{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:19:13Z","timestamp":1740133153368,"version":"3.37.3"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022YFB4500402"]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2027","62302251"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["BX20230193"],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tpds.2024.3396849","type":"journal-article","created":{"date-parts":[[2024,5,6]],"date-time":"2024-05-06T17:45:54Z","timestamp":1715017554000},"page":"1221-1238","source":"Crossref","is-referenced-by-count":0,"title":["Graph-Centric Performance Analysis for Large-Scale Parallel Applications"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2358-3395","authenticated-orcid":false,"given":"Yuyang","family":"Jin","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4605-148X","authenticated-orcid":false,"given":"Haojie","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8654-0192","authenticated-orcid":false,"given":"Runxin","family":"Zhong","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9045-9269","authenticated-orcid":false,"given":"Chen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6823-758X","authenticated-orcid":false,"given":"Xia","family":"Liao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1983-7321","authenticated-orcid":false,"given":"Feng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Data Engineering and Knowledge Engineering (MOE), School of Information, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7656-6428","authenticated-orcid":false,"given":"Jidong","family":"Zhai","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"181","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters","volume-title":"Proc. USENIX Conf. Annu. Tech. Conf.","author":"Zhang"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356209"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-020-0169-8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-022-1546-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1048935.1050204"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2010.18"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1556"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68564-7_9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/1094342006064482"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1553"},{"article-title":"mpiP: Lightweight, scalable mpi profiling","year":"2024","author":"Vetter","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.47"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2012.120"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2012.321"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00032"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/511399.511364"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/1094342016661865"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/0217079"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00104"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751240"},{"key":"ref23","article-title":"Execution-cache-memory performance model: Introduction and validation","author":"Hofmann","year":"2015","journal-title":"arXiv:1509.03118"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-39589-0_1"},{"key":"ref26","first-page":"1","article-title":"The igraph software package for complex network research","volume":"1695","author":"Csardi","year":"2006","journal-title":"Int. J. Complex Syst."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.2172\/983318"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1086\/504594"},{"article-title":"LAMMPS","year":"2013","author":"Atomic","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1149"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.728"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1177\/1094342015593158"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1088\/0953-8984\/21\/39\/395502"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3460357"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-010-0120-5"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356219"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374538"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5555\/977395.977673"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.46"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330358"},{"volume-title":"VTune Performance Analyzer","year":"2005","author":"Reinders","key":"ref42"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356173"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.14529\/jsfi140207"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/872726.806987"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16012-2_2"},{"article-title":"CrayPat-Cray X1 performance analysis tool","year":"2003","author":"Kaufmann","key":"ref48"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5222553"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/1693453.1693489"},{"key":"ref52","first-page":"527","article-title":"wPerf: Generic Off-CPU analysis to identify bottleneck waiting events","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Des. Implementation","author":"Zhou"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370238"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3579990.3580010"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356168"},{"key":"ref56","first-page":"561","article-title":"Spindle: Informed memory access monitoring","volume-title":"Proc. USENIX Conf. Annu. Tech. Conf.","author":"Wang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.17"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3093234"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00034"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10530517\/10521459.pdf?arnumber=10521459","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T17:33:20Z","timestamp":1716226400000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10521459\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":54,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2024.3396849","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"type":"print","value":"1045-9219"},{"type":"electronic","value":"1558-2183"},{"type":"electronic","value":"2161-9883"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}