{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T05:42:26Z","timestamp":1725601346778},"publisher-location":"Berlin, Heidelberg","reference-count":10,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642233968"},{"type":"electronic","value":"9783642233975"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"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":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-23397-5_19","type":"book-chapter","created":{"date-parts":[[2011,8,18]],"date-time":"2011-08-18T07:40:06Z","timestamp":1313653206000},"page":"194-205","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A Fully Empirical Autotuned Dense QR Factorization for Multicore Architectures"],"prefix":"10.1007","author":[{"given":"Emmanuel","family":"Agullo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jack","family":"Dongarra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajib","family":"Nath","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stanimire","family":"Tomov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"19_CR1","first-page":"1381","volume-title":"Proc. 1998 IEEE Intl. Conf. Acoustics Speech and Signal Processing","author":"M. Frigo","year":"1998","unstructured":"Frigo, M., Johnson, S.: FFTW: An adaptive software architecture for the FFT. In: Proc. 1998 IEEE Intl. Conf. Acoustics Speech and Signal Processing, vol.\u00a03, pp. 1381\u20131384. IEEE, Los Alamitos (1998)"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Choi, J.W., Singh, A., Vuduc, R.W.: Model-driven autotuning of sparse matrix-vector multiply on GPUs. In: Proc. ACM SIGPLAN Symp. Principles and Practice of Parallel Programming (PPoPP), Bangalore, India (January 2010)","DOI":"10.1145\/1693453.1693471"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Ansel, J., Chan, C., Wong, Y.L., Olszewski, M., Zhao, Q., Edelman, A., Amarasinghe, S.: Petabricks: A language and compiler for algorithmic choice. In: ACM SIGPLAN Conference on Programming Language Design and Implementation, Dublin, Ireland (June 2009)","DOI":"10.1145\/1542476.1542481"},{"issue":"1-2","key":"19_CR4","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0167-8191(00)00087-9","volume":"27","author":"R. Clint Whaley","year":"2001","unstructured":"Clint Whaley, R., Petitet, A., Dongarra, J.J.: Automated empirical optimizations of software and the atlas project. Parallel Computing\u00a027(1-2), 3\u201335 (2001)","journal-title":"Parallel Computing"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Volkov, V., Demmel, J.W.: Benchmarking gpus to tune dense linear algebra. In: SC 2008: Proceedings of the ACM\/IEEE Conference on Supercomputing, pp. 1\u201311. IEEE Press, Piscataway (2008)","DOI":"10.1109\/SC.2008.5214359"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Tomov, S., Nath, R., Ltaief, H., Dongarra, J.: Dense linear algebra solvers for multicore with gpu accelerators. Accepted for publication at HIPS 2010 (2010)","DOI":"10.1109\/IPDPSW.2010.5470941"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Quintana-Ort\u00ed, G., Quintana-Ort\u00ed, E., van de Geijn, R., Van Zee, F., Chan, E.: Programming matrix algorithms-by-blocks for thread-level parallelism. ACM Trans. Math. Softw.\u00a036(3) (2009)","DOI":"10.1145\/1527286.1527288"},{"issue":"1","key":"19_CR8","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.parco.2008.10.002","volume":"35","author":"A. Buttari","year":"2009","unstructured":"Buttari, A., Langou, J., Kurzak, J., Dongarra, J.: A class of parallel tiled linear algebra algorithms for multicore architectures. Parallel Computing\u00a035(1), 38\u201353 (2009)","journal-title":"Parallel Computing"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Agullo, E., Hadri, B., Ltaief, H., Dongarra, J.: Comparative study of one-sided factorizations with multiple software packages on multi-core hardware. In: 2009 International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2009) (2009)","DOI":"10.1145\/1654059.1654080"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Agullo, E., Dongarra, J., Nath, R., Tomov, S.: A Fully Empirical Autotuned Dense QR Factorization For Multicore Architectures. Research Report 7526, INRIA (Febuary 2011)","DOI":"10.1007\/978-3-642-23397-5_19"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2011 Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-23397-5_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,20]],"date-time":"2020-04-20T00:45:09Z","timestamp":1587343509000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-23397-5_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642233968","9783642233975"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-23397-5_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2011]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}