{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T01:20:34Z","timestamp":1755998434880,"version":"3.37.3"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["#1642441: SI2-SSE: BONSAI"],"award-info":[{"award-number":["#1642441: SI2-SSE: BONSAI"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"An Open Software Infrastructure for Parallel Autotuning of Computational Kernels"},{"DOI":"10.13039\/100000015","name":"Department of Energy","doi-asserted-by":"crossref","award":["#DE-SC0010042"],"award-info":[{"award-number":["#DE-SC0010042"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100007065","name":"Nvidia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. IEEE"],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/jproc.2018.2868961","type":"journal-article","created":{"date-parts":[[2018,9,28]],"date-time":"2018-09-28T19:56:20Z","timestamp":1538164580000},"page":"2040-2055","source":"Crossref","is-referenced-by-count":11,"title":["Autotuning Numerical Dense Linear Algebra for Batched Computation With GPU Hardware Accelerators"],"prefix":"10.1109","volume":"106","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3247-1782","authenticated-orcid":false,"given":"Jack","family":"Dongarra","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2996-1641","authenticated-orcid":false,"given":"Mark","family":"Gates","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9697-0145","authenticated-orcid":false,"given":"Jakub","family":"Kurzak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0089-6965","authenticated-orcid":false,"given":"Piotr","family":"Luszczek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaohung M.","family":"Tsai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Intel Math Kernel Library for Linux* OS","year":"2007","key":"ref39"},{"journal-title":"NVIDIA CUDA TOOLKIT 7 0","year":"2015","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/377792.377804"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1023\/B:IJPP.0000042084.99636.a0"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2017.18"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2016.197"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MLHPC.2016.005"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2003.1214317"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-015-1018-0"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1065895.1065898"},{"article-title":"Sparse direct solvers with accelerators over DAG runtimes","year":"2012","author":"lacoste","key":"ref10"},{"journal-title":"CUBLAS Library User Guide","year":"2016","key":"ref11"},{"journal-title":"Intel Math Kernel Library Developer Reference Revision 011","year":"2017","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/180\/1\/012037"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40047-6_81"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC.2014.30"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2014.52"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2688500.2688534"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/1094342014567546"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2015.2481890"},{"article-title":"Productive high performance parallel programming with auto-tuned domain-specific embedded languages","year":"2012","author":"kamil","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.22"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03869-3_5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2011.311"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/1094342013518807"},{"key":"ref29","first-page":"214","article-title":"Automatic application tuning for HPC architectures","volume":"3","author":"benkner","year":"2014","journal-title":"Dagstuhl report"},{"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":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.44"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2010.5470941"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2015.7363811"},{"article-title":"Optimizing matrix multiply using PHiPAC: A portable, high-performance, ANSI C coding methodology","year":"1996","author":"bilmes","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(00)00087-9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840301"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/16\/1\/071"},{"key":"ref26","first-page":"236","article-title":"Capturing the expert: Generating fast matrix-multiply kernels with spiral","author":"veras","year":"2014","journal-title":"High Performance Computing for Computational Science—VECPAR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840306"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/5\/8510998\/8476161-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5\/8510998\/08476161.pdf?arnumber=8476161","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:55:55Z","timestamp":1649444155000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8476161\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":39,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/jproc.2018.2868961","relation":{},"ISSN":["0018-9219","1558-2256"],"issn-type":[{"type":"print","value":"0018-9219"},{"type":"electronic","value":"1558-2256"}],"subject":[],"published":{"date-parts":[[2018,11]]}}}