{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T08:39:44Z","timestamp":1782895184633,"version":"3.54.5"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017223","name":"National Energy Research Scientific Computing Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017223","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006132","name":"Office of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006132","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,25]]},"DOI":"10.1109\/ipdps65963.2026.00078","type":"proceedings-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T20:55:16Z","timestamp":1782852916000},"page":"899-912","source":"Crossref","is-referenced-by-count":0,"title":["Characterizing Production GPU Workloads using System-wide Telemetry Data"],"prefix":"10.1109","author":[{"given":"Onur","family":"Cankur","sequence":"first","affiliation":[{"name":"University of Maryland,Department of Computer Science,College Park,Maryland,USA,20742"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian","family":"Austin","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Laboratory,NERSC,Berkeley,California,USA,94720"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dhruva","family":"Kulkarni","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Laboratory,NERSC,Berkeley,California,USA,94720"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhinav","family":"Bhatele","sequence":"additional","affiliation":[{"name":"University of Maryland,Department of Computer Science,College Park,Maryland,USA,20742"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS63350.2024.00097"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-32041-5_16"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00093"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3514245"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.18"},{"key":"ref6","article-title":"Nvidia data center gpu manager (dcgm)","year":"2023"},{"key":"ref7","article-title":"Slurm workload manager","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ProTools56701.2022.00007"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SCW63240.2024.00180"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3488423.3519336"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759815"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/(sici)1097-024x(200006)30:7<723::aid-spe314>3.0.co;2-5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2002.1137727"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2016.58"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2018.00070"},{"key":"ref16","article-title":"Analytics of longitudinal system monitoring data for performance prediction","author":"Costello","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-61756-5_6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-43659-3_9"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126935"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00040"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00096"},{"key":"ref22","article-title":"Arcode: Hpc application recognition through image-encoded monitoring data","author":"Li","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-96983-1_7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78713-4_11"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.12.001"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59851-8_18"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/Cluster48925.2021.00086"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2022.102950"},{"key":"ref29","first-page":"533","article-title":"On the diversity of cluster workloads and its impact on research results","volume-title":"2018 USENIX Annual Technical Conference (USENIX ATC 18)","author":"Amvrosiadis"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132772"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2015.60"},{"key":"ref32","article-title":"Analysis and lessons from a publicly available google cluster trace","volume-title":"Tech. Rep. UCB\/EECS-2010-95","volume":"94","author":"Chen","year":"2010"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1773394.1773400"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2391229.2391236"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2012.6402895"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2012.35"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/sc.2016.77"},{"issue":"4","key":"ref38","first-page":"411","article-title":"Understanding application performance via micro-benchmarks on three large supercomputers: Intrepid, Ranger and Jaguar","volume-title":"Int. J. High Perform. Comput. Appl","volume":"24","author":"Bhatele","year":"2010"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3708035.3736010"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356183"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3603166.3632137"},{"key":"ref42","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"}],"event":{"name":"2026 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","location":"New Orleans, LA, USA","start":{"date-parts":[[2026,5,25]]},"end":{"date-parts":[[2026,5,29]]}},"container-title":["2026 IEEE International Parallel and Distributed Processing Symposium (IPDPS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11575315\/11575316\/11575343.pdf?arnumber=11575343","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T07:27:58Z","timestamp":1782890878000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11575343\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,25]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/ipdps65963.2026.00078","relation":{},"subject":[],"published":{"date-parts":[[2026,5,25]]}}}