{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:20:01Z","timestamp":1740122401059,"version":"3.37.3"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,4,2]],"date-time":"2019-04-02T00:00:00Z","timestamp":1554163200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100003329","name":"Ministerio de Econom\u00eda y Competitividad","doi-asserted-by":"crossref","award":["TIN2014-53495-R"],"award-info":[{"award-number":["TIN2014-53495-R"]}],"id":[{"id":"10.13039\/501100003329","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003329","name":"Ministerio de Econom\u00eda y Competitividad","doi-asserted-by":"publisher","award":["TIN2017-82972-R"],"award-info":[{"award-number":["TIN2017-82972-R"]}],"id":[{"id":"10.13039\/501100003329","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"crossref","award":["671602 INTERTWinE"],"award-info":[{"award-number":["671602 INTERTWinE"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003176","name":"Ministerio de Educaci\u00f3n, Cultura y Deporte","doi-asserted-by":"crossref","award":["FPU"],"award-info":[{"award-number":["FPU"]}],"id":[{"id":"10.13039\/501100003176","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003359","name":"Generalitat Valenciana","doi-asserted-by":"crossref","award":["ValI+D 2015 FPI"],"award-info":[{"award-number":["ValI+D 2015 FPI"]}],"id":[{"id":"10.13039\/501100003359","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1007\/s10586-019-02927-z","type":"journal-article","created":{"date-parts":[[2019,4,2]],"date-time":"2019-04-02T14:55:04Z","timestamp":1554216904000},"page":"359-375","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Programming parallel dense matrix factorizations with look-ahead and OpenMP"],"prefix":"10.1007","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9321-2728","authenticated-orcid":false,"given":"Sandra","family":"Catal\u00e1n","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adri\u00e1n","family":"Castell\u00f3","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francisco D.","family":"Igual","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rafael","family":"Rodr\u00edguez-S\u00e1nchez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrique S.","family":"Quintana-Ort\u00ed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,4,2]]},"reference":[{"key":"2927_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, E., Bai, Z., Susan Blackford, L., Demmel, J., Dongarra, J.J., Croz, J.D., Hammarling, S., Greenbaum, A., McKenney, A., Sorensen, D.C.: LAPACK Users\u2019 guide. SIAM, 3rd edition (1999)","DOI":"10.1137\/1.9780898719604"},{"key":"2927_CR2","doi-asserted-by":"publisher","first-page":"2438","DOI":"10.1002\/cpe.1463","volume":"21","author":"RM Badia","year":"2009","unstructured":"Badia, R.M., Herrero, J.R., Labarta, J., P\u00e9rez, J.M., Quintana-Ort\u00ed, E.S., Quintana-Ort\u00ed, G.: Parallelizing dense and banded linear algebra libraries using SMPSs. Conc. Comp. 21, 2438\u20132456 (2009)","journal-title":"Conc. Comp."},{"issue":"1","key":"2927_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1055531.1055532","volume":"31","author":"P Bientinesi","year":"2005","unstructured":"Bientinesi, P., Gunnels, J.A., Myers, M.E., Quintana-Ort\u00ed, E.S., van\u00a0de Geijn, R.A.: The science of deriving dense linear algebra algorithms. ACM Trans. Math. Softw. 31(1), 1\u201326 (2005)","journal-title":"ACM Trans. Math. Softw."