{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T21:03:59Z","timestamp":1791407039470,"version":"4.3.3"},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642233968","type":"print"},{"value":"9783642233975","type":"electronic"}],"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_10","type":"book-chapter","created":{"date-parts":[[2011,8,18]],"date-time":"2011-08-18T03:40:06Z","timestamp":1313638806000},"page":"90-109","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":130,"title":["Communication-Optimal Parallel 2.5D Matrix Multiplication and LU Factorization Algorithms"],"prefix":"10.1007","author":[{"given":"Edgar","family":"Solomonik","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Demmel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"10_CR1","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1147\/rd.395.0575","volume":"39","author":"R.C. Agarwal","year":"1995","unstructured":"Agarwal, R.C., Balle, S.M., Gustavson, F.G., Joshi, M., Palkar, P.: A three-dimensional approach to parallel matrix multiplication. IBM J. Res. Dev.\u00a039, 575\u2013582 (1995)","journal-title":"IBM J. Res. Dev."},{"issue":"1","key":"10_CR2","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/0304-3975(90)90188-N","volume":"71","author":"A. Aggarwal","year":"1990","unstructured":"Aggarwal, A., Chandra, A.K., Snir, M.: Communication complexity of PRAMs. Theoretical Computer Science\u00a071(1), 3\u201328 (1990)","journal-title":"Theoretical Computer Science"},{"key":"10_CR3","unstructured":"Ashcraft, C.: A taxonomy of distributed dense LU factorization methods. Boeing Computer Services Technical Report ECA-TR-161 (March 1991)"},{"key":"10_CR4","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/978-1-4613-8369-7_8","volume-title":"Graph Theory and Sparse Matrix Computation. IMA Volumes in Mathematics and its Applications","author":"C. Ashcraft","year":"1993","unstructured":"Ashcraft, C.: The fan-both family of column-based distributed Cholesky factorization algorithms. In: Alan George, J.R.G., Liu, J.W.H. (eds.) Graph Theory and Sparse Matrix Computation. IMA Volumes in Mathematics and its Applications, vol.\u00a056, pp. 159\u2013190. Springer, Heidelberg (1993)"},{"key":"10_CR5","unstructured":"Ballard, G., Demmel, J., Holtz, O., Schwartz, O.: Minimizing communication in numerical linear algebra. To appear in SIAM J. Mat. Anal. Appl., UCB Technical Report EECS-2009-62 (2010)"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Blackford, L.S., Choi, J., Cleary, A., D\u2019Azeuedo, E., Demmel, J., Dhillon, I., Hammarling, S., Henry, G., Petitet, A., Stanley, K., Walker, D., Whaley, R.C.: ScaLAPACK User\u2019s Guide, Society for Industrial and Applied Mathematics, Philadelphia, PA, USA (1997)","DOI":"10.1137\/1.9780898719642"},{"key":"10_CR7","unstructured":"Cannon, L.E.: A cellular computer to implement the Kalman filter algorithm. Ph.D. thesis, Bozeman, MT, USA (1969)"},{"issue":"4","key":"10_CR8","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1137\/0210049","volume":"10","author":"E. Dekel","year":"1981","unstructured":"Dekel, E., Nassimi, D., Sahni, S.: Parallel matrix and graph algorithms. SIAM Journal on Computing\u00a010(4), 657\u2013675 (1981)","journal-title":"SIAM Journal on Computing"},{"key":"10_CR9","unstructured":"Demmel, J., Grigori, L., Xiang, H.: A Communication Optimal LU Factorization Algorithm. EECS Technical Report EECS-2010-29, UC Berkeley (March 2010)"},{"key":"10_CR10","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/s00211-007-0114-x","volume":"108","author":"J. Demmel","year":"2007","unstructured":"Demmel, J., Dumitriu, I., Holtz, O.: Fast linear algebra is stable. Numerische Mathematik\u00a0108, 59\u201391 (2007)","journal-title":"Numerische Mathematik"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Faraj, A., Kumar, S., Smith, B., Mamidala, A., Gunnels, J.: MPI collective communications