scale computers","volume-title":"Proc. 21st Int. Conf. Archit. Support Programming Lang. Oper. Syst","author":"Chen"},{"key":"ref45","first-page":"17","article-title":"Prophet: Precise QoS prediction on non-preemptive accelerators to improve utilization in warehouse-scale computers","volume-title":"Proc. 22nd Int. Conf. Archit. Support Programming Lang. Oper. Syst","author":"Chen"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3079202"},{"key":"ref47","volume-title":"Device-plugins","year":"2024"},{"key":"ref48","volume-title":"Alibaba cluster trace","year":"2023"}],"container-title":["IEEE Transactions on Network and Service Management"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4275028\/11319294\/11261404.pdf?arnumber=11261404","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:01:15Z","timestamp":1768255275000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11261404\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tnsm.2025.3635529","relation":{},"ISSN":["1932-4537","2373-7379"],"issn-type":[{"value":"1932-4537","type":"electronic"},{"value":"2373-7379","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}