},{"issue":"4","key":"2927_CR4","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1145\/365723.365736","volume":"26","author":"CH Bischof","year":"2000","unstructured":"Bischof, C.H., Lang, B., Sun, X.: Algorithm 807: the SBR toolbox\u2013software for successive band reduction. ACM Trans. Math. Softw. 26(4), 602\u2013616 (2000)","journal-title":"ACM Trans. Math. Softw."},{"issue":"1","key":"2927_CR5","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 Comput. 35(1), 38\u201353 (2009)","journal-title":"Parallel Comput."},{"key":"2927_CR6","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.future.2018.02.016","volume":"84","author":"A Castell\u00f3","year":"2018","unstructured":"Castell\u00f3, A., Mayo, R., Sala, K., Beltran, V., Balaji, P., Pe\u00f1a, A.J.: On the adequacy of lightweight thread approaches for high-level parallel programming models. Future Gener. Comput. Syst. 84, 22\u201331 (2018)","journal-title":"Future Gener. Comput. Syst."},{"key":"2927_CR7","doi-asserted-by":"crossref","unstructured":"Castell\u00f3, A., Pe\u00f1a, A.J., Seo, S., Mayo, R., Balaji, P., Quintana-Ort\u00ed, E.S.: A review of lightweight thread approaches for high performance computing. In: Proceedings of the IEEE International Conference on Cluster Computing, Taipei, Taiwan (September 2016)","DOI":"10.1109\/CLUSTER.2016.12"},{"key":"2927_CR8","doi-asserted-by":"crossref","unstructured":"Castell\u00f3, A., Seo, S., Mayo, R., Balaji, P., Quintana-Ort\u00ed, E.S., Pe\u00f1a, A.J.: GLT: a unified API for lightweight thread libraries. In: Proceedings of the IEEE International European Conference on Parallel and Distributed Computing, Santiago de Compostela, Spain (August 2017)","DOI":"10.1007\/978-3-319-64203-1_34"},{"key":"2927_CR9","doi-asserted-by":"crossref","unstructured":"Castell\u00f3, A., Seo, S., Mayo, R., Balaji, P., Quintana-Ort\u00ed, E.S., Pe\u00f1a, A.J.: GLTO: on the adequacy of lightweight thread approaches for OpenMP implementations. In: Proceedings of the International Conference on Parallel Processing, Bristol, UK (August 2017)","DOI":"10.1109\/ICPP.2017.15"},{"key":"2927_CR10","unstructured":"Catal\u00e1n, S, Herrero, JR., Quintana-Ort\u00ed, E.S., Rodr\u00edguez-S\u00e1nchez, R., van\u00a0de Geijn, R.A.: A case for malleable thread-level linear algebra libraries: The LU factorization with partial pivoting. CoRR (2016) \narXiv:1611.06365"},{"issue":"3","key":"2927_CR11","doi-asserted-by":"publisher","first-page":"1037","DOI":"10.1007\/s10586-016-0611-8","volume":"19","author":"S Catal\u00e1n","year":"2016","unstructured":"Catal\u00e1n, S., Igual, F.D., Mayo, R., Rguez-S\u00e1nchez, R.: Architecture-aware configuration and scheduling of matrix multiplication on asymmetric multicore processors. Clust. Comput. 19(3), 1037\u20131051 (2016)","journal-title":"Clust. Comput."},{"key":"2927_CR12","unstructured":"Chameleon project. \nhttp:\/\/project.inria.fr\/chameleon\/"},{"key":"2927_CR13","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611971446","volume-title":"Applied Numerical Linear Algebra.","author":"J Demmel","year":"1997","unstructured":"Demmel, J.: Applied Numerical Linear Algebra. Society for Industrial and Applied Mathematics, Paris (1997)"},{"issue":"1","key":"2927_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/77626.79170","volume":"16","author":"JJ Dongarra","year":"1990","unstructured":"Dongarra, J.J., Croz, J.D., Hammarling, S., Duff, I.: A set of level 3 basic linear algebra subprograms. ACM Trans. Math. Softw. 16(1), 1\u201317 (1990)","journal-title":"ACM Trans. Math. Softw."