{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T16:09:46Z","timestamp":1725466186609},"publisher-location":"Berlin, Heidelberg","reference-count":17,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642314636"},{"type":"electronic","value":"9783642314643"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-31464-3_68","type":"book-chapter","created":{"date-parts":[[2012,7,2]],"date-time":"2012-07-02T11:20:38Z","timestamp":1341228038000},"page":"671-680","source":"Crossref","is-referenced-by-count":4,"title":["Autotuning of Adaptive Mesh Refinement PDE Solvers on Shared Memory Architectures"],"prefix":"10.1007","author":[{"given":"Svetlana","family":"Nogina","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kristof","family":"Unterweger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tobias","family":"Weinzierl","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"68_CR1","doi-asserted-by":"crossref","unstructured":"Bilmes, J., Asanovic, K., Chin, C.-W., Demmel, J.: Optimizing matrix multiply using PHiPAC: a portable, high-performance, ANSI C coding methodology. In: Proceedings of the 11th International Conference on Supercomputing, pp. 340\u2013347 (1997)","DOI":"10.1145\/263580.263662"},{"key":"68_CR2","doi-asserted-by":"crossref","unstructured":"Cari\u00f1o, R.L., Banicescu, I.: Dynamic Scheduling Parallel Loops With Variable Iterate Execution Times. In: 16th International Parallel and Distributed Processing Symposium (IPDPS 2002). IEEE (2002); electonical proceedings","DOI":"10.1109\/IPDPS.2002.1016663"},{"key":"68_CR3","unstructured":"Chapman, B., Jost, G., van der Pas, R.: Using OpenMP: Portable Shared Memory Parallel Programming. MIT Press (2007)"},{"issue":"1","key":"68_CR4","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1016\/j.procs.2010.04.055","volume":"1","author":"J. Cuenca","year":"2010","unstructured":"Cuenca, J., Garc\u00eda, L.-P., Gim\u00e9nez, D.: A proposal for autotuning linear algebra routines on multicore platforms. Procedia CS\u00a01(1), 515\u2013523 (2010)","journal-title":"Procedia CS"},{"key":"68_CR5","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: Proceedings of the 2008 ACM\/IEEE Conference on Supercomputing, pp. 4:1\u20134:12. IEEE Press (2008)","DOI":"10.1109\/SC.2008.5222004"},{"key":"68_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1007\/978-3-642-14390-8_59","volume-title":"Parallel Processing and Applied Mathematics","author":"W. Eckhardt","year":"2010","unstructured":"Eckhardt, W., Weinzierl, T.: A Blocking Strategy on Multicore Architectures for Dynamically Adaptive PDE Solvers. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wasniewski, J. (eds.) PPAM 2009. LNCS, vol.\u00a06067, pp. 567\u2013575. Springer, Heidelberg (2010)"},{"key":"68_CR7","unstructured":"Gmeiner, B., Gradl, T., K\u00f6stler, H., R\u00fcde, U.: Highly parallel geometric multigrid for hierarchical hybrid grids on Blue-Gene\/P. Numer.\u00a0Linear Algebr. (submitted)"},{"key":"68_CR8","doi-asserted-by":"crossref","unstructured":"Hummel, S.F., Schmidt, J., Uma, R.N., Wein, J.: Load-Sharing in Heterogeneous Systems via Weighted Factoring. In: Proceedings of the 8th Annual ACM Symposium on Parallel Algorithms and Architectures, pp. 318\u2013328. ACM (1997)","DOI":"10.1145\/237502.237576"},{"key":"68_CR9","doi-asserted-by":"crossref","unstructured":"Kamil, S., Chan, C., Oliker, L., Shalf, J., Williams, S.: An auto-tuning framework for parallel multicore stencil computations. In: 24th IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2010, pp. 1\u201312. IEEE (2010)","DOI":"10.1109\/IPDPS.2010.5470421"},{"issue":"1-2","key":"68_CR10","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1016\/j.future.2005.04.001","volume":"22","author":"S.G. Parker","year":"2006","unstructured":"Parker, S.G.: A component-based architecture for parallel multi-physics pde simulation. FGCS\u00a022(1-2), 204\u2013216 (2006)","journal-title":"FGCS"},{"key":"68_CR11","unstructured":"Reinders, J.: Intel Threading Building Blocks: Outfitting C++ for Multi-core Processor Parallelism. O\u2019Reilly Media (2007)"},{"issue":"30","key":"68_CR12","first-page":"202","volume":"3","author":"H. Sutter","year":"2005","unstructured":"Sutter, H.: The Free Lunch Is Over: A Fundamental Turn Toward Concurrency in Software. Dr. Dobb\u2019s Journal\u00a03(30), 202\u2013210 (2005)","journal-title":"Dr. Dobb\u2019s Journal"},{"key":"68_CR13","unstructured":"Tang, P., Yew, P.: Processor self-scheduling for multiple-nested parallel loops. In: Proceedings of the 1986 International Conference on Parallel Processing, pp. 528\u2013535. IEEE (1986)"},{"key":"68_CR14","unstructured":"Vuduc, R.: Automatic assembly of highly tuned code fragments (1998), \n                    \n                      www.cs.berkeley.edu\/~richie\/stat242\/project"},{"key":"68_CR15","unstructured":"Weinzierl, T.: A Framework for Parallel PDE Solvers on Multiscale Adaptive Cartesian Grids. Verlag Dr. Hut (2009)"},{"key":"68_CR16","unstructured":"Weinzierl, T., K\u00f6ppl, T.: A geometric space-time multigrid algorithm for the heat equation. In: NMTMA (accepted)"},{"key":"68_CR17","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.: Automated empirical optimizations of software and the ATLAS project. Parallel Comput.\u00a027, 3\u201335 (2001)","journal-title":"Parallel Comput."}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-31464-3_68.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T08:02:29Z","timestamp":1620115349000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-31464-3_68"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642314636","9783642314643"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-31464-3_68","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}