{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T10:41:18Z","timestamp":1725532878749},"publisher-location":"Berlin, Heidelberg","reference-count":26,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642022845"},{"type":"electronic","value":"9783642023033"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"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":[[2009]]},"DOI":"10.1007\/978-3-642-02303-3_12","type":"book-chapter","created":{"date-parts":[[2009,5,21]],"date-time":"2009-05-21T00:12:28Z","timestamp":1242864748000},"page":"140-153","source":"Crossref","is-referenced-by-count":4,"title":["Tile Reduction: The First Step towards Tile Aware Parallelization in OpenMP"],"prefix":"10.1007","author":[{"given":"Ge","family":"Gan","sequence":"first","affiliation":[]},{"given":"Xu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Joseph","family":"Manzano","sequence":"additional","affiliation":[]},{"given":"Guang R.","family":"Gao","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"#cr-split#-12_CR1.1","doi-asserted-by":"crossref","unstructured":"Anderson, J.M., Amarasinghe, S.P., Lam, M.S.: Data and computation transformations for multiprocessors. In: Proceedings of the Fifth ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming, Santa Barbara, California, July 19???21, pp. 166???178 (1995);","DOI":"10.1145\/209936.209954"},{"key":"#cr-split#-12_CR1.2","doi-asserted-by":"crossref","unstructured":"Anderson, J.M., Amarasinghe, S.P., Lam, M.S.: Data and computation transformations for multiprocessors. In: Proceedings of the Fifth ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming, Santa Barbara, California, July 19\u201321, pp. 166\u2013178 (1995); SIGPLAN Notices 30(8) (August 1995)","DOI":"10.1145\/209937.209954"},{"key":"#cr-split#-12_CR2.1","doi-asserted-by":"crossref","unstructured":"Anderson, J.M., Lam, M.S.: Global optimizations for parallelism and locality on scalable parallel machines. In: Proceedings of the ACM SIGPLAN 1993 Conference on Programming Language Design and Implementation, Albuquerque, New Mexico, June 23???25, pp. 112???125 (1993);","DOI":"10.1145\/155090.155101"},{"key":"#cr-split#-12_CR2.2","doi-asserted-by":"crossref","unstructured":"Anderson, J.M., Lam, M.S.: Global optimizations for parallelism and locality on scalable parallel machines. In: Proceedings of the ACM SIGPLAN 1993 Conference on Programming Language Design and Implementation, Albuquerque, New Mexico, June 23\u201325, pp. 112\u2013125 (1993); SIGPLAN Notices 28(6) (June 1993)","DOI":"10.1145\/173262.155101"},{"key":"#cr-split#-12_CR3.1","doi-asserted-by":"crossref","unstructured":"Wolf, M.E., Lam, M.S.: A data locality optimizing algorithm. In: Proceedings of the ACM SIGPLAN 1991 Conference on Programming Language Design and Implementation, Toronto, Ontario, June 26???28, pp. 30???44 (1991);","DOI":"10.1145\/113445.113449"},{"key":"#cr-split#-12_CR3.2","doi-asserted-by":"crossref","unstructured":"Wolf, M.E., Lam, M.S.: A data locality optimizing algorithm. In: Proceedings of the ACM SIGPLAN 1991 Conference on Programming Language Design and Implementation, Toronto, Ontario, June 26\u201328, pp. 30\u201344 (1991); SIGPLAN Notices 26(6) (June 1991)","DOI":"10.1145\/113446.113449"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Lim, A.W., Lam, M.S.: Maximizing parallelism and minimizing synchronization with affine transforms. In: Conference Record of POPL 1997: The 24th ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages, Paris, January 15\u201317, pp. 201\u2013214 (1997)","DOI":"10.1145\/263699.263719"},{"key":"12_CR5","unstructured":"High Performance Fortran