},{"key":"2927_CR15","unstructured":"FLAME project home page. \nhttp:\/\/www.cs.utexas.edu\/users\/flame\/"},{"key":"2927_CR16","volume-title":"Matrix Computations","author":"GH Golub","year":"1996","unstructured":"Golub, G.H., Van Loan, C.F.: Matrix Computations, 3rd edn. The Johns Hopkins University Press, Baltimore (1996)","edition":"3"},{"issue":"3","key":"2927_CR17","doi-asserted-by":"publisher","first-page":"12:1","DOI":"10.1145\/1356052.1356053","volume":"34","author":"K Goto","year":"2008","unstructured":"Goto, K., van de Geijn, R.A.: Anatomy of high-performance matrix multiplication. ACM Trans. Math. Softw. 34(3), 12:1\u201312:25 (2008)","journal-title":"ACM Trans. Math. Softw."},{"issue":"1","key":"2927_CR18","doi-asserted-by":"publisher","first-page":"4:1","DOI":"10.1145\/1377603.1377607","volume":"35","author":"K Goto","year":"2008","unstructured":"Goto, K., van de Geijn, R.: High performance implementation of the level-3 BLAS. ACM Trans. Math. Softw. 35(1), 4:1\u20134:14 (2008)","journal-title":"ACM Trans. Math. Softw."},{"issue":"8","key":"2927_CR19","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1016\/S0167-8191(99)00041-1","volume":"25","author":"B Grosser","year":"1999","unstructured":"Grosser, B., Lang, B.: Efficient parallel reduction to bidiagonal form. Parallel Comput. 25(8), 969\u2013986 (1999)","journal-title":"Parallel Comput."},{"issue":"1","key":"2927_CR20","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1145\/1055531.1055534","volume":"31","author":"BC Gunter","year":"2005","unstructured":"Gunter, B.C., van de Geijn, R.A.: Parallel out-of-core computation and updating the QR factorization. ACM Trans. Math. Soft. 31(1), 60\u201378 (2005)","journal-title":"ACM Trans. Math. Soft."},{"key":"2927_CR21","unstructured":"IBM. Engineering and Scientific Subroutine Library. \nhttp:\/\/www-03.ibm.com\/systems\/power\/software\/essl\/\n\n (2015)"},{"key":"2927_CR22","unstructured":"Intel. Math Kernel Library. \nhttps:\/\/software.intel.com\/en-us\/intel-mkl\n\n (2015)"},{"key":"2927_CR23","unstructured":"OmpSs project home page. \nhttp:\/\/pm.bsc.es\/ompss"},{"key":"2927_CR24","unstructured":"http:\/\/www.openblas.net\n\n (2015)"},{"key":"2927_CR25","unstructured":"OpenMP API specification for parallel programming. \nhttp:\/\/www.openmp.org\n\n (2017)"},{"key":"2927_CR26","unstructured":"PLASMA project home page. \nhttp:\/\/icl.cs.utk.edu\/plasma"},{"issue":"2","key":"2927_CR27","doi-asserted-by":"publisher","first-page":"11:1","DOI":"10.1145\/1377612.1377615","volume":"35","author":"ES Quintana-Ort\u00ed","year":"2008","unstructured":"Quintana-Ort\u00ed, E.S., van de Geijn, R.A.: Updating an LU factorization with pivoting. ACM Trans. Math. Softw. 35(2), 11:1\u201311:16 (2008)","journal-title":"ACM Trans. Math. Softw."},{"issue":"3","key":"2927_CR28","doi-asserted-by":"publisher","first-page":"14:1","DOI":"10.1145\/1527286.1527288","volume":"36","author":"G Quintana-Ort\u00ed","year":"2009","unstructured":"Quintana-Ort\u00ed, G., Quintana-Ort\u00ed, E.S., van de Geijn, R.A., Van Zee, F.G., Chan, E.: Programming matrix algorithms-by-blocks for thread-level parallelism. ACM Trans. Math. Softw. 36(3), 14:1\u201314:26 (2009)","journal-title":"ACM Trans. Math. Softw."