{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T02:02:39Z","timestamp":1782439359250,"version":"3.54.5"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319219080","type":"print"},{"value":"9783319219097","type":"electronic"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-21909-7_43","type":"book-chapter","created":{"date-parts":[[2015,7,24]],"date-time":"2015-07-24T06:16:04Z","timestamp":1437718564000},"page":"445-457","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Parallelization of 3D MPDATA Algorithm Using Many Graphics Processors"],"prefix":"10.1007","author":[{"given":"Krzysztof","family":"Rojek","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roman","family":"Wyrzykowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2015,7,25]]},"reference":[{"key":"43_CR1","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)"},{"issue":"1","key":"43_CR2","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 Rev. 51(1), 129\u2013159 (2009)","journal-title":"SIAM Rev."},{"key":"43_CR3","volume-title":"Introduction to High Performance Computing for Science and Engineers","author":"G Hager","year":"2011","unstructured":"Hager, G., Wellein, G.: Introduction to High Performance Computing for Science and Engineers. CRC Press, Boca Raton (2011)"},{"issue":"3","key":"43_CR4","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1109\/MCSE.2011.117","volume":"14","author":"A Khajeh-Saeed","year":"2012","unstructured":"Khajeh-Saeed, A., et al.: Computational fluid dynamics simulations using many graphics processors. Comput. Sci. Eng. 14(3), 10\u201319 (2012)","journal-title":"Comput. Sci. Eng."},{"key":"43_CR5","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1016\/j.parco.2013.08.002","volume":"39","author":"M Krotkiewicz","year":"2013","unstructured":"Krotkiewicz, M., Dabrowski, M.: Efficient 3D stencil computations using CUDA. Parallel Comput. 39, 533\u2013548 (2013)","journal-title":"Parallel Comput."},{"key":"43_CR6","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1007\/978-3-642-19536-5_57","volume":"3","author":"K Kurowski","year":"2011","unstructured":"Kurowski, K., Kulczewski, M., Dobski, M.: Parallel and GPU based strategies for selected CFD and climate modeling models. Environ. Sci. Eng. 3, 735\u2013747 (2011)","journal-title":"Environ. Sci. Eng."},{"key":"43_CR7","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Satish, N., Chhugani, J., Changkyu, K., Dubey, P.: 3.5-D blocking optimization for stencil computations on modern CPUs and GPUs. In: Proceedings of 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201313 (2010)","DOI":"10.1109\/SC.2010.2"},{"key":"43_CR8","doi-asserted-by":"publisher","first-page":"1294","DOI":"10.2478\/s11600-011-0049-6","volume":"59","author":"Z Piotrowski","year":"2011","unstructured":"Piotrowski, Z., Wyszogrodzki, A., Smolarkiewicz, P.: Towards petascale simulation of atmospheric circulations with soundproof equations. Acta Geophys. 59, 1294\u20131311 (2011)","journal-title":"Acta Geophys."},{"key":"43_CR9","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.1016\/j.compfluid.2007.12.001","volume":"37","author":"J Prusa","year":"2008","unstructured":"Prusa, J., Smolarkiewicz, P., Wyszogrodzki, A.: EULAG, a computational model for multiscale flows. Comput. Fluids 37, 1193\u20131207 (2008)","journal-title":"Comput. Fluids"},{"key":"43_CR10","doi-asserted-by":"crossref","unstructured":"Rivera, G., Tseng, Ch.-W.: Tiling optimizations for 3D scientific computations. In: SC 2000 Proceedings of ACM\/IEEE Conference on Supercomputing (2000)","DOI":"10.1109\/SC.2000.10015"},{"key":"43_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/978-3-642-31500-8_40","volume-title":"Parallel Processing and Applied Mathematics","author":"K Rojek","year":"2012","unstructured":"Rojek, K., Szustak, L.: Parallelization of EULAG model on multicore architectures with GPU accelerators. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wa\u015bniewski, J. (eds.) PPAM 2011, Part II. LNCS, vol. 7204, pp. 391\u2013400. Springer, Heidelberg (2012)"},{"key":"43_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/978-3-642-55224-3_15","volume-title":"Parallel Processing and Applied Mathematics","author":"K Rojek","year":"2014","unstructured":"Rojek, K., Szustak, L., Wyrzykowski, R.: Performance analysis for stencil-based 3D MPDATA algorithm on GPU architecture. