{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T17:41:44Z","timestamp":1767980504644,"version":"3.49.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"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":[],"published-print":{"date-parts":[[2024,10,2]]},"DOI":"10.1109\/nof62948.2024.10741492","type":"proceedings-article","created":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T18:37:56Z","timestamp":1730918276000},"page":"115-123","source":"Crossref","is-referenced-by-count":3,"title":["Efficient Task Scheduling and Allocation of GPU Resources in Clouds"],"prefix":"10.1109","author":[{"given":"Hoda","family":"Sedighi","sequence":"first","affiliation":[{"name":"Concordia University,Concordia Institute for Information Systems Engineering (CIISE),Montreal,Canada"}]},{"given":"Fetahi","family":"Wuhib","sequence":"additional","affiliation":[{"name":"Ericsson Canada,Ericsson Research,Montreal,Canada"}]},{"given":"Roch","family":"Glitho","sequence":"additional","affiliation":[{"name":"Concordia University,Concordia Institute for Information Systems Engineering (CIISE),Montreal,Canada"}]}],"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":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Weng"},{"key":"ref2","first-page":"515","article-title":"HiveD: Sharing a GPU cluster for deep learning with guarantees","volume-title":"14th USENIX symposium on operating systems design and implementation (OSDI 20)","author":"Zhao"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3115630"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IC2E55432.2022.00030"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563510"},{"key":"ref6","article-title":"Serving dnn models with multi-instance gpus: A case of the reconfigurable machine scheduling problem","author":"Tan","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3136245"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/jos.75"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2883906"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2018.00041"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2018.10.005"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2678373.2665702"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3093336.3037742"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2313342"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASPDAC.2014.6742976"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2014.6974717"},{"key":"ref17","volume-title":"Multi-process service","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3288702"},{"key":"ref19","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"},{"key":"ref20","article-title":"Dominant resource fairness: Fair allocation of multiple resource types","volume-title":"8th USENIX symposium on networked systems design and implementation (NSDI 11)","author":"Ghodsi"},{"key":"ref21","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","volume-title":"16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19)","author":"Gu"},{"key":"ref22","first-page":"289","article-title":"Themis: Fair and efficient GPU cluster scheduling","volume-title":"17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","author":"Mahajan"},{"key":"ref23","volume-title":"Resource Management for Pods and Containers","year":"2023"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1145\/2872362.2872368","article-title":"Baymax: Qos awareness and increased utilization for non-preemptive accelerators in warehouse scale computers","volume-title":"Proceedings of the Twenty-First International Conference on Architectural Support for Programming Languages and Operating Systems","author":"Chen"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1145\/3037697.3037700","article-title":"Prophet: Precise qos prediction on non-preemptive accelerators to improve utilization in warehouse-scale computers","volume-title":"Proceedings of the Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems","author":"Chen"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tpds.2021.3079202"},{"key":"ref27","volume-title":"device-plugins","year":"2024"},{"key":"ref28","volume-title":"NVIDIA A100 Tensor Core GPU Architecture","year":"2021"},{"key":"ref29","volume-title":"NVIDIA Multi-Instance GPU User Guide","year":"2024"}],"event":{"name":"2024 15th International Conference on Network of the Future (NoF)","location":"Castelldefels, Spain","start":{"date-parts":[[2024,10,2]]},"end":{"date-parts":[[2024,10,4]]}},"container-title":["2024 15th International Conference on Network of the Future (NoF)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10741364\/10741354\/10741492.pdf?arnumber=10741492","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T13:38:03Z","timestamp":1732714683000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10741492\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,2]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/nof62948.2024.10741492","relation":{},"subject":[],"published":{"date-parts":[[2024,10,2]]}}}