{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T14:53:03Z","timestamp":1781621583247,"version":"3.54.5"},"reference-count":20,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,12]]},"DOI":"10.1109\/aiccsa.2011.6126599","type":"proceedings-article","created":{"date-parts":[[2012,3,1]],"date-time":"2012-03-01T11:33:07Z","timestamp":1330601587000},"page":"217-224","source":"Crossref","is-referenced-by-count":33,"title":["LU factorization for accelerator-based systems"],"prefix":"10.1109","author":[{"given":"Emmanuel","family":"Agullo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cedric","family":"Augonnet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jack","family":"Dongarra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathieu","family":"Faverge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julien","family":"Langou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hatem","family":"Ltaief","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stanimire","family":"Tomov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2006.55"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.49"},{"key":"ref12","author":"golub","year":"1989","journal-title":"Matrix Computations"},{"key":"ref13","article-title":"Fortran subroutines for out-of-core solutions of large complex linear systems","author":"yip","year":"1979","journal-title":"Technical Report CR-159142"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654080"},{"key":"ref15","first-page":"31","article-title":"QR factorization for the CELL processor","volume":"17","author":"kurzak","year":"2009","journal-title":"Scientific Programming Special Issue High Performance Computing with the Cell Broadband Engine"},{"key":"ref16","first-page":"15","article-title":"Scheduling dense linear algebra operations on multicore processors","volume":"21","author":"kurzak","year":"2009","journal-title":"Concurrency Computat Pract Exper"},{"key":"ref17","article-title":"LU, QR and Cholesky factorizations using vector capabilities of GPUs","author":"volkov","year":"2008","journal-title":"Technical Report UCB\/EECS-2009–45"},{"key":"ref18","article-title":"StarPU: a Runtime System for Scheduling Tasks over Accelerator-Based Multicore Machines","author":"augonnet","year":"2010","journal-title":"Technical Report 7240"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/0611023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.90"},{"key":"ref3","article-title":"GPU Computing Gems","volume":"2","author":"agullo","year":"2010","journal-title":"Nvidia"},{"key":"ref6","article-title":"Retargeting PLAPACK to clusters with hardware accelerators flame working note #42","author":"fogu\u00e9","year":"2010"},{"key":"ref5","article-title":"CULA: hybrid GPU accelerated linear algebra routines","volume":"7705","author":"humphrey","year":"2010","journal-title":"Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series"},{"key":"ref8","first-page":"851","article-title":"An Extension of the StarSs Programming Model for Platforms with Multiple GPUs","author":"ayguad\u00e9","year":"2009","journal-title":"Proceedings of the 15th International Euro-Par Conference on Parallel Processing"},{"key":"ref7","first-page":"234","article-title":"A unified HPC environment for hybrid manycore\/GPU distributed systems","author":"bosilca","year":"2010","journal-title":"Technical Report LAPACK Working Note"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1145\/1248377.1248397","article-title":"Supermatrix Out-of-Order Scheduling of Matrix Operations for SMP and Multi-Core Architectures","author":"chan","year":"2007","journal-title":"Nineteenth Annual ACM Symposium on Parallel Algorithms and Architectures SPAA '07"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2008.10.002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1383422.1383447"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1377612.1377615"}],"event":{"name":"2011 9th IEEE\/ACS International Conference on Computer Systems and Applications (AICCSA)","location":"Sharm El-Sheikh, Egypt","start":{"date-parts":[[2011,12,27]]},"end":{"date-parts":[[2011,12,30]]}},"container-title":["2011 9th IEEE\/ACS International Conference on Computer Systems and Applications (AICCSA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6122397\/6126580\/06126599.pdf?arnumber=6126599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T11:03:23Z","timestamp":1497956603000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6126599\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,12]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/aiccsa.2011.6126599","relation":{},"subject":[],"published":{"date-parts":[[2011,12]]}}}