{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T00:40:10Z","timestamp":1748824810438,"version":"3.41.0"},"reference-count":19,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,3,28]],"date-time":"2016-03-28T00:00:00Z","timestamp":1459123200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2017,1]]},"DOI":"10.1007\/s11227-016-1694-y","type":"journal-article","created":{"date-parts":[[2016,3,28]],"date-time":"2016-03-28T18:25:04Z","timestamp":1459189504000},"page":"227-239","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Automatic tuning to performance modelling of matrix polynomials on multicore and multi-GPU systems"],"prefix":"10.1007","volume":"73","author":[{"given":"Murilo","family":"Boratto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro","family":"Alonso","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Domingo","family":"Gim\u00e9nez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexey","family":"Lastovetsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,3,28]]},"reference":[{"issue":"1\/2\/3","key":"1694_CR1","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1504\/IJHPCN.2004.007567","volume":"1","author":"PV Alberti","year":"2004","unstructured":"Alberti PV, Alonso P, Vidal AM, Cuenca J, Gim\u00e9nez D (2004) Designing polylibraries to speed up linear algebra computations. IJHPCN 1(1\/2\/3):75\u201384","journal-title":"IJHPCN"},{"key":"1694_CR2","unstructured":"Alonso P, Boratto M, Pinilla J, Iba\u00f1ez J, Martinez J (2014) On the evaluation of matrix polynomials using several GPGPUs. Tech Rep Riunet\/E10251\/39615"},{"key":"1694_CR3","volume-title":"LAPACK users guide","author":"E Anderson","year":"2013","unstructured":"Anderson E, Bai Z, Bischof C, Demmel J, Dongarra J, Croz JD, Greenbaum A, Hammarling S, McKenney A, Ostrouchov S, Sorensen D (2013) LAPACK users guide, 2nd edn. SIAM, Philadelphia","edition":"2"},{"key":"1694_CR4","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1145\/567806.567807","volume":"28","author":"LS Blackford","year":"2001","unstructured":"Blackford LS, Demmel J, Dongarra J, Duff I, Hammarling S, Henry G, Heroux M, Kaufman L, Lumsdaine A, Petitet A, Pozo R, Remington K, Whaley RC (2001) An updated set of basic linear algebra subprograms (blas). ACM Trans Math Softw 28:135\u2013151","journal-title":"ACM Trans Math Softw"},{"key":"1694_CR5","first-page":"80","volume":"11","author":"E Caron","year":"2002","unstructured":"Caron E, Uter F (2002) Parallel extension of a dynamic performance forecasting tool. Sci Ann Cuza Univ 11:80\u201393","journal-title":"Sci Ann Cuza Univ"},{"key":"1694_CR6","volume-title":"Parallel programming in OpenMP","author":"R Chandra","year":"2001","unstructured":"Chandra R (2001) Parallel programming in OpenMP. Morgan Kaufmann, Burlington"},{"issue":"3","key":"1694_CR7","doi-asserted-by":"crossref","first-page":"1508","DOI":"10.1137\/070688778","volume":"30","author":"J Demmel","year":"2008","unstructured":"Demmel J, Marques O, Parlett BN, V\u00f6mel C (2008) Performance and accuracy of LAPACK\u2019s symmetric tridiagonal eigensolvers. SIAM J.Sci Comput 30(3):1508\u20131526","journal-title":"SIAM J.Sci Comput"},{"key":"1694_CR8","doi-asserted-by":"crossref","unstructured":"Frigo M, Johnson S (1998) FFTW: an adaptive software architecture for the FFT. In: Proceedings of IEEE International Conference on Acoustics Speech and Signal Processing vol. 3, pp 1381\u20131384","DOI":"10.1109\/ICASSP.1998.681704"},{"key":"1694_CR9","doi-asserted-by":"crossref","unstructured":"Garc\u00eda L, Cuenca J, Gim\u00e9nez D (2007) Including improvement of the execution time in a software architecture of libraries with self-optimisation. In: ICSOFT 2007, Proceedings of the Second International Conference on Software and Data