{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T16:39:54Z","timestamp":1725727194579},"publisher-location":"Berlin, Heidelberg","reference-count":9,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642387173"},{"type":"electronic","value":"9783642387180"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-38718-0_6","type":"book-chapter","created":{"date-parts":[[2013,5,24]],"date-time":"2013-05-24T00:57:50Z","timestamp":1369357070000},"page":"28-35","source":"Crossref","is-referenced-by-count":0,"title":["Programming the LU Factorization for a Multicore System with Accelerators"],"prefix":"10.1007","author":[{"given":"Jakub","family":"Kurzak","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Piotr","family":"Luszczek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathieu","family":"Faverge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jack","family":"Dongarra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"6_CR1","doi-asserted-by":"publisher","DOI":"10.1145\/1693453.1693484","volume-title":"ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2010","author":"A.M. Castaldo","year":"2010","unstructured":"Castaldo, A.M., Whaley, R.C.: Scaling LAPACK panel operations using parallel cache assignment. In: ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2010. ACM, Bangalore (2010), doi:10.1145\/1693453.1693484 (accepted to ACM TOMS)"},{"issue":"9","key":"6_CR2","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1002\/cpe.728","volume":"15","author":"J.J. Dongarra","year":"2003","unstructured":"Dongarra, J.J., Luszczek, P., Petitet, A.: The LINPACK benchmark: Past, present and future. Concurrency Computat.: Pract. Exper.\u00a015(9), 803\u2013820 (2003), doi:10.1002\/cpe.728","journal-title":"Concurrency Computat.: Pract. Exper."},{"issue":"6","key":"6_CR3","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1147\/rd.416.0737","volume":"41","author":"F.G. Gustavson","year":"1997","unstructured":"Gustavson, F.G.: Recursion leads to automatic variable blocking for dense linear-algebra algorithms. IBM J. Res. Dev.\u00a041(6), 737\u2013756 (1997), doi:10.1147\/rd.416.0737","journal-title":"IBM J. Res. Dev."},{"key":"6_CR4","unstructured":"Gustavson, F.G., Karlsson, L., K\u00e5gstr\u00f6m, B.: Parallel and cache-efficient in-place matrix storage format conversion. Tech. Rep. UMINF 10.05, Department of Computer Science, Ume\u00e5 University (2010), http:\/\/www8.cs.umu.se\/research\/uminf\/reports\/2010\/005\/part1.pdf (accepted to ACM TOMS)"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Kurzak, J., Tomov, S., Dongarra, J.: Autotuning GEMMs for Fermi. Tech. Rep. UT-CS-11-671, Electrical Engineering and Computer Science Department, University of Tennessee (2011), http:\/\/www.netlib.org\/lapack\/lawnspdf\/lawn245.pdf (accepted to IEEE TPDS)","DOI":"10.1109\/TPDS.2011.311"},{"key":"6_CR6","unstructured":"MAGMA, http:\/\/icl.eecs.utk.edu\/magma\/"},{"key":"6_CR7","unstructured":"PLASMA, http:\/\/icl.eecs.utk.edu\/plasma\/"},{"key":"6_CR8","unstructured":"QUARK, http:\/\/icl.eecs.utk.edu\/quark\/"},{"issue":"1-2","key":"6_CR9","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0167-8191(00)00087-9","volume":"27","author":"R.C. Whaley","year":"2001","unstructured":"Whaley, R.C., Petitet, A., Dongarra, J.: Automated empirical optimizations of software and the ATLAS project. Parallel Comput. Syst. Appl.\u00a027(1-2), 3\u201335 (2001), doi:10.1016\/S0167-8191(00)00087-9","journal-title":"Parallel Comput. Syst. Appl."}],"container-title":["Lecture Notes in Computer Science","High Performance Computing for Computational Science - VECPAR 2012"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-38718-0_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T19:46:54Z","timestamp":1645559214000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-38718-0_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642387173","9783642387180"],"references-count":9,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-38718-0_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}