{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T07:46:57Z","timestamp":1759132017479,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":21,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642152900"},{"type":"electronic","value":"9783642152917"}],"license":[{"start":{"date-parts":[[2010,1,1]],"date-time":"2010-01-01T00:00:00Z","timestamp":1262304000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2010,1,1]],"date-time":"2010-01-01T00:00:00Z","timestamp":1262304000000},"content-version":"vor","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":[[2010]]},"DOI":"10.1007\/978-3-642-15291-7_29","type":"book-chapter","created":{"date-parts":[[2010,8,30]],"date-time":"2010-08-30T15:56:39Z","timestamp":1283183799000},"page":"316-327","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Optimized Dense Matrix Multiplication on a Many-Core Architecture"],"prefix":"10.1007","author":[{"given":"Elkin","family":"Garcia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis E.","family":"Venetis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rishi","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guang R.","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"29_CR1","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/BF01185206","volume":"12","author":"B. Alpern","year":"1992","unstructured":"Alpern, B., Carter, L., Feig, E., Selker, T.: The uniform memory hierarchy model of computation. Algorithmica\u00a012, 72\u2013109 (1992)","journal-title":"Algorithmica"},{"key":"29_CR2","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1109\/PMMP.1993.315548","volume-title":"Proceedings Programming Models for Massively Parallel Computers","author":"B. Alpern","year":"1993","unstructured":"Alpern, B., Carter, L., Ferrante, J.: Modeling parallel computers as memory hierarchies. In: Proceedings Programming Models for Massively Parallel Computers, pp. 116\u2013123. IEEE Computer Society Press, Los Alamitos (1993)"},{"unstructured":"Amaral, J.N., Gao, G.R., Merkey, P., Sterling, T., Ruiz, Z., Ryan, S.: Performance Prediction for the HTMT: A Programming Example. In: Proceedings of the Third PETAFLOP Workshop (1999)","key":"29_CR3"},{"key":"29_CR4","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. Journal of Supercomputing\u00a04, 357\u2013371 (1991)","journal-title":"Journal of Supercomputing"},{"key":"29_CR5","first-page":"564","volume-title":"Supercomputing 1990: Proceedings of the 1990 ACM\/IEEE conference on Supercomputing","author":"D. Callahan","year":"1990","unstructured":"Callahan, D., Porterfield, A.: Data cache performance of supercomputer applications. In: Supercomputing 1990: Proceedings of the 1990 ACM\/IEEE conference on Supercomputing, pp. 564\u2013572. IEEE Computer Society Press, Los Alamitos (1990)"},{"unstructured":"Cannon, L.E.: A Cellular Computer to Implement the Kalman Filter Algorithm. Ph.D. thesis, Montana State University, Bozeman, MT, USA (1969)","key":"29_CR6"},{"doi-asserted-by":"crossref","unstructured":"Chen, L., Hu, Z., Lin, J., Gao, G.R.: Optimizing the Fast Fourier Transform on a Multi-core Architecture. In: IEEE 2007 International Parallel and Distributed Processing Symposium (IPDPS 2007), pp. 1\u20138 (March 2007)","key":"29_CR7","DOI":"10.1109\/IPDPS.2007.370639"},{"key":"29_CR8","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1145\/207110.207162","volume-title":"PLDI 1995: Proceedings of the ACM SIGPLAN 1995 conference on Programming language design and implementation","author":"S. Coleman","year":"1995","unstructured":"Coleman, S., McKinley, K.S.: Tile size selection using cache organization and data layout. In: PLDI 1995: Proceedings of the ACM SIGPLAN 1995 conference on Programming language design and implementation, pp. 279\u2013290. ACM, New York (1995)"},{"doi-asserted-by":"crossref","unstructured":"Coppersmith, D., Winograd, S.: Matrix Multiplication via Arithmetic Progressions. In: Proceedings of the 19th Annual ACM symposium on Theory of Computing (STOC 1987), New York, NY, USA, pp. 1\u20136 (1987)","key":"29_CR9","DOI":"10.1145\/28395.28396"},{"unstructured":"Cormen, T.H., Leiserson, C.E., Rivest, R.L., Stein, C.: Introduction to Algorithms, 2nd edn. The MIT Press, Cambridge (2001)","key":"29_CR10"},{"unstructured":"Denneau, M.: Warren Jr., H.S.: 64-bit Cyclops: Principles of Operation. Tech. rep., IBM Watson Research Center, Yorktown Heights, NY (April 