{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T11:34:25Z","timestamp":1770464065576,"version":"3.49.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T00:00:00Z","timestamp":1668124800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T00:00:00Z","timestamp":1668124800000},"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":[[2022,11,11]]},"DOI":"10.1109\/ipccc55026.2022.9894345","type":"proceedings-article","created":{"date-parts":[[2022,10,12]],"date-time":"2022-10-12T19:51:26Z","timestamp":1665604286000},"page":"120-129","source":"Crossref","is-referenced-by-count":2,"title":["PickyMan: A Preemptive Scheduler for Deep Learning Jobs on GPU Clusters"],"prefix":"10.1109","author":[{"given":"Chen","family":"Chen","sequence":"first","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingwen","family":"Chen","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoyun","family":"Chen","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianchen","family":"Han","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangtao","family":"Xue","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","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"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2931558"},{"key":"ref3","first-page":"1","article-title":"Characterization and prediction of deep learning workloads in large-scale gpu datacenters","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Hu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387555"},{"key":"ref5","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"},{"key":"ref6","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":"ref7","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref9","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":"ref10","article-title":"Pollux: Co-adaptive cluster scheduling for goodput-optimized deep learning","volume-title":"15th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 21)","author":"Qiao"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387547"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486978"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0022289"},{"key":"ref14","first-page":"267","article-title":"{PACMan}: Coordinated memory caching for parallel jobs","volume-title":"9th USENIX Symposium on Networked Systems Design and Implementation (NSDI 12)","author":"Ananthanarayanan"},{"key":"ref15","article-title":"A study of checkpointing in large scale training of deep neural networks","author":"Rojas","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IRI.2013.6642536"},{"key":"ref17","first-page":"481","article-title":"{Heterogeneity-Aware} cluster scheduling policies for deep learning workloads","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Narayanan"},{"key":"ref18","article-title":"Nccl 2.0","volume-title":"GPU Technology Conference (GTC)","volume":"2","author":"Jeaugey"},{"key":"ref19","article-title":"Bringing hpc techniques to deep learning","volume-title":"Tech. Rep","author":"Gibiansky","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920931"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"}],"event":{"name":"2022 IEEE International Performance, Computing, and Communications Conference (IPCCC)","location":"Austin, TX, USA","start":{"date-parts":[[2022,11,11]]},"end":{"date-parts":[[2022,11,13]]}},"container-title":["2022 IEEE International Performance, Computing, and Communications Conference (IPCCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9894293\/9894294\/09894345.pdf?arnumber=9894345","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:26:02Z","timestamp":1705958762000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9894345\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,11]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/ipccc55026.2022.9894345","relation":{},"subject":[],"published":{"date-parts":[[2022,11,11]]}}}