{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T16:08:51Z","timestamp":1725466131714},"publisher-location":"Berlin, Heidelberg","reference-count":24,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642314636"},{"type":"electronic","value":"9783642314643"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-31464-3_23","type":"book-chapter","created":{"date-parts":[[2012,7,2]],"date-time":"2012-07-02T11:20:38Z","timestamp":1341228038000},"page":"225-234","source":"Crossref","is-referenced-by-count":2,"title":["Generalizing Matrix Multiplication for Efficient Computations on Modern Computers"],"prefix":"10.1007","author":[{"given":"Stanislav G.","family":"Sedukhin","sequence":"first","affiliation":[]},{"given":"Marcin","family":"Paprzycki","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"23_CR1","unstructured":"Robinson, S.: Towards an optimal algorithm for matrix multiplication. SIAM News 38 (2005)"},{"key":"23_CR2","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1002\/(SICI)1096-9128(199705)9:5<345::AID-CPE258>3.0.CO;2-7","volume":"9","author":"J. Li","year":"1997","unstructured":"Li, J., Skjellum, A., Falgout, R.D.: A poly-algorithm for parallel dense matrix multiplication on two-dimensional process grid topologies. Concurrency - Practice and Experience\u00a09, 345\u2013389 (1997)","journal-title":"Concurrency - Practice and Experience"},{"key":"23_CR3","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/j.parco.2008.03.003","volume":"34","author":"S. Hunold","year":"2008","unstructured":"Hunold, S., Rauber, T., R\u00fcnger, G.: Combining building blocks for parallel multi-level matrix multiplication. Parallel Comput.\u00a034, 411\u2013426 (2008)","journal-title":"Parallel Comput."},{"key":"23_CR4","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1142\/S0129626496000029","volume":"6","author":"B. Grayson","year":"1996","unstructured":"Grayson, B., Van De Geijn, R.: A high performance parallel Strassen implementation. Parallel Processing Letters\u00a06, 3\u201312 (1996)","journal-title":"Parallel Processing Letters"},{"key":"23_CR5","unstructured":"Song, F., Moore, S., Dongarra, J.: Experiments with Strassen\u2019s Algorithm: from Sequential to Parallel. In: International Conference on Parallel and Distributed Computing and Systems (PDCS 2006). ACTA Press (November 2006)"},{"key":"23_CR6","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1007\/BF00129836","volume":"4","author":"D.H. Bailey","year":"1991","unstructured":"Bailey, D.H., Lee, K., Simon, H.D.: Using Strassen\u2019s algorithm to accelerate the solution of linear systems. J. Supercomputer\u00a04, 357\u2013371 (1991)","journal-title":"J. Supercomputer"},{"key":"23_CR7","first-page":"77","volume":"6","author":"M. Paprzycki","year":"1991","unstructured":"Paprzycki, M., Cyphers, C.: Multiplying matrices on the Cray \u2013 practical considerations. CHPC Newsletter\u00a06, 77\u201382 (1991)","journal-title":"CHPC Newsletter"},{"key":"23_CR8","doi-asserted-by":"publisher","first-page":"534","DOI":"10.1587\/transinf.E93.D.534","volume":"E93.D","author":"S.G. Sedukhin","year":"2010","unstructured":"Sedukhin, S.G., Miyazaki, T., Kuroda, K.: Orbital systolic algorithms and array processors for solution of the algebraic path problem. IEICE Trans. on Information and Systems\u00a0E93.D, 534\u2013541 (2010)","journal-title":"IEICE Trans. on Information and Systems"},{"key":"23_CR9","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/0304-3975(77)90056-1","volume":"4","author":"D.J. Lehmann","year":"1977","unstructured":"Lehmann, D.J.: Algebraic structures for transitive closure. Theoretical Computer Science\u00a04, 59\u201376 (1977)","journal-title":"Theoretical Computer Science"},{"key":"23_CR10","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/0304-3975(85)90170-7","volume":"40","author":"S.K. Abdali","year":"1985","unstructured":"Abdali, S.K., Saunders, B.D.: Transitive closure and related semiring properties via eliminants. Theoretical Computer Science\u00a040, 257\u2013274 (1985)","journal-title":"Theoretical Computer Science"},{"key":"23_CR11","doi-asserted-by":"publisher","first-page":"1225","DOI":"10.1587\/transinf.E92.D.1225","volume":"92-D","author":"K. Matsumoto","year":"2009","unstructured":"Matsumoto, K., Sedukhin, S.G.: A solution of the all-pairs shortest paths problem on the Cell broadband engine processor. IEICE Trans. on Information and Systems\u00a092-D, 1225\u20131231 (2009)","journal-title":"IEICE Trans. on Information and Systems"},{"key":"23_CR12","unstructured":"Sedukhin, S.G., Miyazaki, T.: Rapid*Closure: Algebraic extensions of a scalar multiply-add operation. In: Philips, T. (ed.) CATA, ISCA, pp. 19\u201324 (2010)"},{"key":"23_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/77626.79170","volume":"16","author":"J.J. Dongarra","year":"1990","unstructured":"Dongarra, J.J., Croz, J.D., Duff, I., Hammarling, S.: A set of level 3 basic linear algebra subprograms. ACM Trans. Math. Software\u00a016, 1\u201317 (1990)","journal-title":"ACM Trans. Math. Software"},{"key":"23_CR14","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1145\/359327.359336","volume":"21","author":"R.M. Russell","year":"1978","unstructured":"Russell, R.M.: The CRAY-1 computer system. Commun. ACM\u00a021, 63\u201372 (1978)","journal-title":"Commun. ACM"},{"key":"23_CR15","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1145\/355841.355847","volume":"5","author":"C.L. Lawson","year":"1979","unstructured":"Lawson, C.L., Hanson, R.J., Kincaid, R.J., Krogh, F.T.: Basic linear algebra subprograms for FORTRAN usage. ACM Trans. Math. Software\u00a05, 308\u2013323 (1979)","journal-title":"ACM Trans. Math. Software"},{"key":"23_CR16","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1147\/rd.341.0059","volume":"34","author":"R.K. Montoye","year":"1990","unstructured":"Montoye, R.K., Hokenek, E., Runyon, S.L.: Design of the IBM RISC System\/6000 floating-point execution unit. IBM J. Res. Dev.\u00a034, 59\u201370 (1990)","journal-title":"IBM J. Res. Dev."},{"key":"23_CR17","unstructured":"Gustavson, F.G., Moreira, J.E., Enenkel, R.F.: The fused multiply-add instruction leads to algorithms for extended-precision floating point: applications to Java and high-performance computing. In: CASCON 1999: Proceedings of the 1999 Conference of the Centre for Advanced Studies on Collab. Research, p. 4. IBM Press (1999)"},{"key":"23_CR18","unstructured":"Gustafson, J.L.: Algorithm leadership. HPCwire, April 06 (2007)"},{"key":"23_CR19","unstructured":"Birkhoff, G., McLane, S.: A Survey of Modern Algebra. AKP Classics. A K Peters, Massachusetts (1997)"},{"key":"23_CR20","volume-title":"MPI: The Complete Reference","author":"M. Snir","year":"1996","unstructured":"Snir, M., Otto, S., Huss-Lederman, S., Walker, D., Dongarra, J.: MPI: The Complete Reference. The MIT Press, Cambridge (1996)"},{"key":"23_CR21","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1147\/rd.492.0195","volume":"49","author":"A. Gara","year":"2005","unstructured":"Gara, A., Blumrich, M.A., Chen, D., Chiu, G.L.T., Coteus, P., Giampapa, M., Haring, R.A., Heidelberger, P., Hoenicke, D., Kopcsay, G.V., Liebsch, T.A., Ohmacht, M., Steinmacher-Burow, B.D., Takken, T., Vranas, P.: Overview of the Blue Gene\/L system architecture. IBM J. Res. and Dev.\u00a049, 195\u2013212 (2005)","journal-title":"IBM J. Res. and Dev."},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Sedukhin, S.G., Zekri, A.S., Myiazaki, T.: Orbital algorithms and unified array processor for computing 2D separable transforms. In: International Conference on Parallel Processing Workshops, pp. 127\u2013134 (2010)","DOI":"10.1109\/ICPPW.2010.29"},{"key":"23_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/42288.42291","volume":"14","author":"J.J. Dongarra","year":"1988","unstructured":"Dongarra, J.J., Croz, J.D., Hammarling, S., Hanson, R.J.: An extended set of FORTRAN basic linear algebra subprograms. ACM Trans. Math. Software\u00a014, 1\u201317 (1988)","journal-title":"ACM Trans. Math. Software"},{"key":"23_CR24","first-page":"439","volume-title":"Proceedings of the Federated Conference on Computer Science and Information Systems","author":"M. Ganzha","year":"2011","unstructured":"Ganzha, M., Sedukhin, S., Paprzycki, M.: Object oriented model of generalized matrix multipication. In: Proceedings of the Federated Conference on Computer Science and Information Systems, pp. 439\u2013442. IEEE Press, Los Alamitos (2011)"}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-31464-3_23.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T08:01:58Z","timestamp":1620115318000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-31464-3_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642314636","9783642314643"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-31464-3_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}