{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T04:54:01Z","timestamp":1725512041280},"publisher-location":"Berlin, Heidelberg","reference-count":36,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540693291"},{"type":"electronic","value":"9783540693307"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/978-3-540-69330-7_9","type":"book-chapter","created":{"date-parts":[[2007,5,14]],"date-time":"2007-05-14T21:16:20Z","timestamp":1179177380000},"page":"121-135","source":"Crossref","is-referenced-by-count":5,"title":["Optimizing Matrix Multiplication with a Classifier Learning System"],"prefix":"10.1007","author":[{"given":"Xiaoming","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mar\u00eda Jes\u00fas","family":"Garzar\u00e1n","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"9_CR1","unstructured":"ATLAS home page, http:\/\/math-atlas.sourceforge.net\/errata.html#tuneCE"},{"key":"9_CR2","unstructured":"ATLAS home page, http:\/\/math-atlas.sourceforge.net\/faq.html#NB80"},{"issue":"5","key":"9_CR3","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1109\/TC.1981.1675792","volume":"30","author":"W. Abu-Sufah","year":"1981","unstructured":"Abu-Sufah, W., Kuck, D., Lawrie, D.: On the Performance Enhancememt of Paging Systems through Program Analysis and Transformations. IEEE Transactions on Computers\u00a030(5), 341\u2013356 (1981)","journal-title":"IEEE Transactions on Computers"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Bilmes, J., Asanovic, K., Chin, C., Demmel, J.: OptimizingMatrixMultiply using PHiPAC: A Portable, High-Performance, ANSI C Coding Methodology. In: Proc. of the 11th ACM International Conference on Supercomputing (ICS) (July 1997)","DOI":"10.1145\/263580.263662"},{"key":"9_CR5","first-page":"80","volume-title":"Proc. of the Symposium on Principles and Practice of Parallel Programming (PPoPP)","author":"E.A. Brewer","year":"1995","unstructured":"Brewer, E.A.: High-level Optimization via Automated Statistical Modeling. In: Proc. of the Symposium on Principles and Practice of Parallel Programming (PPoPP), pp. 80\u201391. ACM Press, New York (1995)"},{"key":"9_CR6","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/3-540-44640-0_15","volume-title":"Advances in Learning Classifier Systems","author":"M.V. Butz","year":"2001","unstructured":"Butz, M.V., Wilson, S.W.: An Algorithmic Description of XCS. In: Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds.) IWLCS 2000. LNCS (LNAI), vol.\u00a01996, pp. 253\u2013272. Springer, Heidelberg (2001)"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Chatterjee, S., Jain, V.V., Lebeck, A.R., Mundhra, S., Thottethodi, M.: Nonlinear Array Layouts for Hierarchical Memory Systems. In: International Conference on Supercomputing, pp. 444\u2013453 (1999)","DOI":"10.1145\/305138.305231"},{"key":"9_CR8","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1109\/TPDS.2002.1058095","volume":"13","author":"S. Chatterjee","year":"2002","unstructured":"Chatterjee, S., Lebeck, A.R., Patnala, P.K., Thotterhodi, M.: Recursive array layouts and fast matrix multiplication. IEEE Transactions on Parallel and Distributed Systems\u00a013, 1105\u20131123 (2002)","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Coleman, S., McKinley, K.s.: Tile Selection Using Cache Organization and Data Layout. In: Proc. of Int. Conference Programming Language Design and Implementation, June 1995, pp. 279\u2013290 (1995)","DOI":"10.1145\/207110.207162"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Frens, J., Wise, D.: Auto-blocking Matrix-Multiplication or Tracking BLAS3 Performance with Source Code. In: Proc. of the Intenational Symp. on Principles and Practice of Parallel programming (PPoPP), June 1997, pp. 206\u2013216 (1997)","DOI":"10.1145\/263764.263789"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Frigo, M.: A Fast Fourier Transform Compiler. In: Proc. of Programing Language Design and Implementation (1999)","DOI":"10.1145\/301618.301661"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Frigo, M., Leiserson, C.E., Prokop, H., Ramachandran, S.: Cache-Oblivious Algorithms. In: Proc. of the Intenational