{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T23:48:39Z","timestamp":1783036119133,"version":"3.54.6"},"reference-count":21,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2016,7,1]],"date-time":"2016-07-01T00:00:00Z","timestamp":1467331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Bench-testing Environment for Automated Software Tuning (BEAST)","award":["#SHF-1320603"],"award-info":[{"award-number":["#SHF-1320603"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"Department of Energy","doi-asserted-by":"publisher","award":["#DE-SC0010042"],"award-info":[{"award-number":["#DE-SC0010042"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007065","name":"NVIDIA Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2016,7,1]]},"DOI":"10.1109\/tpds.2015.2481890","type":"journal-article","created":{"date-parts":[[2015,9,24]],"date-time":"2015-09-24T14:31:23Z","timestamp":1443105083000},"page":"2036-2048","source":"Crossref","is-referenced-by-count":36,"title":["Implementation and Tuning of Batched Cholesky Factorization and Solve for NVIDIA GPUs"],"prefix":"10.1109","volume":"27","author":[{"given":"Jakub","family":"Kurzak","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hartwig","family":"Anzt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Gates","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jack","family":"Dongarra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Sparse direct solvers with accelerators over DAG runtimes","author":"lacoste","year":"2012"},{"key":"ref11","first-page":"813","author":"villa","year":"0","journal-title":"Euro-Par"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2013.6702656"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC.2014.30"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2014.52"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2688500.2688534"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/1094342014567546"},{"key":"ref17","year":"0","journal-title":"NVIDIA CUDA CUBLAS Library Programming Guide"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719604"},{"key":"ref19","year":"0","journal-title":"NVIDIA CUDA TOOLKIT 7 0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.22"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2011.311"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/1094342013518807"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF02321405"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.3.001780"},{"key":"ref7","volume":"77","author":"ma","year":"2011","journal-title":"Computational Lithography"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/1094342015580139"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2010.5470941"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.44"},{"key":"ref20","article-title":"Intel Math Kernel Library for Linux OS","year":"0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.2005.7"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/7488924\/07275187.pdf?arnumber=7275187","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:45:29Z","timestamp":1641987929000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7275187\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,7,1]]},"references-count":21,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2015.2481890","relation":{},"ISSN":["1045-9219"],"issn-type":[{"value":"1045-9219","type":"print"}],"subject":[],"published":{"date-parts":[[2016,7,1]]}}}