{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T18:03:13Z","timestamp":1793037793301,"version":"4.5.0"},"publisher-location":"Berlin, Heidelberg","reference-count":37,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642195945","type":"print"},{"value":"9783642195952","type":"electronic"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-19595-2_10","type":"book-chapter","created":{"date-parts":[[2011,2,24]],"date-time":"2011-02-24T07:17:18Z","timestamp":1298531838000},"page":"136-150","source":"Crossref","is-referenced-by-count":35,"title":["A Programming Language Interface to Describe Transformations and Code Generation"],"prefix":"10.1007","author":[{"given":"Gabe","family":"Rudy","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Malik Murtaza","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mary","family":"Hall","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacqueline","family":"Chame","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Ahmed, N., Mateev, N., Pingali, K.: Synthesizing transformations for locality enhancement of imperfectly-nested loop nests. In: Proceedings of the 2000 ACM International Conference on Supercomputing (May 2000)","DOI":"10.1109\/SC.2000.10018"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Bailey, D.H., Chame, J., Chen, C., Dongarra, J., Hall, M., Hollingsworth, J.K., Hovland, P., Moore, S., Seymour, K., Shin, J., Tiwari, A., Williams, S., You, H.: PERI auto-tuning. Journal of Physics: Conference Series\u00a0125(1) (2008)","DOI":"10.1088\/1742-6596\/125\/1\/012089"},{"key":"10_CR3","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1145\/1375527.1375562","volume-title":"Proceedings of the 22nd Annual International Conference on Supercomputing, ICS 2008","author":"M.M. Baskaran","year":"2008","unstructured":"Baskaran, M.M., Bondhugula, U., Krishnamoorthy, S., Ramanujam, J., Rountev, A., Sadayappan, P.: A compiler framework for optimization of affine loop nests for GPGPUs. In: Proceedings of the 22nd Annual International Conference on Supercomputing, ICS 2008, pp. 225\u2013234. ACM, New York (2008)"},{"issue":"6","key":"10_CR4","doi-asserted-by":"publisher","first-page":"1768","DOI":"10.1145\/197320.197366","volume":"16","author":"S. Carr","year":"1994","unstructured":"Carr, S., Kennedy, K.: Improving the ratio of memory operations to floating-point operations in loops. ACM Transactions on Programming Languages and Systems\u00a016(6), 1768\u20131810 (1994)","journal-title":"ACM Transactions on Programming Languages and Systems"},{"key":"10_CR5","unstructured":"Chen, C.: Model-Guided Empirical Optimization for Memory Hierarchy. PhD thesis, University of Southern California (May 2007)"},{"key":"10_CR6","unstructured":"Chen, C., Chame, J., Hall, M.: CHiLL: A framework for composing high-level loop transformations. Technical Report 08-897, University of Southern California (June 2008)"},{"key":"10_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1007\/978-3-540-69330-7_10","volume-title":"Languages and Compilers for Parallel Computing","author":"S. Donadio","year":"2006","unstructured":"Donadio, S., Brodman, J., Roeder, T., Yotov, K., Barthou, D., Cohen, A., Garzar\u00e1n, M.J., Padua, D., Pingali, K.: A language for the compact representation of multiple program versions. In: Ayguad\u00e9, E., Baumgartner, G., Ramanujam, J., Sadayappan, P. (eds.) LCPC 2005. LNCS, vol.\u00a04339, pp. 136\u2013151. Springer, Heidelberg (2006)"},{"issue":"3","key":"10_CR8","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s10766-006-0012-3","volume":"34","author":"S. Girbal","year":"2006","unstructured":"Girbal, S., Vasilache, N., Bastoul, C., Cohen, A., Parello, D., Sigler, M., Temam, O.: Semi-automatic composition of loop transformations for deep parallelism and memory hierarchies. International Journal of Parallel Programming\u00a034(3), 261\u2013317 (2006)","journal-title":"International Journal of Parallel Programming"},{"key":"10_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1007\/978-3-642-13374-9_4","volume-title":"Languages and Compilers for Parallel Computing","author":"M. Hall","year":"2010","unstructured":"Hall, M., Chame, J., Chen, C., Shin, J., Rudy, G., Khan, M.M.: Loop transformation recipes for code generation and auto-tuning. In: Gao, G.R., Pollock, L.L., Cavazos, J., Li, X. (eds.) LCPC 2009. LNCS, vol.