Forum: High-performance fortran language specification version 2.0. Technical report, Rice University (1997)"},{"key":"12_CR6","volume-title":"UPC: Distributed Shared-Memory Programming","author":"T. El-Ghazawi","year":"2003","unstructured":"El-Ghazawi, T., Carlson, W., Sterling, T., Yelick, K.: UPC: Distributed Shared-Memory Programming. Wiley-Interscience, Hoboken (2003)"},{"key":"12_CR7","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1145\/1094811.1094852","volume-title":"OOPSLA 2005: Proceedings of the 20th annual ACM SIGPLAN conference on Object oriented programming, systems, languages and applications","author":"P. Charles","year":"2005","unstructured":"Charles, P., Grothoff, C., Saraswat, V., Donawa, C., Kielstra, A., Ebcioglu, K., von Praun, C., Sarkar, V.: X10: an object-oriented approach to non-uniform cluster computing. In: OOPSLA 2005: Proceedings of the 20th annual ACM SIGPLAN conference on Object oriented programming, systems, languages and applications, pp. 519\u2013538. ACM, New York (2005)"},{"key":"12_CR8","unstructured":"Deitz, S.J.: High-level programming language abstractions for advanced and dynamic parallel computations. Ph.D thesis, Seattle, WA, USA, Chair-Lawrence Snyder (2005)"},{"key":"12_CR9","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/PACT.2004.1342539","volume-title":"PACT 2004: Proceedings of the 13th International Conference on Parallel Architectures and Compilation Techniques","author":"Y. Dotsenko","year":"2004","unstructured":"Dotsenko, Y., Coarfa, C., Mellor-Crummey, J.: A multi-platform co-array fortran compiler. In: PACT 2004: Proceedings of the 13th International Conference on Parallel Architectures and Compilation Techniques, Washington, DC, USA, pp. 29\u201340. IEEE Computer Society, Los Alamitos (2004)"},{"key":"12_CR10","unstructured":"Hilfinger, P.N., Bonachea, D., Gay, D., Graham, S., Liblit, B., Pike, G., Yelick, K.: Titanium language reference manual. Technical report, Berkeley, CA, USA (2001)"},{"key":"12_CR11","first-page":"111","volume-title":"PPoPP 2008: Proceedings of the 13th ACM SIGPLAN Symposium on Principles and practice of parallel programming","author":"J. Guo","year":"2008","unstructured":"Guo, J., Bikshandi, G., Fraguela, B.B., Garzaran, M.J., Padua, D.: Programming with tiles. In: PPoPP 2008: Proceedings of the 13th ACM SIGPLAN Symposium on Principles and practice of parallel programming, pp. 111\u2013122. ACM, New York (2008)"},{"key":"12_CR12","unstructured":"UPC Consortium: UPC Collective Operations Specifications V1.0 A publication of the UPC Consortium (2003)"},{"key":"12_CR13","unstructured":"Forum, M.P.I.: MPI: A message-passing interface standard (version 1.0). Technical report (May 1994), http:\/\/www.mcs.anl.gov\/mpi\/mpi-report.ps"},{"key":"12_CR14","first-page":"155","volume-title":"PPoPP 2003: Proceedings of the ninth ACM SIGPLAN symposium on Principles and practice of parallel programming","author":"S.J. Deitz","year":"2003","unstructured":"Deitz, S.J., Chamberlain, B.L., Choi, S.E., Snyder, L.: The design and implementation of a parallel array operator for the arbitrary remapping of data. In: PPoPP 2003: Proceedings of the ninth ACM SIGPLAN symposium on Principles and practice of parallel programming, pp. 155\u2013166. ACM, New York (2003)"},{"key":"12_CR15","unstructured":"OpenMP Architecture Review Board: OpenMP Application Program Interface Version 3.0 (May 2008), http:\/\/www.openmp.org\/mp-documents\/spec30.pdf"},{"issue":"1","key":"12_CR16","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1023\/A:1015781018449","volume":"23","author":"S.J. Deitz","year":"2002","unstructured":"Deitz, S.J., Chamberlain, B.L., Snyder, L.: High-level language support for user-defined reductions. J. Supercomput.