{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T08:33:32Z","timestamp":1778834012210,"version":"3.51.4"},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,4]]},"DOI":"10.1109\/ipdpsw.2010.5470941","type":"proceedings-article","created":{"date-parts":[[2010,5,28]],"date-time":"2010-05-28T14:25:42Z","timestamp":1275056742000},"page":"1-8","source":"Crossref","is-referenced-by-count":142,"title":["Dense linear algebra solvers for multicore with GPU accelerators"],"prefix":"10.1109","author":[{"given":"Stanimire","family":"Tomov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajib","family":"Nath","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hatem","family":"Ltaief","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jack","family":"Dongarra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"A scalable high performant Cholesky factorization for multicore with GPU accelerators","volume":"223","author":"ltaief","year":"2009","journal-title":"Lawn"},{"key":"ref11","article-title":"Towards dense linear algebra for hybrid GPU accelerated manycore systems","volume":"210","author":"tomov","year":"2008","journal-title":"Lawn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1513895.1513901"},{"key":"ref13","author":"agullo","year":"2009","journal-title":"PLASMA version 2 0 user guide"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654080"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2008.10.002"},{"key":"ref3","author":"tomov","year":"2009","journal-title":"MAGMA Version 0 2 User Guide"},{"key":"ref6","year":"2009","journal-title":"Nvidia's Next Generation CUDA Compute Architecture Fermi"},{"key":"ref5","article-title":"Parallel band two-sided matrix bidiagonalization for multicore architectures","author":"ltaief","year":"2009","journal-title":"Accepted for publication at TPDS"},{"key":"ref8","article-title":"Some issues in dense linear algebra for multicore and special purpose architectures","author":"baboulin","year":"2008","journal-title":"Lapack working note 200"},{"key":"ref7","first-page":"884","article-title":"A Note on Auto-tuning GEMM for GPUs","author":"li","year":"2009","journal-title":"ICC'09"},{"key":"ref2","year":"0","journal-title":"General-Purpose Computation Using Graphics Hardware"},{"key":"ref1","year":"0","journal-title":"Nvidia Cuda Zone"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5214359"}],"event":{"name":"Distributed Processing, Workshops and Phd Forum (IPDPSW)","location":"Atlanta, GA, USA","start":{"date-parts":[[2010,4,19]]},"end":{"date-parts":[[2010,4,23]]}},"container-title":["2010 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum (IPDPSW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5465895\/5470678\/05470941.pdf?arnumber=5470941","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,19]],"date-time":"2017-03-19T01:19:02Z","timestamp":1489886342000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5470941\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,4]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/ipdpsw.2010.5470941","relation":{},"subject":[],"published":{"date-parts":[[2010,4]]}}}