{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T05:16:25Z","timestamp":1738300585813,"version":"3.35.0"},"publisher-location":"Berlin, Heidelberg","reference-count":19,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540695004"},{"type":"electronic","value":"9783540695011"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-69501-1_23","type":"book-chapter","created":{"date-parts":[[2008,6,2]],"date-time":"2008-06-02T07:20:45Z","timestamp":1212391245000},"page":"220-232","source":"Crossref","is-referenced-by-count":3,"title":["Adaptive Loop Tiling for a Multi-cluster CMP"],"prefix":"10.1007","author":[{"given":"Jisheng","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Matthew","family":"Horsnell","sequence":"additional","affiliation":[]},{"given":"Mikel","family":"Luj\u00e1n","sequence":"additional","affiliation":[]},{"given":"Ian","family":"Rogers","sequence":"additional","affiliation":[]},{"given":"Chris","family":"Kirkham","sequence":"additional","affiliation":[]},{"given":"Ian","family":"Watson","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"23_CR1","unstructured":"Lattice boltzmann method, http:\/\/www.latticeboltzmann.com\/"},{"key":"23_CR2","unstructured":"The Jamaica Project (May 2005), http:\/\/www.cs.manchester.ac.uk\/apt\/projects\/jamaica"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, E., Bai, Z., Bischof, C., Blackford, L.S., Demmel, J., Dongarra, J.J., Du Croz, J., Hammarling, S., Greenbaum, A., McKenney, A., Sorensen, D.: LAPACK Users\u2019 guide, 3rd edn. Society for Industrial and Applied Mathematics, Philadelphia (1999)","DOI":"10.1137\/1.9780898719604"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Arnold, M., Fink, S.J., Grove, D., Hind, M., Sweeney, P.F.: Adaptive optimization in the Jalape\u00f1o JVM. In: ACM SIGPLAN International Conference on Object-Oriented Programming, Systems, Languages, and Applications, pp. 47\u201365 (2000)","DOI":"10.1145\/354222.353175"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Burke, M., Choi, J., Fink, S., Grove, D., Hind, M., Sarkar, V., Serrano, M., Sreedhar, V., Srinivasan, H., Whaley, J.: The Jalape\u00f1o dynamic optimizing compiler for Java. In: Proceedings ACM 1999 Java Grande Conference, San Francisco, CA, United States, June 1999, pp. 129\u2013141. ACM (1999)","DOI":"10.1145\/304065.304113"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Carr, S., Kennedy, K.: Compiler blockability of numerical algorithms. Supercomputing, 114\u2013124 (1992)","DOI":"10.1109\/SUPERC.1992.236704"},{"key":"23_CR7","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1145\/207110.207162","volume-title":"SIGPLAN 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: SIGPLAN Conference on Programming Language Design and Implementation, pp. 279\u2013290. ACM Press, New York (1995)"},{"issue":"1","key":"23_CR8","first-page":"13","volume":"1","author":"G. Fursin","year":"2006","unstructured":"Fursin, G., Cohen, A., O\u2019Boyle, M., Temam, O.: Quick and practical run-time evaluation of multiple program optimizations. Transactions on High-Performance Embedded Architectures and Compilers\u00a01(1), 13\u201331 (2006)","journal-title":"Transactions on High-Performance Embedded Architectures and Compilers"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Hammond, L., Hubbard, B.A., Siu, M., Prabhu, M.K., Chen, M., Olukotun, K.: The Stanford Hydra CMP. IEEE Micro, 71\u201384 (March\u2013April 2000)","DOI":"10.1109\/40.848474"},{"key":"23_CR10","unstructured":"Horsnell, M.J.: A chip multi-cluster architecture with locality aware task distribution. PhD thesis, The University of Manchester (2007)"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Kisuki, T., Knijnenburg, P.M.W., O\u2019Boyle, M.F.P.: Combined selection of tile sizes and unroll factors using iterative compilation. In: International Conference on Parallel Architectures and Compilation Techniques, pp. 237\u2013246 (2000)","DOI":"10.1109\/PACT.2000.888348"},{"issue":"2","key":"23_CR12","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/MM.2005.35","volume":"25","author":"P. Kongetira","year":"2005","unstructured":"Kongetira, P., Aingaran, K., Olukotun, K.: Niagara: A 32-way multithreaded sparc processor. IEEE Micro\u00a025(2), 21\u201329 (2005)","journal-title":"IEEE Micro"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Lam, M.S., Rothberg, E.E., Wolf, M.E.: The cache performance and optimizations of blocked algorithms. In: International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 63\u201374 (1991)","DOI":"10.1145\/106972.106981"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Voss, M., Eigenmann, R.: High-level adaptive program optimization with ADAPT. In: ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 93\u2013102 (2001)","DOI":"10.1145\/379539.379583"},{"issue":"2","key":"23_CR15","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1002\/spe.626","volume":"35","author":"R.C. Whaley","year":"2005","unstructured":"Whaley, R.C., Petitet, A.: Minimizing development and maintenance costs in supporting persistently optimized BLAS. Software: Practice and Experience\u00a035(2), 101\u2013121 (2005)","journal-title":"Software: Practice and Experience"},{"issue":"1\u20132","key":"23_CR16","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0167-8191(00)00087-9","volume":"27","author":"R.C. Whaley","year":"2001","unstructured":"Whaley, R.C., Petitet, A., Dongarra, J.J.: Automated empirical optimizations of software and the ATLAS project. Parallel Computing\u00a027(1\u20132), 3\u201335 (2001)","journal-title":"Parallel Computing"},{"key":"23_CR17","volume-title":"High performance compilers for parallel computing","author":"M.J. Wolfe","year":"1996","unstructured":"Wolfe, M.J.: High performance compilers for parallel computing. Addison-Wesley, Redwood City (1996)"},{"key":"23_CR18","unstructured":"Wright, G.: A single-chip multiprocessor architecture with hardware thread support. PhD thesis, The University of Manchester (2001)"},{"key":"23_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/978-3-540-74466-5_29","volume-title":"Euro-Par 2007 Parallel Processing","author":"J. Zhao","year":"2007","unstructured":"Zhao, J., Horsnell, M., Rogers, I., Dinn, A., Kirkham, C.C., Watson, I.: Optimizing chip multiprocessor work distribution using dynamic compilation. In: Kermarrec, A.-M., Boug\u00e9, L., Priol, T. (eds.) Euro-Par 2007. LNCS, vol.\u00a04641, pp. 258\u2013267. Springer, Heidelberg (2007)"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-69501-1_23.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T14:38:40Z","timestamp":1738247920000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-69501-1_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540695004","9783540695011"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-69501-1_23","relation":{},"subject":[]}}