{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T15:49:06Z","timestamp":1783784946894,"version":"3.55.0"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319065472","type":"print"},{"value":"9783319065489","type":"electronic"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-06548-9_1","type":"book-chapter","created":{"date-parts":[[2014,7,3]],"date-time":"2014-07-03T08:32:46Z","timestamp":1404376366000},"page":"3-28","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":68,"title":["Accelerating Numerical Dense Linear Algebra Calculations with GPUs"],"prefix":"10.1007","author":[{"given":"Jack","family":"Dongarra","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Gates","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Azzam","family":"Haidar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jakub","family":"Kurzak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Piotr","family":"Luszczek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stanimire","family":"Tomov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ichitaro","family":"Yamazaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2014,6,9]]},"reference":[{"key":"1_CR1","unstructured":"Anderson, E., Bai, Z., Bischof, C., Blackford, L.S., Demmel, J.W., Dongarra, J.J. Du Croz, J., Greenbaum, A., Hammarling, S., McKenney, A., Sorensen, D.: LAPACK Users\u2019 Guide. SIAM, Philadelphia (1992). http:\/\/www.netlib.org\/lapack\/lug\/"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Bientinesi, P., Igual, F.D., Kressner, D., Quintana-Ort\u00ed, E.S.: Reduction to condensed forms for symmetric eigenvalue problems on multi-core architectures. In: Proceedings of the 8th International Conference on Parallel Processing and Applied Mathematics: Part I, PPAM\u201909, pp. 387\u2013395. Springer, Berlin\/Heidelberg (2010)","DOI":"10.1007\/978-3-642-14390-8_40"},{"issue":"1\u20132","key":"1_CR3","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/0377-0427(89)90367-1","volume":"27","author":"J.J. Dongarra","year":"1989","unstructured":"Dongarra, J.J., Sorensen, D.C., Hammarling, S.J.: Block reduction of matrices to condensed forms for eigenvalue computations. J. Comput. Appl. Math. 27(1\u20132), 215\u2013227 (1989)","journal-title":"J. Comput. Appl. Math."},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Gansterer, W., Kvasnicka, D., Ueberhuber, C.: Multi-sweep algorithms for the symmetric eigenproblem. In: Vector and Parallel Processing - VECPAR\u201998. Lecture Notes in Computer Science, vol. 1573, pp. 20\u201328. Springer, Berlin (1999)","DOI":"10.1007\/10703040_3"},{"key":"1_CR5","volume-title":"Matrix Computations","author":"G. Golub","year":"1996","unstructured":"Golub, G., Loan, C.V.: Matrix Computations, 3rd edn. Johns Hopkins, Baltimore (1996)","edition":"3"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Haidar, A., Ltaief, H., Dongarra, J.: Parallel reduction to condensed forms for symmetric eigenvalue problems using aggregated fine-grained and memory-aware kernels. In: Proceedings of SC \u201911, pp. 8:1\u20138:11. ACM, New York (2011)","DOI":"10.1145\/2063384.2063394"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Haidar, A., Ltaief, H., Luszczek, P., Dongarra, J.: A comprehensive study of task coalescing for selecting parallelism granularity in a two-stage bidiagonal reduction. In: Proceedings of the IEEE International Parallel and Distributed Processing Symposium, Shanghai, 21\u201325 May 2012. ISBN 978-1-4673-0975-2","DOI":"10.1109\/IPDPS.2012.13"},{"issue":"2","key":"1_CR8","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1177\/1094342013502097","volume":"28","author":"A. Haidar","year":"2014","unstructured":"Haidar, A., Tomov, S., Dongarra, J., Solca, R., Schulthess, T.: A novel hybrid CPU-GPU generalized eigensolver for electronic structure calculations based on fine grained memory aware tasks. Int. J. High Perform. Comput. Appl. 28(2), 196\u2013209 (2014)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Haidar, A., Kurzak, J., Luszczek, P.: An improved parallel singular value algorithm and its implementation for multicore hardware. In: SC13, The International Conference for High Performance Computing, Networking, Storage and Analysis, Denver, CO, 17\u201322 November 2013","DOI":"10.1145\/2503210.2503292"},{"issue":"7","key":"1_CR10","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1016\/S0167-8191(99)00021-6","volume":"25","author":"B. Lang","year":"1999","unstructured":"Lang, B.: Efficient eigenvalue and singular value computations on shared memory machines. Parallel Comput. 25(7), 845\u2013860 (1999)","journal-title":"Parallel Comput."},{"key":"1_CR11","first-page":"661","volume":"7203","author":"H. Ltaief","year":"2012","unstructured":"Ltaief, H., Luszczek, P., Haidar, A., Dongarra, J.: Enhancing parallelism of tile bidiagonal transformation on multicore architectures using tree reduction. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wasniewski, J. (eds.) Proceedings of 9th International Conference, PPAM 2011, Torun, vol. 7203, pp. 661\u2013670 (2012)","journal-title":"Torun"},{"key":"1_CR12","unstructured":"MAGMA 1.4.1: http:\/\/icl.cs.utk.edu\/magma\/ (2013)"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Nath, R., Tomov, S., Dong, T., Dongarra, J.: Optimizing symmetric dense matrix-vector multiplication on GPUs. In: 2011 International Conference for High Performance Computing, Networking, Storage and Analysis (SC), pp. 1\u201310. New York, NY, USAm 2011, ACM","DOI":"10.1145\/2063384.2063392"},{"key":"1_CR14","unstructured":"Strazdins, P.E.: Lookahead and algorithmic blocking techniques compared for parallel matrix factorization. In: 10th International Conference on Parallel and Distributed Computing and Systems, IASTED, Las Vegas, 1998"},{"issue":"1","key":"1_CR15","first-page":"26","volume":"4","author":"P.E. Strazdins","year":"2001","unstructured":"Strazdins, P.E.: A comparison of lookahead and algorithmic blocking techniques for parallel matrix factorization. Int. J. Parallel Distrib. Syst. Netw. 4(1), 26\u201335 (2001)","journal-title":"Int. J. Parallel Distrib. Syst. Netw."},{"issue":"12","key":"1_CR16","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1016\/j.parco.2010.06.001","volume":"36","author":"S. Tomov","year":"2010","unstructured":"Tomov, S., Nath, R., Dongarra, J.: Accelerating the reduction to upper Hessenberg, tridiagonal, and bidiagonal forms through hybrid GPU-based computing. Parallel Comput. 36(12), 645\u2013654 (2010)","journal-title":"Parallel Comput."},{"key":"1_CR17","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.3152","author":"I. Yamazaki","year":"2013","unstructured":"Yamazaki, I., Dong, T., Solc\u00e0, R., Tomov, S., Dongarra, J., Schulthess, T.: Tridiagonalization of a dense symmetric matrix on multiple GPUs and its application to symmetric eigenvalue problems. Concurr. Comput. Pract. Exp. (2013). doi:10.1002\/cpe.3152","journal-title":"Concurr. Comput. Pract. Exp."}],"container-title":["Numerical Computations with GPUs"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-06548-9_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T17:13:44Z","timestamp":1746292424000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-06548-9_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319065472","9783319065489"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-06548-9_1","relation":{},"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"9 June 2014","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}