2005)","key":"29_CR11"},{"doi-asserted-by":"crossref","unstructured":"Douglas, C.C., Heroux, M., Slishman, G., Smith, R.M.: GEMMW: A Portable Level 3 Blas Winograd Variant of Strassen\u2019s Matrix-Matrix Multiply Algorithm (1994)","key":"29_CR12","DOI":"10.1006\/jcph.1994.1001"},{"doi-asserted-by":"crossref","unstructured":"Feng, W.C., Scogland, T.: The Green500 List: Year One. In: 5th IEEE Workshop on High-Performance, Power-Aware Computing. In: Conjunction with the 23rd International Parallel & Distributed Processing Symposium, Rome, Italy (May 2009)","key":"29_CR13","DOI":"10.1109\/IPDPS.2009.5160978"},{"issue":"4","key":"29_CR14","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1145\/98267.98290","volume":"16","author":"N.J. Higham","year":"1990","unstructured":"Higham, N.J.: Exploiting Fast Matrix Multiplication Within the Level 3 BLAS. ACM Transactions on Mathematical Software\u00a016(4), 352\u2013368 (1990)","journal-title":"ACM Transactions on Mathematical Software"},{"key":"29_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1007\/11823285_14","volume-title":"Euro-Par 2006 Parallel Processing","author":"Z. Hu","year":"2006","unstructured":"Hu, Z., del Cuvillo, J., Zhu, W., Gao, G.R.: Optimization of Dense Matrix Multiplication on IBM Cyclops-64: Challenges and Experiences. In: Nagel, W.E., Walter, W.V., Lehner, W. (eds.) Euro-Par 2006. LNCS, vol.\u00a04128, pp. 134\u2013144. Springer, Heidelberg (2006)"},{"key":"29_CR16","first-page":"44","volume-title":"Proc. of the 11th International Conference on Supercomputing (ICS 1997)","author":"H.-J. Lee","year":"1997","unstructured":"Lee, H.-J., Robertson, J.P., Fortes, J.A.B.: Generalized Cannon\u2019s algorithm for parallel matrix multiplication. In: Proc. of the 11th International Conference on Supercomputing (ICS 1997), pp. 44\u201351. ACM, Vienna (1997)"},{"doi-asserted-by":"crossref","unstructured":"Kondo, M., Okawara, H., Nakamura, H., Boku, T., Sakai, S.: Scima: a novel processor architecture for high performance computing. In: Proceedings of the Fourth International Conference\/Exhibition on High Performance Computing in the Asia-Pacific Region, vol.\u00a01, pp. 355\u2013360 (2000)","key":"29_CR17","DOI":"10.1109\/HPC.2000.846577"},{"key":"29_CR18","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1145\/106972.106981","volume-title":"ASPLOS-IV: Proceedings of the fourth international conference on Architectural support for programming languages and operating systems","author":"M.D. Lam","year":"1991","unstructured":"Lam, M.D., Rothberg, E.E., Wolf, M.E.: The cache performance and optimizations of blocked algorithms. In: ASPLOS-IV: Proceedings of the fourth international conference on Architectural support for programming languages and operating systems, pp. 63\u201374. ACM, New York (1991)"},{"key":"29_CR19","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1109\/ICPP.2009.44","volume-title":"ICPP 2009: Proceedings of the 2009 International Conference on Parallel Processing","author":"D.A. Orozco","year":"2009","unstructured":"Orozco, D.A., Gao, G.R.: Mapping the fdtd application to many-core chip architectures. In: ICPP 2009: Proceedings of the 2009 International Conference on Parallel Processing, pp. 309\u2013316. IEEE Computer Society, Washington (2009)"},{"issue":"3","key":"29_CR20","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1007\/BF02165411","volume":"14","author":"V. Strassen","year":"1969","unstructured":"Strassen, V.: Gaussian Elimination is not Optimal. Numerische Mathematik\u00a014(3), 354\u2013356 (1969)","journal-title":"Numerische Mathematik"},{"doi-asserted-by":"crossref","unstructured":"Venetis, I.E., Gao, G.R.: Mapping the LU Decomposition on a Many-Core Architecture: Challenges and Solutions. In: Proceedings of the 6th ACM Conference on Computing Frontiers (CF 2009), Ischia, Italy, pp. 71\u201380 (May 2009)","key":"29_CR21","DOI":"10.1145\/1531743.1531756"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2010 - Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-15291-7_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,19]],"date-time":"2020-05-19T14:28:08Z","timestamp":1589898488000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-15291-7_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642152900","9783642152917"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-15291-7_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}