{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T10:13:17Z","timestamp":1767262397286,"version":"3.37.3"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272155","61932010"],"award-info":[{"award-number":["62272155","61932010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/tpds.2023.3317535","type":"journal-article","created":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T17:48:56Z","timestamp":1695232136000},"page":"2978-2993","source":"Crossref","is-referenced-by-count":3,"title":["UMA-MF: A Unified Multi-CPU\/GPU Asynchronous Computing Framework for SGD-Based Matrix Factorization"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8808-7718","authenticated-orcid":false,"given":"Yizhi","family":"Huang","sequence":"first","affiliation":[{"name":"Key Laboratory for Embedded and Network Computing of Hunan Province, College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1849-6991","authenticated-orcid":false,"given":"Yan","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory for Embedded and Network Computing of Hunan Province, College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6292-3730","authenticated-orcid":false,"given":"Yang","family":"Bai","sequence":"additional","affiliation":[{"name":"Key Laboratory for Embedded and Network Computing of Hunan Province, College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9030-3969","authenticated-orcid":false,"given":"Si","family":"Chen","sequence":"additional","affiliation":[{"name":"Key Laboratory for Embedded and Network Computing of Hunan Province, College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4573-7375","authenticated-orcid":false,"given":"Renfa","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory for Embedded and Network Computing of Hunan Province, College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020426"},{"year":"2021","key":"ref35","article-title":"Intel memory latency checker v3.10"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2507157.2507164"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICPPW.2014.34"},{"article-title":"NOMAD: Non-locking, stochastic multi-machine algorithm for asynchronous and decentralized matrix completion","year":"2013","author":"yun","key":"ref15"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240369"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2012.120"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"year":"2017","key":"ref31","article-title":"Baidu-allreduce"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HCS49909.2020.9220622"},{"article-title":"HOGWILD!: A lock-free approach to parallelizing stochastic gradient descent","year":"2011","author":"niu","key":"ref11"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2015.7095789"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3472456.3472520"},{"year":"2017","key":"ref32","article-title":"Intel performance counter monitor - a better way to measure CPU utilization"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11251"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959165"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2718515"},{"key":"ref39","first-page":"30","article-title":"The architecture of the Nehalem processor and Nehalem-EP SMP platforms","volume":"3","author":"thomadakis","year":"2011","journal-title":"Resource"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1248"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3078597.3078602"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00169"},{"key":"ref24","first-page":"195","article-title":"Authentication of sub-NUMA clustering effect on Intel Skylake for memory latency and bandwidth","volume":"12","author":"mohapatra","year":"2021","journal-title":"Turkish Journal of Computer and Mathematics Education"},{"article-title":"ALX: Large scale matrix factorization on TPUs","year":"2021","author":"mehta","key":"ref46"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1964179.1964194"},{"key":"ref45","article-title":"The Netflix prize","author":"bennett","year":"2007","journal-title":"Proc KDD Cup Workshop"},{"year":"2009","key":"ref26","article-title":"ATI crossfire pro user guide"},{"year":"2011","key":"ref25","article-title":"SLI best practices"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911489"},{"year":"2021","key":"ref20","article-title":"3rd gen Intel Xeon scalable processors"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638950"},{"key":"ref41","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9063103"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225135"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2018.8310173"},{"key":"ref43","first-page":"4120","article-title":"Asynchronous stochastic gradient descent with delay compensation","author":"zheng","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"journal-title":"NVIDIA DGX-1 System Architecture White Paper","year":"2017","key":"ref28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2017.37"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230560"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3106879"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186009"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911417"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.2975196"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2890117"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3019181"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053164"},{"key":"ref40","first-page":"1","article-title":"Intel 64 and IA-32 architectures software developer's manual","volume":"3","author":"intel","year":"2016","journal-title":"System Programming Guide"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10248992\/10256153.pdf?arnumber=10256153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:28:12Z","timestamp":1698085692000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10256153\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":47,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2023.3317535","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":[[2023,11]]}}}