\u00a05898, pp. 50\u201364. Springer, Heidelberg (2010)"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Hartono, A., Norris, B., Sadayappan, P.: Annotation-based empirical performance tuning using Orio. In: Proceedings of the 23rd International Parallel and Distributed Processing Symposium (May 2009)","DOI":"10.1109\/IPDPS.2009.5161004"},{"key":"10_CR11","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1002\/(SICI)1097-024X(199606)26:6<635::AID-SPE26>3.0.CO;2-P","volume":"26","author":"R. Ierusalimschy","year":"1996","unstructured":"Ierusalimschy, R., de Figueiredo, L.H., Filho, W.C.: Lua an extensible extension language. Softw. Pract. Exper.\u00a026, 635\u2013652 (1996)","journal-title":"Softw. Pract. Exper."},{"issue":"4","key":"10_CR12","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1145\/567097.567101","volume":"24","author":"M. Jim\u00e9nez","year":"2002","unstructured":"Jim\u00e9nez, M., Llaber\u00eda, J.M., Fern\u00e1ndez, A.: Register tiling in nonrectangular iteration spaces. ACM Transactions on Programming Languages and Systems\u00a024(4), 409\u2013453 (2002)","journal-title":"ACM Transactions on Programming Languages and Systems"},{"key":"10_CR13","unstructured":"Kelly, W., Pugh, W.: A framework for unifying reordering transformations. Technical Report CS-TR-3193, Department of Computer Science, University of Maryland (1993)"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Kennedy, K., McKinley, K.: Optimizing for parallelism and data locality. In: ACM International Conference on Supercomputing (July 1992)","DOI":"10.1145\/143369.143427"},{"key":"10_CR15","volume-title":"Programming Massively Parallel Processors: A Hands-on Approach","author":"D. Kirk","year":"2010","unstructured":"Kirk, D., Hwu, W.: Programming Massively Parallel Processors: A Hands-on Approach. Morgan Kaufmann Publishers, San Francisco (2010)"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Kodukula, I., Ahmed, N., Pingali, K.: Data-centric multi-level blocking. In: Proceedings of ACM SIGPLAN Conference on Programming Languages Design and Implementation (June 1997)","DOI":"10.1145\/258915.258946"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Lee, S., Min, S.-J., Eigenmann, R.: OpenMP to GPGPU: a compiler framework for automatic translation and optimization. In: ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (February 2009)","DOI":"10.1145\/1504176.1504194"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Lim, A.W., Lam, M.S.: Maximizing parallelism and minimizing synchronization with affine partitioning. In: Proceedings of ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages (POPL 1997) (January 1997)","DOI":"10.1145\/263699.263719"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Lim, A.W., Liao, S.-W., Lam, M.S.: Blocking and array contraction across arbitrarily nested loops using affine partitioning. In: ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (June 2001)","DOI":"10.1145\/379539.379586"},{"issue":"4","key":"10_CR20","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1145\/233561.233564","volume":"18","author":"K.S. McKinley","year":"1996","unstructured":"McKinley, K.S., Carr, S., Tseng, C.-W.: Improving data locality with loop transformations. ACM Transactions on Programming Languages and Systems\u00a018(4), 424\u2013453 (1996)","journal-title":"ACM Transactions on Programming Languages and Systems"},{"key":"10_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1007\/3-540-44905-1_11","volume-title":"Languages and Compilers for Parallel Computing","author":"B. Pugh","year":"2000","unstructured":"Pugh, B., Rosser, E.: Iteration space slicing for locality. In: Carter, L., Ferrante, J. (eds.) LCPC 1999. LNCS, vol.\u00a01863, p. 164. Springer, Heidelberg (2000)"},{"key":"10_CR22","unstructured":"Qasem, A., Jin, G., Mellor-Crummey, J.: Improving performance with integrated program transformations. Technical Report TR03-419, Rice University (October 2003)"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Rivera, G., Tseng, C.