\u00a023(1), 23\u201337 (2002)","journal-title":"J. Supercomput."},{"key":"12_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1007\/3-540-39999-2_39","volume-title":"High Performance Computing","author":"K. Kusano","year":"2000","unstructured":"Kusano, K., Satoh, S., Sato, M.: Performance evaluation of the omni openmp compiler. In: Valero, M., Joe, K., Kitsuregawa, M., Tanaka, H. (eds.) ISHPC 2000. LNCS, vol.\u00a01940, pp. 403\u2013414. Springer, Heidelberg (2000)"},{"key":"12_CR18","unstructured":"Viswanathan, G., Larus, J.R.: User-defined reductions for efficient communication in data-parallel languages. Technical Report 1293, University of Wisconsin-Madison (January 1996)"},{"key":"12_CR19","first-page":"32","volume-title":"APL 1998: Proceedings of the APL 1998 conference on Array processing language","author":"S.B. Scholz","year":"1998","unstructured":"Scholz, S.B.: On defining application-specific high-level array operations by means of shape-invariant programming facilities. In: APL 1998: Proceedings of the APL 1998 conference on Array processing language, pp. 32\u201338. ACM, New York (1998)"},{"key":"12_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/978-3-540-79561-2_11","volume-title":"OpenMP in a New Era of Parallelism","author":"P. Kambadur","year":"2008","unstructured":"Kambadur, P., Gregor, D., Lumsdaine, A.: Openmp extensions for generic libraries. In: Eigenmann, R., de Supinski, B.R. (eds.) IWOMP 2008. LNCS, vol.\u00a05004, pp. 123\u2013133. Springer, Heidelberg (2008)"},{"key":"12_CR21","first-page":"226","volume-title":"PPoPP 2007: Proceedings of the 12th ACM SIGPLAN symposium on Principles and practice of parallel programming","author":"T.J. Knight","year":"2007","unstructured":"Knight, T.J., Park, J.Y., Ren, M., Houston, M., Erez, M., Fatahalian, K., Aiken, A., Dally, W.J., Hanrahan, P.: Compilation for explicitly managed memory hierarchies. In: PPoPP 2007: Proceedings of the 12th ACM SIGPLAN symposium on Principles and practice of parallel programming, pp. 226\u2013236. ACM, New York (2007)"},{"key":"12_CR22","first-page":"161","volume-title":"PACT 2005: Proceedings of the 14th International Conference on Parallel Architectures and Compilation Techniques, Washington, DC, USA","author":"A.E. Eichenberger","year":"2005","unstructured":"Eichenberger, A.E., O\u2019Brien, K., O\u2019Brien, K., Wu, P., Chen, T., Oden, P.H., Prener, D.A., Shepherd, J.C., So, B., Sura, Z., Wang, A., Zhang, T., Zhao, P., Gschwind, M.: Optimizing compiler for the cell processor. In: PACT 2005: Proceedings of the 14th International Conference on Parallel Architectures and Compilation Techniques, Washington, DC, USA, pp. 161\u2013172. IEEE Computer Society, Los Alamitos (2005)"},{"key":"12_CR23","unstructured":"del Cuvillo, J., Zhu, W., Hu, Z., Gao, G.R.: Fast: A functionally accurate simulation toolset for the cyclops-64 cellular architecture. In: Workshop on Modeling, Benchmarking and Simulation (MoBS 2005) of ISCA 2005, Madison, Wisconsin (June 2005)"}],"container-title":["Lecture Notes in Computer Science","Evolving OpenMP in an Age of Extreme Parallelism"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-02303-3_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T04:00:02Z","timestamp":1558324802000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-02303-3_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642022845","9783642023033"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-02303-3_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}