},{"key":"2927_CR29","unstructured":"Rodr\u00edguez-S\u00e1nchez, R., Catal\u00e1n, Sandra, H., Jos\u00e9, R., Quintana-Ort\u00ed, E.S., Tom\u00e1s, A.E.: Two-sided reduction to compact band forms with look-ahead (2017) CoRR, \narXiv:1709.00302"},{"issue":"99","key":"2927_CR30","first-page":"1","volume":"PP","author":"S Seo","year":"2017","unstructured":"Seo, S., Amer, A., Balaji, P., Bordage, C., Bosilca, G., Brooks, A., Carns, P., Castell\u00f3, A., Genet, D., Herault, T., Iwasaki, S., Jindal, P., Kale, S., Krishnamoorthy, S., Lifflander, J., Lu, H., Meneses, E., Snir, M., Sun, Y., Taura, K., Beckman, P.: Argobots: a lightweight low-level threading and tasking framework. IEEE Trans. Parallel Distrib. Syst. PP(99), 1\u20131 (2017)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"2927_CR31","doi-asserted-by":"crossref","unstructured":"Smith, T.M., van\u00a0de Geijn, R., Smelyanskiy, M., Hammond, J.R., Van\u00a0Zee, F.G.: Anatomy of high-performance many-threaded matrix multiplication. In: Proceedings of IEEE 28th International Parallel and Distributed Processing Symposium, IPDPS\u201914, pp. 1049\u20131059 (2014)","DOI":"10.1109\/IPDPS.2014.110"},{"key":"2927_CR32","unstructured":"StarPU project. \nhttp:\/\/runtime.bordeaux.inria.fr\/StarPU\/"},{"key":"2927_CR33","unstructured":"Stein, D., Shah, D.: Implementing lightweight threads. In: USENIX Summer (1992)"},{"key":"2927_CR34","unstructured":"Strazdins, P.: A comparison of lookahead and algorithmic blocking techniques for parallel matrix factorization. Technical Report TR-CS-98-07, Department of Computer Science, The Australian National University, Canberra 0200 ACT, Australia (1998)"},{"issue":"3","key":"2927_CR35","doi-asserted-by":"publisher","first-page":"14:1","DOI":"10.1145\/2764454","volume":"41","author":"FG Zee Van","year":"2015","unstructured":"Van Zee, F.G., van de Geijn, R.A.: BLIS: a framework for rapidly instantiating BLAS functionality. ACM Trans. Math. Softw. 41(3), 14:1\u201314:33 (2015)","journal-title":"ACM Trans. Math. Softw."},{"key":"2927_CR36","doi-asserted-by":"crossref","unstructured":"Whaley, C.R., Dongarra, J.J.: Automatically tuned linear algebra software. In: Proceedings of SC\u201998 (1998)","DOI":"10.1109\/SC.1998.10004"},{"issue":"2","key":"2927_CR37","doi-asserted-by":"publisher","first-page":"12:1","DOI":"10.1145\/2755561","volume":"42","author":"FG Zee Van","year":"2016","unstructured":"Van Zee, F.G., Smith, T.M., Marker, B., Low, T., Van\u00a0De Geijn, R.A., Igual, F.D., Smelyanskiy, M., Zhang, X., Kistler, M., Austel, V., Gunnels, J.A., Killough, L.: The BLIS framework: experiments in portability. ACM Trans. Math. Softw. 42(2), 12:1\u201312:19 (2016)","journal-title":"ACM Trans. Math. Softw."}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-019-02927-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10586-019-02927-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-019-02927-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,3,31]],"date-time":"2020-03-31T23:41:07Z","timestamp":1585698067000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10586-019-02927-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,2]]},"references-count":37,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["2927"],"URL":"https:\/\/doi.org\/10.1007\/s10586-019-02927-z","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"type":"print","value":"1386-7857"},{"type":"electronic","value":"1573-7543"}],"subject":[],"published":{"date-parts":[[2019,4,2]]},"assertion":[{"value":"23 April 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 March 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 April 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}