{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T22:06:06Z","timestamp":1725660366911},"publisher-location":"Berlin, Heidelberg","reference-count":17,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642281440"},{"type":"electronic","value":"9783642281457"}],"license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"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":[[2012]]},"DOI":"10.1007\/978-3-642-28145-7_31","type":"book-chapter","created":{"date-parts":[[2012,2,15]],"date-time":"2012-02-15T19:58:14Z","timestamp":1329335894000},"page":"313-323","source":"Crossref","is-referenced-by-count":2,"title":["Fast Wavelet Transform Utilizing a Multicore-Aware Framework"],"prefix":"10.1007","author":[{"given":"Markus","family":"St\u00fcrmer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harald","family":"K\u00f6stler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ulrich","family":"R\u00fcde","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"31_CR1","unstructured":"Abschlussbericht des Projekts Ru 422\/7-5 (DiME-2). Lehrstuhl f\u00fcr Informatik 10 (Systemsimulation), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (2008)"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Christen, M., Schenk, O., Neufeld, E., Messmer, P., Burkhart, H.: Parallel data-locality aware stencil computations on modern micro-architectures. In: Proceedings of the 2009 IEEE International Symposium on Parallel & Distributed Processing, pp. 1\u201310. IEEE Computer Society (2009)","DOI":"10.1109\/IPDPS.2009.5161031"},{"issue":"1","key":"31_CR3","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1137\/070693199","volume":"51","author":"K. Datta","year":"2009","unstructured":"Datta, K., Kamil, S., Williams, S., Oliker, L., Shalf, J., Yelick, K.: Optimization and performance modeling of stencil computations on modern microprocessors. SIAM Review\u00a051(1), 129\u2013159 (2009)","journal-title":"SIAM Review"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Datta, K., Murphy, M., Volkov, V., Williams, S., Carter, J., Oliker, L., Patterson, D., Shalf, J., Yelick, K.: Stencil computation optimization and auto-tuning on state-of-the-art multicore architectures. In: International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2008, pp. 1\u201312 (2009)","DOI":"10.1109\/SC.2008.5222004"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Franco, J., Bernab\u00e9, G., Fern\u00e1ndez, J., Acacio, M.: A Parallel Implementation of the 2D Wavelet Transform Using CUDA. In: Parallel, Distributed and Network-Based Processing, pp. 111\u2013118 (2009)","DOI":"10.1109\/PDP.2009.40"},{"issue":"1","key":"31_CR6","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.1016\/j.procs.2010.04.122","volume":"1","author":"J. Franco","year":"2010","unstructured":"Franco, J., Bernab\u00e9, G., Fern\u00e1ndez, J., Ujald\u00f3n, M.: Parallel 3D fast wavelet transform on manycore GPUs and multicore CPUs. Procedia Computer Science\u00a01(1), 1095\u20131104 (2010)","journal-title":"Procedia Computer Science"},{"issue":"8","key":"31_CR7","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1007\/s00371-005-0332-0","volume":"21","author":"A. Garcia","year":"2005","unstructured":"Garcia, A., Shen, H.: GPU-based 3D wavelet reconstruction with tileboarding. The Visual Computer\u00a021(8), 755\u2013763 (2005)","journal-title":"The Visual Computer"},{"key":"31_CR8","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/BF01456326","volume":"69","author":"A. Haar","year":"1910","unstructured":"Haar, A.: Zur Theorie der orthogonalen Funktionensysteme. Mathematische Annalen\u00a069, 331\u2013371 (1910)","journal-title":"Mathematische Annalen"},{"key":"31_CR9","unstructured":"International Business Machines Corporation, Sony Computer Entertainment Incorporated, Toshiba Corporation: Cell Broadband Engine Architecture 1.02 (2007)"},{"key":"31_CR10","unstructured":"Kowarschik, M.: Data Locality Optimizations for Iterative Numerical Algorithms and Cellular Automata on Hierarchical Memory Architectures (2004)"},{"issue":"4","key":"31_CR11","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 Trans. Program. Lang. Syst.\u00a018(4), 424\u2013453 (1996)","journal-title":"ACM Trans. Program. Lang. Syst."},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Mohiyuddin, M., Hoemmen, M., Demmel, J., Yelick, K.: Minimizing communication in sparse matrix solvers. In: SC 2009: Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis. pp. 1\u201312. ACM, New York (2009)","DOI":"10.1145\/1654059.1654096"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Ohshima, S., Hirasawa, S., Honda, H.: OMPCUDA: OpenMP Execution Framework for CUDA Based on Omni OpenMP Compiler. In: Beyond Loop Level Parallelism in OpenMP: Accelerators, Tasking and More, pp. 161\u2013173 (2010)","DOI":"10.1007\/978-3-642-13217-9_13"},{"key":"31_CR14","unstructured":"St\u00fcrmer, M., R\u00fcde, U.: A framework that supports in writing performance-optimized stencil-based codes. Tech. Rep. 10-5, Lehrstuhl f\u00fcr Informatik 10 (Systemsimulation), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (2010)"},{"issue":"3","key":"31_CR15","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1109\/TPDS.2007.70716","volume":"19","author":"C. Tenllado","year":"2008","unstructured":"Tenllado, C., Setoain, J., Prieto, M., et al.: Parallel implementation of the 2d discrete wavelet transform on graphics processing units: Filter bank versus lifting. IEEE Transactions on Parallel and Distributed Systems\u00a019(3), 299\u2013310 (2008)","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"31_CR16","unstructured":"Wei\u00df, C.: Data Locality Optimizations for Multigrid Methods on Structured Grids. Ph.D. thesis, Lehrstuhlr f\u00fcr Rechnertechnik und Rechnerorganisation, Institut f\u00fcr Informatik, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany (2001)"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Wellein, G., Hager, G., Zeiser, T., Wittmann, M., Fehske, H.: Efficient temporal blocking for stencil computations by multicore-aware wavefront parallelization. In: Proceedings of the 2009 33rd Annual IEEE International Computer Software and Applications Conference, vol.\u00a001, pp. 579\u2013586. IEEE Computer Society (2009)","DOI":"10.1109\/COMPSAC.2009.82"}],"container-title":["Lecture Notes in Computer Science","Applied Parallel and Scientific Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-28145-7_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,4,27]],"date-time":"2019-04-27T21:14:58Z","timestamp":1556399698000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-28145-7_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642281440","9783642281457"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-28145-7_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}