Symp. on Foundations of Computer Science (FOCS) (October 1999)","DOI":"10.1109\/SFFCS.1999.814600"},{"key":"9_CR13","volume-title":"Genetic Algorithms in Search, Optimization, and Machine Learning","author":"D. Goldberg","year":"1989","unstructured":"Goldberg, D.: Genetic Algorithms in Search, Optimization, and Machine Learning. Addison- Wesley, Reading (1989)"},{"issue":"6","key":"9_CR14","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1147\/rd.416.0737","volume":"41","author":"F.G. Gustavson","year":"1997","unstructured":"Gustavson, F.G.: Recursion Leads to Automatic Variable Blocking for Dense Linear-Algebra Algorithms. IBM Journal of Research and Development\u00a041(6), 737\u2013755 (1997)","journal-title":"IBM Journal of Research and Development"},{"key":"9_CR15","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/BF01199431","volume":"38","author":"D. Hilbert","year":"1891","unstructured":"Hilbert, D.: \u00dcber Stetige Abbildung einer Linie auf ein Fl\u00e4chenstr\u00fcck. Mathematische Annalen\u00a038, 459\u2013460 (1891)","journal-title":"Mathematische Annalen"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Lam, M., Rothberg, E., Wolf, M.E.: The Cache Performance and Optimizations of Blocked Algorithms. In: Proc. of the Int. conf. on Architectural Support for Programming Languages and Operating Systems (ASPLOS), October 1991, pp. 63\u201374 (1991)","DOI":"10.1145\/106972.106981"},{"key":"9_CR17","unstructured":"Li, X., Garzar\u00e1n, M.J., Padua, D.: A Dynamically Tuned Sorting Library. In: Proc. of the Int. Symp. on Code Generation and Optimization, pp. 111\u2013124 (2004)"},{"key":"9_CR18","unstructured":"Li, X., Garzar\u00e1n, M.J., Padua, D.: Optimizing Sorting with Genetic Algorithms. In: Proc. of the Int. Symp. on Code Generation and Optimization, March 2005, pp. 99\u2013110 (2005)"},{"issue":"3","key":"9_CR19","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1145\/362875.362879","volume":"12","author":"A. McKellar","year":"1969","unstructured":"McKellar, A., Coffman, E.: Organizing Matrices andMatrix Operations for Paged Memory Systems. Communications of the ACM\u00a012(3), 153\u2013165 (1969)","journal-title":"Communications of the ACM"},{"issue":"6","key":"9_CR20","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1023\/A:1018782528453","volume":"26","author":"N. Mitchell","year":"1998","unstructured":"Mitchell, N., Hogstedt, K., Carter, L., Ferrante, J.: Quantifying the Multi-Level Nature of Tiling Interactions. Int. Journal of Parallel Programming\u00a026(6), 641\u2013670 (1998)","journal-title":"Int. Journal of Parallel Programming"},{"issue":"2","key":"9_CR21","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/12.752655","volume":"48","author":"P. Panda","year":"1999","unstructured":"Panda, P., Nakamura, H., Dutt, N., Nicolau, A.: Augmenting Loop Tiling with Data Alignment for Improved Cache Performance. IEEE Trans. on Computers\u00a048(2), 142\u2013149 (1999)","journal-title":"IEEE Trans. on Computers"},{"issue":"7","key":"9_CR22","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPDS.2003.1214317","volume":"14","author":"N. Park","year":"2003","unstructured":"Park, N., Hong, B., Prasanna, V.: Tiling, Block Data Layout, and Memory Hierarchy Performance. IEEE Trans. on Parallel and Distributed Systems\u00a014(7), 640\u2013654 (2003)","journal-title":"IEEE Trans. on Parallel and Distributed Systems"},{"key":"9_CR23","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/BF01199438","volume":"36","author":"G. Peano","year":"1890","unstructured":"Peano, G.: Sur Une Curbe qui Remplit Toute une Aire Plaine. Mathematische Annalen\u00a036, 157\u2013160 (1890)","journal-title":"Mathematische Annalen"},{"key":"9_CR24","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45027-0","volume-title":"Learning Classifier Systems, From Foundations to Applications","author":"W.S. Pier Luca Lanzi","year":"2000","unstructured":"Pier Luca Lanzi, W.S., Wilson, S.W.: Learning Classifier Systems, From Foundations to Applications. Springer, Heidelberg (2000)"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Rivera, G., Tseng, C.: Data Transformations for Eliminating