{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T03:40:54Z","timestamp":1783568454411,"version":"3.55.0"},"reference-count":10,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008,4]]},"DOI":"10.1109\/ipdps.2008.4536485","type":"proceedings-article","created":{"date-parts":[[2008,6,6]],"date-time":"2008-06-06T12:44:52Z","timestamp":1212756292000},"page":"1-8","source":"Crossref","is-referenced-by-count":54,"title":["Evaluation and tuning of the Level 3 CUBLAS for graphics processors"],"prefix":"10.1109","author":[{"given":"Sergio","family":"Barrachina","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maribel","family":"Castillo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francisco D.","family":"Igual","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rafael","family":"Mayo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enrique S.","family":"Quintana-Orti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"3","doi-asserted-by":"publisher","DOI":"10.1145\/1058129.1058148"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1145\/1055531.1055532"},{"key":"10","year":"2007","journal-title":"NVIDIA CUDA Compute Unified Device Architecture Programming Guide"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719604"},{"key":"7","first-page":"43","article-title":"fast matrix multiplies using graphics hardware","author":"larsen","year":"2001","journal-title":"Supercomputing ACM\/IEEE 2001 Conference"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1145\/292395.292412"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"4","author":"goto","year":"2005","journal-title":"Goto BLAS implementation"},{"key":"9","year":"2007","journal-title":"CUBLAS Library"},{"key":"8","author":"morava?nszky","year":"2003","journal-title":"Dense matrix algebra on the GPU"}],"event":{"name":"Distributed Processing Symposium (IPDPS)","location":"Miami, FL, USA","start":{"date-parts":[[2008,4,14]]},"end":{"date-parts":[[2008,4,18]]}},"container-title":["2008 IEEE International Symposium on Parallel and Distributed Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4519061\/4536075\/04536485.pdf?arnumber=4536485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,16]],"date-time":"2017-03-16T13:50:59Z","timestamp":1489672259000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4536485\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,4]]},"references-count":10,"URL":"https:\/\/doi.org\/10.1109\/ipdps.2008.4536485","relation":{},"ISSN":["1530-2075"],"issn-type":[{"value":"1530-2075","type":"print"}],"subject":[],"published":{"date-parts":[[2008,4]]}}}