{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T08:26:18Z","timestamp":1778228778571,"version":"3.51.4"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2015,9,1]],"date-time":"2015-09-01T00:00:00Z","timestamp":1441065600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61133005"],"award-info":[{"award-number":["61133005"]}],"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":["61432005"],"award-info":[{"award-number":["61432005"]}],"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":["61370095"],"award-info":[{"award-number":["61370095"]}],"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":["61472124"],"award-info":[{"award-number":["61472124"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hunan Science and Technology Commission","award":["2013sk2014"],"award-info":[{"award-number":["2013sk2014"]}]},{"name":"Hunan Provincial Education Department","award":["13A011"],"award-info":[{"award-number":["13A011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2015,9,1]]},"DOI":"10.1109\/tc.2014.2366731","type":"journal-article","created":{"date-parts":[[2014,11,24]],"date-time":"2014-11-24T14:42:24Z","timestamp":1416840144000},"page":"2623-2636","source":"Crossref","is-referenced-by-count":115,"title":["Performance Optimization Using Partitioned SpMV on GPUs and Multicore CPUs"],"prefix":"10.1109","volume":"64","author":[{"given":"Wangdong","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenli","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyao","family":"Mo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keqin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2012.95"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2012.96"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.2896"},{"key":"ref36","author":"davis","year":"2009"},{"key":"ref35","first-page":"36","author":"johnson","year":"1993","journal-title":"Univariate Discrete Distributions"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2308221"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2013.09.001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654078"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503234"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CIT.2010.208"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1016\/j.jpdc.2009.04.002","article-title":"Optimization of a lattice boltzmann computation on state-of-the-art multicore platforms","volume":"69","author":"williams","year":"2009","journal-title":"J Parallel Distrib Comput"},{"key":"ref15","first-page":"80","article-title":"Exact sparse matrix vector multiplication on GPU’s and multicore architectures","author":"boyer","year":"0","journal-title":"Proc 4th Int Workshop Parallel Symbolic Comput"},{"key":"ref16","first-page":"721","article-title":"Reduced-bandwidth multithreaded algorithms for sparse matrix-vector multiplication","author":"buluc","year":"0","journal-title":"Proc IEEE Int Parallel Distrib Process Symp"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2011.2161389"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"1539","DOI":"10.1016\/j.jpdc.2013.07.017","article-title":"Sparse matrix-vector multiplication on the single-chip cloud computer many-core processor","volume":"73","author":"c","year":"2013","journal-title":"J Parallel Distrib Comput"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1080\/17445760802337010"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2012.290"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2012.132"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"806","DOI":"10.1016\/j.parco.2011.08.004","article-title":"Two-dimensional cache-oblivious sparse matrix vector multiplication","volume":"37","author":"n","year":"2011","journal-title":"Parallel Comput"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1145\/1816038.1816021","article-title":"Debunking the 100X GPU versus CPU myth: An evaluation of throughput computing on CPU and GPU","volume":"38","author":"lee","year":"0","journal-title":"Proc Int Symp Comput Arch"},{"key":"ref6","article-title":"Clearspeed whitepaper: Accelerating the intel math kernel library","author":"gustafson","year":"0"},{"key":"ref29","article-title":"A performance modeling and optimization analysis tool for sparse matrix vector multiplication on GPUs","volume":"25","author":"chen","year":"0","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"ref5","year":"0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882364"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/1094342013501126"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SASP.2010.5521144"},{"key":"ref9","year":"2012"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2007.70811"},{"key":"ref20","article-title":"New row-grouped CSR format for storing the sparse matrices on GPU with implementation in CUDA","author":"oberhuber","year":"2010"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2008.12.006"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1542275.1542294"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1693453.1693471"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/978-3-642-11515-8_10","article-title":"Automatically tuning sparse matrix vector multiplication for GPU architectures","author":"monakov","year":"2010","journal-title":"High Performance Embedded Architectures and Compilers"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2012.211"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2011.91"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/7180479\/06965639.pdf?arnumber=6965639","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:41:31Z","timestamp":1641987691000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6965639\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,9,1]]},"references-count":36,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tc.2014.2366731","relation":{},"ISSN":["0018-9340"],"issn-type":[{"value":"0018-9340","type":"print"}],"subject":[],"published":{"date-parts":[[2015,9,1]]}}}