{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T23:34:51Z","timestamp":1778024091861,"version":"3.51.4"},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642330773","type":"print"},{"value":"9783642330780","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-33078-0_32","type":"book-chapter","created":{"date-parts":[[2012,9,3]],"date-time":"2012-09-03T21:37:49Z","timestamp":1346708269000},"page":"443-457","source":"Crossref","is-referenced-by-count":7,"title":["Fast Parallel Algorithms for Blocked Dense Matrix Multiplication on Shared Memory Architectures"],"prefix":"10.1007","author":[{"given":"G.","family":"Nimako","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"E. J.","family":"Otoo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"D.","family":"Ohene-Kwofie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"32_CR1","unstructured":"Cannon, L.E.: A cellular computer to implement the kalman filter algorithm. PhD thesis, Montana State University (1969)"},{"issue":"7","key":"32_CR2","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1002\/cpe.4330060702","volume":"6","author":"J. Choi","year":"1994","unstructured":"Choi, J., Dongarra, J., Walker, D.: Parallel universal matrix multiplication algorithms on distributed memory concurrent computers. Concurrency: Practice and Experience\u00a06(7), 543\u2013570 (1994)","journal-title":"Concurrency: Practice and Experience"},{"issue":"4","key":"32_CR3","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1002\/(SICI)1096-9128(199704)9:4<255::AID-CPE250>3.0.CO;2-2","volume":"9","author":"R.A. Geijn van de","year":"1997","unstructured":"van de Geijn, R.A., Watts, J.: Scalable universal matrix multiplication algorithm. Concurrency: Practice and Experience\u00a09(4), 255\u2013274 (1997)","journal-title":"Concurrency: Practice and Experience"},{"key":"32_CR4","unstructured":"Krishnan, M., Nieplocha, J.: Srumma: a matrix multiplication algorithm suitable for clusters and scalable shared memory systems. In: Proceedings of Parallel and Distributed Processing Symposium (2004)"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Ranger, C., Raghuraman, R., Penmetsa, A., Bradski, G., Kozyrakis, C.: Evaluating mapreduce for multi-core and multiprocessor systems. In: Proc. of the 13th Int\u2019l Symposium on High Performance Computer Architecture, pp. 13\u201324 (2007)","DOI":"10.1109\/HPCA.2007.346181"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Yoo, R.M., Romano, A., Kozyrakis, C.: Phoenix rebirth: Scalable mapreduce on a large-scale shared-memory system. In: Proc. of the 2009 IEEE Int\u2019l Symposium on Workload Characterization, pp. 198\u2013207 (2009)","DOI":"10.1109\/IISWC.2009.5306783"},{"key":"32_CR7","unstructured":"Dean, J., Ghemawat, J.: Mapreduce: Simplified data processing on large clusters. In: Proceedings of the 6th Symp. on Operating Systems Design and Implementation (2004)"},{"key":"32_CR8","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719642","volume-title":"Scalapack users guide","author":"L. Blackford","year":"1997","unstructured":"Blackford, L., Choi, J., Cleary, A., DAzevedo, E., Demmel, J., Dhillon, I., Dongarra, J., Hammarling, S., Henry, G., Petitet, A., Stanley, K., Walker, D., Whaley, R.: Scalapack users guide. SIAM, Philadelphia (1997)"},{"key":"32_CR9","volume-title":"Lapack users guide","author":"E. Anderson","year":"1992","unstructured":"Anderson, E., Bai, Z., Bischof, C., Blackford, L., Demmel, J., Dongarra, J., Hammarling, S., Croz, J., Greenbaum, A., McKenney, A., Sorensen, D.: Lapack users guide. SIAM, Philadelphia (1992)"},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"Jakub, K., Ltaief, H., Dongarra, J., Badia, R.: Scheduling dense linear algebra operations on multicore processors. Concurrency and Computation: Practice and Experience\u00a022(1) (2010)","DOI":"10.1002\/cpe.1467"},{"key":"32_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-540-31832-3_1","volume-title":"Shared Memory Parallel Programming with Open MP","author":"J.L. Bentz","year":"2005","unstructured":"Bentz, J.L., Kendall, R.A.: Parallelization of General Matrix Multiply Routines Using OpenMP. In: Chapman, B.M. (ed.) WOMPAT 2004. LNCS, vol.\u00a03349, pp. 1\u201311. Springer, Heidelberg (2005)"},{"key":"32_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/11823285_15","volume-title":"Euro-Par 2006 Parallel Processing","author":"D. Hackenberg","year":"2006","unstructured":"Hackenberg, D., Sch\u00f6ne, R., Nagel, W.E., Pfl\u00fcger, S.: Optimizing OpenMP Parallelized DGEMM Calls on SGI Altix 3700. In: Nagel, W.E., Walter, W.V., Lehner, W. (eds.) Euro-Par 2006. LNCS, vol.\u00a04128, pp. 145\u2013154. Springer, Heidelberg (2006)"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Alpatov, P., Baker, G., Edwards, C., Gunnels, J., Morrow, G., Overfelt, J., van de Geiju, R., Wu, J.: Plapack: Parallel linear algebra package. In: Proceedings of the SIAM Parallel Processing Conference (1997)","DOI":"10.1145\/509593.509622"},{"issue":"3","key":"32_CR14","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1007\/BF02165411","volume":"14","author":"V. Strassen","year":"1969","unstructured":"Strassen, V.: Guassian elimination is not optimal. Numerische Mathematick\u00a014(3), 354\u2013356 (1969)","journal-title":"Numerische Mathematick"},{"key":"32_CR15","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/S0747-7171(08)80013-2","volume":"9","author":"D. Coppersmith","year":"1990","unstructured":"Coppersmith, D., Winograd, S.: Matrix multiplication via arithmetic progressions. Journal of Symbolic Computing\u00a09, 251\u2013280 (1990)","journal-title":"Journal of Symbolic Computing"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-33078-0_32.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T11:54:32Z","timestamp":1620129272000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-33078-0_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642330773","9783642330780"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-33078-0_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012]]}}}