conflict Misses. In: Proc. of Int. Conference Programming Language Design and Implementation, June 1998, pp. 38\u201349 (1998)","DOI":"10.1145\/277650.277661"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Rivera, G., Tseng, C.: Locality Optimizations for Multi-Level Caches. In: Proc. of IEEE Supercomputing (November 1999)","DOI":"10.1145\/331532.331534"},{"key":"9_CR27","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-0871-6","volume-title":"Space-Filling Curves","author":"H. Sagan","year":"1994","unstructured":"Sagan, H.: Space-Filling Curves. Springer, Heidelberg (1994)"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Temam, O., Granston, E., Jalby, W.: To Copy or Not to Copy: A Compile\u2013Time Technique for Assessing When Data Copying Should be Used to Eliminate Cache Conflicts. In: Proc. of the ACM\/IEEE Supercomputing Conference (November 1993)","DOI":"10.1145\/169627.169762"},{"key":"9_CR29","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1145\/1065944.1065981","volume-title":"Proc. of Symposium on Principles and Practice of Parallel Programming (PPoPP)","author":"N. Thomas","year":"2005","unstructured":"Thomas, N., Tanase, G., Tkachyshyn, O., Perdue, J., Amato, N.M., Rauchwerger, L.: A Framework for Adaptive Algorithm Selection in STAPL. In: Proc. of Symposium on Principles and Practice of Parallel Programming (PPoPP), pp. 277\u2013288. ACM Press, New York (2005)"},{"issue":"1-2","key":"9_CR30","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0167-8191(00)00087-9","volume":"27","author":"R. Whaley","year":"2001","unstructured":"Whaley, R., Petitet, A., Dongarra, J.: Automated Empirical Optimizations of Sofware and the ATLAS Project. Parallel Computing\u00a027(1-2), 3\u201335 (2001)","journal-title":"Parallel Computing"},{"issue":"2","key":"9_CR31","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1162\/evco.1995.3.2.149","volume":"3","author":"S.W. Wilson","year":"1995","unstructured":"Wilson, S.W.: Classifier Fitness Based on Accuracy. Evolutionary Computation\u00a03(2), 149\u2013175 (1995)","journal-title":"Evolutionary Computation"},{"key":"9_CR32","unstructured":"Wolfe, M.: Iteration Space Tiling for Memory Hierarchies. In: Third SIAM Conference on Parallel Processing for Scientific Computing (December 1987)"},{"key":"9_CR33","doi-asserted-by":"crossref","unstructured":"Xiong, J., Johnson, J., Johnson, R., Padua, D.: SPL: A Language and a Compiler for DSP Algorithms. In: Proc. of the International Conference on Programming Language Design and Implementation, pp. 298\u2013308 (2001)","DOI":"10.1145\/378795.378860"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Yi, Q., Adve, V., Kennedy, K.: Transforming Loops To Recursion for Multi-LevelMemory Hierarchies. In: Proc. of the Int. Conf. on Programming Language Design and Implementation (PLDI), June 2000, pp. 169\u2013181 (2000)","DOI":"10.1145\/358438.349323"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Yotov, K., Li, X., Ren, G., Cibulskis, M., DeJong, G., Garzar\u00e1n, M., Padua, D., Pingali, K., Stodghill, P., Wu, P.: A Comparison of Empirical and Model-driven Optimization. In: Proc. of Programing Language Design and Implementation, June 2003, pp. 63\u201376 (2003)","DOI":"10.1145\/781139.781140"},{"key":"9_CR36","first-page":"358","volume":"23","author":"K. Yotov","year":"2005","unstructured":"Yotov, K., Li, X., Ren, G., Garzar\u00e1n, M.J., Padua, D., Pingali, K., Stodghill, P.: Is Search Really Necessary to Generate a High Performance Blas? Proc. of the IEEE, special issue on Program Generation, Optimization, and Platform Adaptation\u00a023, 358\u2013386 (2005)","journal-title":"Proc. of the IEEE, special issue on Program Generation, Optimization, and Platform Adaptation"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-69330-7_9.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T04:57:40Z","timestamp":1605761860000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-69330-7_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540693291","9783540693307"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-69330-7_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}