{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T06:10:29Z","timestamp":1694585429528},"reference-count":13,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2010,11,8]],"date-time":"2010-11-08T00:00:00Z","timestamp":1289174400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Concurrency and Computation"],"published-print":{"date-parts":[[2011,5]]},"abstract":"Abstract<\/jats:title>We investigate the performance of the routines in LAPACK and the Successive Band Reduction<\/jats:italic> (SBR) toolbox for the reduction of a dense matrix to tridiagonal form, a crucial preprocessing stage in the solution of the symmetric eigenvalue problem, on general\u2010purpose multi\u2010core processors. In response to the advances of hardware accelerators, we also modify the code in the SBR toolbox to accelerate the computation by off\u2010loading a significant part of the operations to a graphics processor (GPU). The performance results illustrate the parallelism and scalability of these algorithms on current high\u2010performance multi\u2010core and many\u2010core architectures. Copyright \u00a9 2010 John Wiley & Sons, Ltd.<\/jats:p>","DOI":"10.1002\/cpe.1680","type":"journal-article","created":{"date-parts":[[2010,11,9]],"date-time":"2010-11-09T03:16:21Z","timestamp":1289272581000},"page":"694-707","source":"Crossref","is-referenced-by-count":16,"title":["Condensed forms for the symmetric eigenvalue problem on multi\u2010threaded architectures"],"prefix":"10.1002","volume":"23","author":[{"given":"Paolo","family":"Bientinesi","sequence":"first","affiliation":[]},{"given":"Francisco D.","family":"Igual","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Kressner","sequence":"additional","affiliation":[]},{"given":"Matthias","family":"Petschow","sequence":"additional","affiliation":[]},{"given":"Enrique S.","family":"Quintana\u2010Ort\u00ed","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2010,11,8]]},"reference":[{"key":"e_1_2_8_2_2","volume-title":"Matrix Computations","author":"Golub GH","year":"1996"},{"key":"e_1_2_8_3_2","volume-title":"Electronic Structure: Basic Theory and Practical Methods","author":"Martin RM","year":"2008"},{"key":"e_1_2_8_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2003.12.028"},{"key":"e_1_2_8_5_2","doi-asserted-by":"publisher","DOI":"10.1137\/030601107"},{"key":"e_1_2_8_6_2","volume-title":"LAPACK Users' Guide","author":"Anderson E","year":"1992"},{"key":"e_1_2_8_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/365723.365736"},{"key":"e_1_2_8_8_2","unstructured":"DongarraJ HammarlingSJ SorensenDC.Block reduction of matrices to condensed forms for eigenvalue computations. LAPACK Working Note 2 Technical Report MCS\u2010TM\u201099 Argonne National Laboratory September 1987."},{"key":"e_1_2_8_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(99)00021-6"},{"key":"e_1_2_8_10_2","series-title":"Lecture Notes in Computer Science","first-page":"387","volume-title":"Proceedings of the 8th International Conference on Parallel Processing and Applied Mathematics, PPAM 2009","author":"Bientinesi P","year":"2009"},{"key":"e_1_2_8_11_2","doi-asserted-by":"publisher","DOI":"10.1137\/0908009"},{"key":"e_1_2_8_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85451-7_79"},{"key":"e_1_2_8_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5214359"},{"key":"e_1_2_8_14_2","unstructured":"IgualFD Quintana\u2010Ort\u00edG van de GeijnR.Level\u20103 BLAS on a GPU: Picking the low hanging fruit. FLAME Working Note #37. DICC 2009\u201004\u201001 Universidad Jaume I. Depto ICC 2009."}],"container-title":["Concurrency and Computation: Practice and Experience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fcpe.1680","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.1680","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,12]],"date-time":"2023-09-12T13:29:29Z","timestamp":1694525369000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cpe.1680"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,11,8]]},"references-count":13,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2011,5]]}},"alternative-id":["10.1002\/cpe.1680"],"URL":"http:\/\/dx.doi.org\/10.1002\/cpe.1680","archive":["Portico"],"relation":{},"ISSN":["1532-0626","1532-0634"],"issn-type":[{"value":"1532-0626","type":"print"},{"value":"1532-0634","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,11,8]]}}}