-W.: Data transformations for eliminating conflict misses. In: Proceedings of ACM SIGPLAN Conference on Programming Languages Design and Implementation (June 1998)","DOI":"10.1145\/277650.277661"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Rudy, G.: CUDA-CHiLL: A programming language interface for GPGPU optimizations and code generation. Master\u2019s thesis, University of Utah (May 2010)","DOI":"10.1007\/978-3-642-19595-2_10"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Sarkar, V., Thekkath, R.: A general framework for iteration-reordering loop transformations. In: Proceedings of ACM SIGPLAN Conference on Programming Languages Design and Implementation (June 1992)","DOI":"10.1145\/143095.143132"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Shin, J., Hall, M., Chame, J., Chen, C., Fischer, P.F., Hovland, P.D.: Speeding up nek5000 with autotuning and specialization. In: Proceedings of the 2010 ACM International Conference on Supercomputing (June 2010)","DOI":"10.1145\/1810085.1810120"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Shin, J., Hall, M.W., Chame, J., Chen, C., Hovland, P.D.: Autotuning and specialization: Speeding up matrix multiply for small matrices with compiler technology. In: Proceedings of the 4th International Workshop on Automatic Performance Tuning (October 2009)","DOI":"10.1007\/978-1-4419-6935-4_20"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Temam, O., Granston, E.D., Jalby, W.: To copy or not to copy: A compile-time technique for assessing when data copying should be used to eliminate cache conflicts. In: Proceedings of Supercomputing 1993 (November 1993)","DOI":"10.1145\/169627.169762"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Tiwari, A., Chen, C., Chame, J., Hall, M., Hollingsworth, J.K.: A scalable auto-tuning framework for compiler optimization. In: Proceedings of the 24th International Parallel and Distributed Processing Symposium (April 2009)","DOI":"10.1109\/IPDPS.2009.5161054"},{"key":"10_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-540-89740-8_1","volume-title":"Languages and Compilers for Parallel Computing","author":"S.-Z. Ueng","year":"2008","unstructured":"Ueng, S.-Z., Lathara, M., Baghsorkhi, S.S., Hwu, W.-m.W.: CUDA-Lite: Reducing GPU Programming Complexity. In: Amaral, J.N. (ed.) LCPC 2008. LNCS, vol.\u00a05335, pp. 1\u201315. Springer, Heidelberg (2008)"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Wolf, M.E., Lam, M.S.: A data locality optimizing algorithm. In: Proceedings of ACM SIGPLAN Conference on Programming Languages Design and Implementation (June 1991)","DOI":"10.1145\/113445.113449"},{"issue":"4","key":"10_CR32","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1109\/71.97902","volume":"2","author":"M.E. Wolf","year":"1991","unstructured":"Wolf, M.E., Lam, M.S.: A loop transformation theory and an algorithm to maximize parallelism. IEEE Transactions on Parallel and Distributed Systems\u00a02(4), 452\u2013471 (1991)","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"10_CR33","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1145\/76263.76337","volume-title":"Proceedings of the 1989 ACM\/IEEE Conference on Supercomputing","author":"M. Wolfe","year":"1989","unstructured":"Wolfe, M.: More iteration space tiling. In: Proceedings of the 1989 ACM\/IEEE Conference on Supercomputing, pp. 655\u2013664. ACM, New York (1989)"},{"issue":"4","key":"10_CR34","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/BF00129834","volume":"4","author":"M. Wolfe","year":"1991","unstructured":"Wolfe, M.: Data dependence and program restructuring. The Journal of Supercomputing\u00a04(4), 321\u2013344 (1991)","journal-title":"The Journal of Supercomputing"},{"issue":"6","key":"10_CR35","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1145\/1809028.1806606","volume":"45","author":"Y. Yang","year":"2010","unstructured":"Yang, Y., Xiang, P., Kong, J., Zhou, H.: A gpgpu compiler for memory optimization and parallelism management. SIGPLAN Not.\u00a045(6), 86\u201397 (2010)","journal-title":"SIGPLAN Not."},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Yi, Q., Seymour, K., You, H., Vuduc, R., Quinlan, D.: POET: parameterized optimizations for empirical tuning. In: Proceedings of the 21st International Parallel and Distributed Processing Symposium (March 2007)","DOI":"10.1109\/IPDPS.2007.370637"},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Zima, H., Hall, M., Chen, C., Chame, J.: Model-guided autotuning of high-productivity languages for petascale computing. In: Proceedings of the 18th ACM International Symposium on High Performance Distributed Computing (HPDC 2009) (June 2009)","DOI":"10.1145\/1551609.1551611"}],"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\/978-3-642-19595-2_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,19]],"date-time":"2021-11-19T11:27:11Z","timestamp":1637321231000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-19595-2_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642195945","9783642195952"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-19595-2_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011]]}}}