{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T07:10:51Z","timestamp":1750749051018,"version":"3.37.3"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":["2022YFB4500304"],"award-info":[{"award-number":["2022YFB4500304"]}]},{"name":"Guangdong Province Special Support Program for Cultivating High-Level Talents","award":["2021TQ06X160"],"award-info":[{"award-number":["2021TQ06X160"]}]},{"name":"Pazhou Lab Research Project","award":["PZL2023KF0001"],"award-info":[{"award-number":["PZL2023KF0001"]}]},{"name":"Fundamental Research Funds for the Central Universities, Sun Yat-sen University","award":["23xkjc016"],"award-info":[{"award-number":["23xkjc016"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tpds.2024.3432620","type":"journal-article","created":{"date-parts":[[2024,7,23]],"date-time":"2024-07-23T18:25:06Z","timestamp":1721759106000},"page":"2177-2192","source":"Crossref","is-referenced-by-count":2,"title":["Sophisticated Orchestrating Concurrent DLRM Training on CPU\/GPU Platform"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6582-0877","authenticated-orcid":false,"given":"Rui","family":"Tian","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1417-3012","authenticated-orcid":false,"given":"Jiazhi","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4707-9492","authenticated-orcid":false,"given":"Jiangsu","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5582-1031","authenticated-orcid":false,"given":"Dan","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutong","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015941"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00047"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00044"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2017.46"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS46320.2019.00042"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/isca59077.2024.00081"},{"year":"2024","key":"ref8","article-title":"Multi-process service documentation"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00324"},{"key":"ref10","first-page":"412","article-title":"Distributed hierarchical GPU parameter server for massive scale deep learning ADS systems","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Zhao"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00084"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00047"},{"key":"ref13","first-page":"161","article-title":"Zico: Efficient $\\lbrace${GPU $\\rbrace$} memory sharing for concurrent $\\lbrace${ DNN$\\rbrace$} training","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Lim"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid54584.2022.00078"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480127"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD53106.2021.00056"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid49817.2020.00-66"},{"key":"ref18","first-page":"533","article-title":"$\\lbrace${AntMan $\\rbrace$}: Dynamic scaling on $\\lbrace${ GPU$\\rbrace$} clusters for deep learning","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Des. Implementation","author":"Xiao"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00072"},{"issue":"1","key":"ref20","first-page":"105","article-title":"PaddlePaddle: An open-source deep learning platform from industrial practice","volume":"1","author":"Ma","year":"2019","journal-title":"Front. Data Domputing"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26347"},{"article-title":"FLEN: Leveraging field for scalable CTR prediction","year":"2019","author":"Chen","key":"ref22"},{"article-title":"Click-through rate prediction","year":"2024","author":"Steve Wang","key":"ref23"},{"year":"2024","key":"ref24","article-title":"Real-time performance monitoring, done right!"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417050"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2022.102954"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463117"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5346"},{"article-title":"Deep learning recommendation model for personalization and recommendation systems","year":"2019","author":"Naumov","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3124749.3124754"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/10670174\/10607952.pdf?arnumber=10607952","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T06:07:09Z","timestamp":1727330829000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10607952\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":32,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2024.3432620","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":[[2024,11]]}}}