on the Blue Gene\/P supercomputer: Algorithms and optimizations. In: 17th IEEE Symposium on High Performance Interconnects HOTI 2009, pp. 63\u201372 (2009)","DOI":"10.1109\/HOTI.2009.12"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Grigori, L., Demmel, J.W., Xiang, H.: Communication avoiding Gaussian elimination. In: Proceedings of the 2008 ACM\/IEEE Conference on Supercomputing SC 2008, pp. 29:1\u201329:12. IEEE Press, Piscataway (2008)","DOI":"10.1109\/SC.2008.5214287"},{"key":"10_CR13","volume-title":"Using MPI: portable parallel programming with the message-passing interface","author":"W. Gropp","year":"1994","unstructured":"Gropp, W., Lusk, E., Skjellum, A.: Using MPI: portable parallel programming with the message-passing interface. MIT Press, Cambridge (1994)"},{"key":"10_CR14","first-page":"3","volume":"71","author":"D. Irony","year":"2002","unstructured":"Irony, D., Toledo, S.: Trading replication for communication in parallel distributed-memory dense solvers. Parallel Processing Letters\u00a071, 3\u201328 (2002)","journal-title":"Parallel Processing Letters"},{"issue":"9","key":"10_CR15","doi-asserted-by":"publisher","first-page":"1017","DOI":"10.1016\/j.jpdc.2004.03.021","volume":"64","author":"D. Irony","year":"2004","unstructured":"Irony, D., Toledo, S., Tiskin, A.: Communication lower bounds for distributed-memory matrix multiplication. Journal of Parallel and Distributed Computing\u00a064(9), 1017\u20131026 (2004)","journal-title":"Journal of Parallel and Distributed Computing"},{"key":"10_CR16","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.1016\/0167-8191(93)90029-K","volume":"19","author":"S.L. Johnsson","year":"1993","unstructured":"Johnsson, S.L.: Minimizing the communication time for matrix multiplication on multiprocessors. Parallel Comput.\u00a019, 1235\u20131257 (1993)","journal-title":"Parallel Comput."},{"key":"10_CR17","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1145\/1375527.1375544","volume-title":"Proceedings of the 22nd Annual International Conference on Supercomputing ICS 2008","author":"S. Kumar","year":"2008","unstructured":"Kumar, S., Dozsa, G., Almasi, G., Heidelberger, P., Chen, D., Giampapa, M.E., Michael, B., Faraj, A., Parker, J., Ratterman, J., Smith, B., Archer, C.J.: The deep computing messaging framework: generalized scalable message passing on the Blue Gene\/P supercomputer. In: Proceedings of the 22nd Annual International Conference on Supercomputing ICS 2008, pp. 94\u2013103. ACM, New York (2008)"},{"key":"10_CR18","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1007\/PL00008264","volume":"24","author":"W.F. McColl","year":"1999","unstructured":"McColl, W.F., Tiskin, A.: Memory-efficient matrix multiplication in the BSP model. Algorithmica\u00a024, 287\u2013297 (1999)","journal-title":"Algorithmica"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Solomonik, E., Demmel, J.: Communication-optimal parallel 2.5D matrix multiplication and LU factorization algorithms. Tech. Rep. UCB\/EECS-2011-10, EECS Department, University of California, Berkeley (February 2011), http:\/\/www.eecs.berkeley.edu\/Pubs\/TechRpts\/2011\/EECS-2011-10.html","DOI":"10.1007\/978-3-642-23397-5_10"},{"issue":"4","key":"10_CR20","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.: SUMMA: scalable universal matrix multiplication algorithm. Concurrency: Practice and Experience\u00a09(4), 255\u2013274 (1997)","journal-title":"Concurrency: Practice and Experience"}],"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_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,30]],"date-time":"2021-11-30T19:57:32Z","timestamp":1638302252000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-23397-5_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642233968","9783642233975"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-23397-5_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}