{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:44:31Z","timestamp":1768031071047,"version":"3.49.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"The National Key Research and Development Program of China","award":["2018YFB0204400"],"award-info":[{"award-number":["2018YFB0204400"]}]},{"name":"The National Key Research and Development Program of China","award":["XDC01030000"],"award-info":[{"award-number":["XDC01030000"]}]},{"name":"The National Key Research and Development Program of China","award":["XDC05010100"],"award-info":[{"award-number":["XDC05010100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62032023"],"award-info":[{"award-number":["62032023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972377"],"award-info":[{"award-number":["61972377"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702483"],"award-info":[{"award-number":["61702483"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CAS","award":["QYZDJ-SSW-JSC035"],"award-info":[{"award-number":["QYZDJ-SSW-JSC035"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2021,9,1]]},"DOI":"10.1109\/tpds.2021.3067731","type":"journal-article","created":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T19:57:35Z","timestamp":1616443055000},"page":"2367-2380","source":"Crossref","is-referenced-by-count":20,"title":["Optimizing the LINPACK Algorithm for Large-Scale PCIe-Based CPU-GPU Heterogeneous Systems"],"prefix":"10.1109","volume":"32","author":[{"given":"Guangming","family":"Tan","sequence":"first","affiliation":[{"name":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4008-0036","authenticated-orcid":false,"given":"Chaoyang","family":"Shui","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinshan","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianzhi","family":"Yu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujin","family":"Yan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2015.50"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/0909042"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.14529\/jsfi150405"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33518-1_40"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s00450-011-0161-5"},{"issue":"3\/4","key":"ref6","first-page":"153","article-title":"Optimized HPL for AMD GPU and multi-core CPU usage","volume-title":"Comput. Sci.","volume":"26","author":"Bach","year":"2011"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23400-2_52"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-53065-7_102"},{"key":"ref9","article-title":"David Rohr. High Performance Linpack for GPUs (HPL-GPU)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0096-3003(86)90126-8"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.3110"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-06548-9_1"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.1994.1108"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/AICCSA.2011.6126599"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470353"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470353"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1513895.1513901"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2005.42"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2013.86"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.113"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1362622.1362664"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-29400-7_35"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2321742"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2012.242"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304626"},{"key":"ref28","first-page":"45","article-title":"Qilin: Exploiting parallelism on heterogeneous multiprocessors with adaptive mapping","volume-title":"Proc. 42nd Annu. IEEE\/ACM Int. Symp. Microarchit.","author":"Luk"},{"key":"ref29","article-title":"Some issues in dense linear algebra for multicore and special purpose architectures","author":"Marc","year":"2008"},{"key":"ref30","article-title":"End-to-end high-speed ethernet and infiniband interconnect solutions"},{"key":"ref33","author":"Petitet","journal-title":"HPL\u2014A Portable Implementation of the High-Performance Linpack Benchmark for Distributed-Memory Computers"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1377612.1377615"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2015.89"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC-CSS-ICESS.2015.17"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85451-7_79"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2010.5470941"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2012.23"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2013.6702619"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2312005.2312025"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304625"},{"key":"ref43","article-title":"A comparison of lookahead and algorithmic blocking techniques for parallel matrix factorization","volume-title":"Tech. Rep. TR-CS-98\u201307","author":"Strazdins","year":"1998"},{"key":"ref45","first-page":"1","article-title":"Fast implementation of DGEMM on fermi GPU","volume-title":"Proc. Int. Conf. High Perform. Comput., Netw., Storage Anal.","author":"Tan"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2009.12.005"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.4330020102"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5214359"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2010.12"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9380848\/09382911.pdf?arnumber=9382911","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T04:43:42Z","timestamp":1715229822000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9382911\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,1]]},"references-count":44,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2021.3067731","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,1]]}}}