Technologies, Volume SE, Barcelona, Spain, pp 156\u2013161, 22\u201325 July","DOI":"10.5220\/0001337501560161"},{"issue":"1","key":"1694_CR10","first-page":"10","volume":"1","author":"LP Garc\u00eda","year":"2014","unstructured":"Garc\u00eda LP, Cuenca J, Gim\u00e9nez D (2014) On optimization techniques for the matrix multiplication on hybrid cpu+gpu platforms. Ann Multicore GPU Program 1(1):10\u201318","journal-title":"Ann Multicore GPU Program"},{"key":"1694_CR11","unstructured":"Hasanov K, Quintin JN, Lastovetsky A (2014) Hierarchical approach to optimization of parallel matrix multiplication on large-scale platforms. J Supercomput 71(11):24\u201334"},{"key":"1694_CR12","unstructured":"Katagiri T, Kise K, Honda H (2005) RAO-SS: a prototype of run-time auto-tuning facility for sparse direct solvers. Tech Rep 22(1):1\u201310"},{"key":"1694_CR13","doi-asserted-by":"crossref","unstructured":"Katagiri T, Kise K, Honda H, Yuba T (2004) Effect of auto-tuning with user\u2019s knowledge for numerical software. Proceedings of the 1st conference on computing frontiers, Ischia, Italy. ACM, New York, NY, USA, pp 12\u201325","DOI":"10.1145\/977091.977095"},{"issue":"4","key":"1694_CR14","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1177\/1094342010385729","volume":"24","author":"R Nath","year":"2010","unstructured":"Nath R, Tomov S, Dongarra J (2010) An improved magma gemm for fermi graphics processing units. Int J High Perform Comput Appl 24(4):511\u2013515","journal-title":"Int J High Perform Comput Appl"},{"issue":"1","key":"1694_CR15","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1137\/0202007","volume":"2","author":"MS Paterson","year":"1973","unstructured":"Paterson MS, Stockmeyer LJ (1973) On the number of nonscalar multiplications necessary to evaluate polynomials. SIAM J Comput 2(1):60\u201366","journal-title":"SIAM J Comput"},{"key":"1694_CR16","unstructured":"PLASMA (2015) Parallel linear algebra software for multicore architectures. Available in: http:\/\/www.netlib.org\/plasma\/ . Accessed 1 June 2015"},{"key":"1694_CR17","doi-asserted-by":"crossref","unstructured":"Tanaka T, Katagiri T, Yuba T (2007) D-spline based incremental parameter estimation in automatic performance tuning. In: International Conference on Applied Parallel Computing: State of the Art in Scientific Computing, PARA\u201906. Springer-Verlag, Berlin, Heidelberg, pp 986\u2013995","DOI":"10.1007\/978-3-540-75755-9_116"},{"key":"1694_CR18","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1177\/1094342004041293","volume":"18","author":"R Vuduc","year":"2004","unstructured":"Vuduc R, Demmel J, Bilmes J (2004) Statistical models for empirical search-based performance tuning. Int J High Perform Comput Appl 18:65\u201394","journal-title":"Int J High Perform Comput Appl"},{"key":"1694_CR19","first-page":"21","volume":"27","author":"RC Whaley","year":"2001","unstructured":"Whaley RC, Petitet A, Dongarra JJ (2001) Automated empirical optimizations of software and the ATLAS project. Parallel Comput 27:21\u201337","journal-title":"Parallel Comput"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-016-1694-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-016-1694-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-016-1694-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-016-1694-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T00:27:54Z","timestamp":1748824074000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-016-1694-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3,28]]},"references-count":19,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,1]]}},"alternative-id":["1694"],"URL":"https:\/\/doi.org\/10.1007\/s11227-016-1694-y","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2016,3,28]]}}}