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wa\u015bniewski, J. (eds.) PPAM 2013, Part I. LNCS, vol. 8384, pp. 145\u2013154. Springer, Heidelberg (2014)"},{"issue":"4","key":"43_CR13","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1002\/cpe.3417","volume":"27","author":"K Rojek","year":"2015","unstructured":"Rojek, K., Ciznicki, M., Rosa, B., Kopta, P., Kulczewski, M., Kurowski, K., Piotrowski, Z., Szustak, L., Wojcik, D., Wyrzykowski, R.: Adaptation of fluid model EULAG to graphics processing unit architecture. Concurrency Comput. Pract. Experience 27(4), 937\u2013957 (2015)","journal-title":"Concurrency Comput. Pract. Experience"},{"key":"43_CR14","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1002\/fld.1071","volume":"50","author":"P Smolarkiewicz","year":"2006","unstructured":"Smolarkiewicz, P.: Multidimensional positive definite advection transport algorithm: an overview. Int. J. Numer. Meth. Fluids 50, 1123\u20131144 (2006)","journal-title":"Int. J. Numer. Meth. Fluids"},{"key":"43_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1007\/978-3-642-55224-3_54","volume-title":"Parallel Processing and Applied Mathematics","author":"L Szustak","year":"2014","unstructured":"Szustak, L., Rojek, K., Gepner, P.: Using intel xeon phi coprocessor to accelerate computations in MPDATA algorithm. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wa\u015bniewski, J. (eds.) PPAM 2013, Part I. LNCS, vol. 8384, pp. 582\u2013592. Springer, Heidelberg (2014)"},{"key":"43_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1007\/978-3-642-31500-8_43","volume-title":"Parallel Processing and Applied Mathematics","author":"DK W\u00f3jcik","year":"2012","unstructured":"W\u00f3jcik, D.K., Kurowski, M.J., Rosa, B., Ziemia\u0144ski, M.Z.: A study on parallel performance of the EULAG F90\/95 code. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wa\u015bniewski, J. (eds.) PPAM 2011, Part II. LNCS, vol. 7204, pp. 419\u2013428. Springer, Heidelberg (2012)"},{"issue":"8","key":"43_CR17","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(8), 425\u2013447 (2014)","journal-title":"Parallel Comput."},{"key":"43_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1007\/978-3-662-43880-0_52","volume-title":"Large-Scale Scientific Computing","author":"R Wyrzykowski","year":"2014","unstructured":"Wyrzykowski, R., Szustak, L., Rojek, K., Tomas, A.: Towards efficient decomposition and parallelization of MPDATA on hybrid CPU-GPU cluster. In: Lirkov, I., Margenov, S., Wa\u015bniewski, J. (eds.) LSSC 2013. LNCS, vol. 8353, pp. 457\u2013464. Springer, Heidelberg (2014)"},{"key":"43_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1007\/978-3-642-31500-8_26","volume-title":"Parallel Processing and Applied Mathematics","author":"AA Wyszogrodzki","year":"2012","unstructured":"Wyszogrodzki, A.A., Piotrowski, Z.P., Grabowski, W.W.: Parallel implementation and scalability of cloud resolving EULAG model. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wa\u015bniewski, J. (eds.) PPAM 2011, Part II. LNCS, vol. 7204, pp. 252\u2013261. Springer, Heidelberg (2012)"},{"key":"43_CR20","doi-asserted-by":"publisher","unstructured":"Xue, W., Yang, C., Fu, H., Xu, Y., Liao, J., Gan, L., Lu, Y., Ranjan, R., Wang, L.: Ultra-scalable CPU-MIC acceleration of mesoscale atmospheric modeling on Tianhe-2. IEEE Trans. Comput. (2014). doi:10.1109\/TC.2014.2366754 (to appear)","DOI":"10.1109\/TC.2014.2366754"},{"key":"43_CR21","unstructured":"GPUDirect RDMA. http:\/\/docs.nvidia.com\/cuda\/gpudirect-rdma\/index.html"},{"key":"43_CR22","unstructured":"NVIDIA GeForce GTX TITAN Specification. http:\/\/www.geforce.com\/hardware\/ desktop-gpus\/geforce-gtx-titan\/specifications"},{"key":"43_CR23","unstructured":"PizDaint & PizDora. http:\/\/www.cscs.ch\/computers\/piz_daint\/index.html"},{"key":"43_CR24","unstructured":"Top 500 Supercomputing Sites. http:\/\/www.top500.org"}],"container-title":["Lecture Notes in Computer Science","Parallel Computing Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-21909-7_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,24]],"date-time":"2023-01-24T13:35:53Z","timestamp":1674567353000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-21909-7_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319219080","9783319219097"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-21909-7_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"25 July 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}