{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T03:26:29Z","timestamp":1725852389571},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319321516"},{"type":"electronic","value":"9783319321523"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[[2016]]},"DOI":"10.1007\/978-3-319-32152-3_55","type":"book-chapter","created":{"date-parts":[[2016,3,31]],"date-time":"2016-03-31T22:10:11Z","timestamp":1459462211000},"page":"594-606","source":"Crossref","is-referenced-by-count":4,"title":["Scaling the GCR Solver Using a High-Level Stencil Framework on Multi- and Many-Core Architectures"],"prefix":"10.1007","author":[{"given":"Milosz","family":"Ciznicki","sequence":"first","affiliation":[]},{"given":"Michal","family":"Kulczewski","sequence":"additional","affiliation":[]},{"given":"Piotr","family":"Kopta","sequence":"additional","affiliation":[]},{"given":"Krzysztof","family":"Kurowski","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,4,2]]},"reference":[{"key":"55_CR1","series-title":"Computer and Information Science Series","doi-asserted-by":"publisher","DOI":"10.1201\/b10376","volume-title":"Scientific Computing with Multicore and Accelerators","author":"J Kurzak","year":"2010","unstructured":"Kurzak, J., Bader, D., Dongarra, J.: Scientific Computing with Multicore and Accelerators. Computer and Information Science Series. Chapmann & Hall\/CRC, Boca Raton (2010)"},{"key":"55_CR2","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1002\/fld.2462","volume":"64","author":"S Georgescu","year":"2010","unstructured":"Georgescu, S., Okuda, H.: Conjugate gradients on multiple GPUs. Int J. Numer. Meth. Fluids 64, 1254\u20131273 (2010)","journal-title":"Int J. Numer. Meth. Fluids"},{"key":"55_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Cohen, J.M., Owens, J.D.: Fast tridiagonal solvers on GPU. In: Newsletter ACM SIGPLAN Notices - PPoPP, vol. 45, p. 5 (2010)","DOI":"10.1145\/1837853.1693472"},{"key":"55_CR4","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.1016\/j.compfluid.2007.12.001","volume":"37","author":"JM Prusa","year":"2008","unstructured":"Prusa, J.M., Smolarkiewicz, P.K., Wyszogrodzki, A.: Eulag a computational model for multiscale flows. Comput. Fluids 37, 1193\u20131207 (2008)","journal-title":"Comput. Fluids"},{"key":"55_CR5","unstructured":"Smolarkiewicz, P.K., Margolin, L.G.: Variational methods for elliptic problems in fluid models. In: Proceedings of ECMWF Workshop on Developments in Numerical Methods for Very High Resolution Global Models, vol. 7, pp. 137\u2013159 (2000)"},{"key":"55_CR6","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: IEEE International Symposium on Parallel and Distributed Processing (IPDPS 2010), pp. 1\u201312. IEEE (2010)","DOI":"10.1109\/IPDPS.2010.5470421"},{"key":"55_CR7","doi-asserted-by":"crossref","unstructured":"Christen, M., Schenk, O., Burkhart, H.: Patus: a code generation and autotuning framework for parallel iterative stencil computations on modern microarchitectures. In: IEEE International Parallel and Distributed Processing Symposium (IPDPS 2011), pp. 676\u2013687. IEEE (2011)","DOI":"10.1109\/IPDPS.2011.70"},{"issue":"4","key":"55_CR8","first-page":"59","volume":"9","author":"T Lutz","year":"2013","unstructured":"Lutz, T., Fensch, C., Cole, M.: PARTANS: an autotuning framework for stencil computation on multi-GPU systems. ACM Trans. Archit. Code Optim. (TACO) 9(4), 59 (2013)","journal-title":"ACM Trans. Archit. Code Optim. (TACO)"},{"issue":"1\u20132","key":"55_CR9","first-page":"1","volume":"21","author":"M Blazewicz","year":"2013","unstructured":"Blazewicz, M., Hinder, I., Koppelman, D.M., Brandt, S.R., Ciznicki, M., Kierzynka, M., L\u00f6ffler, F., Schnetter, E., Tao, J.: From physics model to results: an optimizing framework for cross-architecture code generation. Sci. Program. 21(1\u20132), 1\u201316 (2013)","journal-title":"Sci. Program."},{"key":"55_CR10","doi-asserted-by":"crossref","unstructured":"Szustak, L., Rojek, K., Olas, T., Kuczynski, L., Halbiniak, K., Gepner, P.: Adaptation of MPDATA heterogeneous stencil computation to Intel Xeon Phi coprocessor. Sci. Program. (2015)","DOI":"10.1155\/2015\/642705"},{"key":"55_CR11","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1016\/j.parco.2014.04.009","volume":"40","author":"R Wyrzykowski","year":"2014","unstructured":"Wyrzykowski, R., Szustak, L., Rojek, K.: Parallelization of 2D MPDATA EULAG algorithm on hybrid architectures with GPU accelerators. Parallel Comput. 40, 425\u2013447 (2014)","journal-title":"Parallel Comput."},{"key":"55_CR12","doi-asserted-by":"crossref","unstructured":"Maruyama, N., Nomura, T., Sato, K., Matsuoka, S.: Physis: an implicitly parallel programming model for stencil computations on large-scale GPU-accelerated supercomputers. In: International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2011), pp. 1\u201312. IEEE (2011)","DOI":"10.1145\/2063384.2063398"},{"key":"55_CR13","doi-asserted-by":"crossref","unstructured":"Pereira, A.D., Ramos, L., G\u00f3es, L.F.: PSkel: a stencil programming framework for CPU-GPU systems. In: Practice and Experience, Concurrency and Computation (2015)","DOI":"10.1002\/cpe.3479"},{"issue":"4","key":"55_CR14","doi-asserted-by":"crossref","first-page":"937","DOI":"10.1002\/cpe.3417","volume":"27","author":"Krzysztof Andrzej Rojek","year":"2014","unstructured":"Rojek, K.A., Ciznicki, M., Rosa, B., Kopta, P., Kulczewski, M., Kurowski, K., Piotrowski, Z.P., Szustak, L., Wojcik, D.K., Wyrzykowski, R.: Adaptation of fluid model EULAG to graphics processing unit architecture. In: Practice and Experience, Concurrency and Computation (2014)","journal-title":"Concurrency and Computation: Practice and Experience"},{"key":"55_CR15","doi-asserted-by":"crossref","unstructured":"Xue, W., Yang, C., Fu, H., Wang, X., Xu, Y., Gan, L., Lu, Y., Zhu, X.: Enabling and scaling a global shallow-water atmospheric model on tianhe-2. In: IEEE 28th International Parallel and Distributed Processing Symposium, pp. 745\u2013754. IEEE (2014)","DOI":"10.1109\/IPDPS.2014.82"},{"key":"55_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/978-3-642-55224-3_16","volume-title":"Parallel Processing and Applied Mathematics","author":"M Ciznicki","year":"2014","unstructured":"Ciznicki, M., Kopta, P., Kulczewski, M., Kurowski, K., Gepner, P.: Elliptic solver performance evaluation on modern hardware architectures. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wa\u015bniewski, J. (eds.) PPAM 2013, Part I. LNCS, vol. 8384, pp. 155\u2013165. Springer, Heidelberg (2014)"}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-32152-3_55","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T19:00:27Z","timestamp":1559415627000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-32152-3_55"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319321516","9783319321523"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-32152-3_55","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}