{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T20:20:07Z","timestamp":1743106807290,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319629315"},{"type":"electronic","value":"9783319629322"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"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":[[2017]]},"DOI":"10.1007\/978-3-319-62932-2_34","type":"book-chapter","created":{"date-parts":[[2017,7,28]],"date-time":"2017-07-28T14:27:55Z","timestamp":1501252075000},"page":"351-364","source":"Crossref","is-referenced-by-count":2,"title":["Islands-of-Cores Approach for Harnessing SMP\/NUMA Architectures in Heterogeneous Stencil Computations"],"prefix":"10.1007","author":[{"given":"Lukasz","family":"Szustak","sequence":"first","affiliation":[]},{"given":"Roman","family":"Wyrzykowski","sequence":"additional","affiliation":[]},{"given":"Ond\u0159ej","family":"Jakl","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,7,29]]},"reference":[{"key":"34_CR1","unstructured":"Cao, X., et al.: Accelerating data shuffling in MapReduce framework with a scale-up NUMA computing architecture. In: Proceedings of the 24th High Performance Computing Symposium, HPC 2016. International Society for Computer Simulation (2016)"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Castro, M., Francesquini, E., Ngu\u00e9l\u00e9, T.M., M\u00e9haut, J.F.: Analysis of computing and energy performance of multicore, NUMA, and manycore platforms for an irregular application. In: Proceedings of the 3rd Workshop on Irregular Applications: Architectures and Algorithms. ACM (2013)","DOI":"10.1145\/2535753.2535757"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Ciznicki, M., Kulczewski, M., Kopta, P., Kurowski, K.: Methods to load balance a GCR pressure solver using a stencil framework on multi-and many-core architectures. Sci. Program. (2015)","DOI":"10.1155\/2015\/648752"},{"key":"34_CR4","volume-title":"Parallel Computer Architecture: A Hardware\/Software Approach","author":"D Culler","year":"1999","unstructured":"Culler, D., Pal Singh, J., Gupta, A.: Parallel Computer Architecture: A Hardware\/Software Approach. Morgan Kaufmann Publishers Inc., San Francisco (1999)"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Czarnul, P.: Benchmarking performance of a hybrid Xeon\/Xeon Phi system for parallel computation of similarity measures between large vectors. Int. J. Parallel Program. 1\u201317 (2017)","DOI":"10.1007\/s10766-016-0455-0"},{"issue":"1","key":"34_CR6","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1002\/cpe.1340","volume":"21","author":"J Guo","year":"2009","unstructured":"Guo, J., Bikshandi, G., Fraguela, B.B., Padua, D.: Writing productive stencil codes with overlapped tiling. Concurr. Comput. Pract. Exp. 21(1), 25\u201339 (2009)","journal-title":"Concurr. Comput. Pract. Exp."},{"issue":"22","key":"34_CR7","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1002\/cpe.3180","volume":"28","author":"G Hager","year":"2016","unstructured":"Hager, G., Treibig, J., Habich, J., Wellein, G.: Exploring performance and power properties of modern multi-core chips via simple machine models. Concurr. Comput. Pract. Exp. 28(22), 189\u2013210 (2016)","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"34_CR8","unstructured":"National Supercomputing Center IT4Innovations (2017). http:\/\/www.it4i.cz"},{"issue":"2","key":"34_CR9","doi-asserted-by":"crossref","first-page":"80","DOI":"10.3847\/0004-637X\/830\/2\/80","volume":"830","author":"S Kumar","year":"2016","unstructured":"Kumar, S., Bhattacharyya, R., Joshi, B., Smolarkiewicz, P.: On the role of repetitive magnetic reconnections in evolution of magnetic flux ropes in solar corona. Astrophys. J. 830(2), 80 (2016)","journal-title":"Astrophys. J."},{"issue":"3","key":"34_CR10","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1109\/TPDS.2016.2599527","volume":"28","author":"A Lastovetsky","year":"2017","unstructured":"Lastovetsky, A., Szustak, L., Wyrzykowski, R.: Model-based optimization of EULAG kernel on Intel Xeon Phi through load imbalancing. IEEE Trans. Parallel Distrib. Syst. 28(3), 787\u2013797 (2017)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"34_CR11","unstructured":"SGI Products: Servers SGI UV (2015). https:\/\/www.sgi.com\/products\/servers\/uv\/"},{"key":"34_CR12","unstructured":"SGI UV 2000 System User Guide. Document Number 007\u20135832-002 (2013)"},{"issue":"10","key":"34_CR13","doi-asserted-by":"crossref","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. Methods Fluids 50(10), 1123\u20131144 (2006)","journal-title":"Int. J. Numer. Methods Fluids"},{"issue":"2","key":"34_CR14","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1006\/jcph.1998.5901","volume":"140","author":"P Smolarkiewicz","year":"1998","unstructured":"Smolarkiewicz, P., Margolin, L.: MPDATA: a finite-difference solver for geophysical flows. J. Comput. Phys. 140(2), 459\u2013480 (1998)","journal-title":"J. Comput. Phys."},{"key":"34_CR15","doi-asserted-by":"crossref","first-page":"608","DOI":"10.1016\/j.jcp.2012.11.008","volume":"236","author":"PK Smolarkiewicz","year":"2013","unstructured":"Smolarkiewicz, P.K., Charbonneau, P.: EULAG, a computational model for multiscale flows: an MHD extension. J. Comput. Phys. 236, 608\u2013623 (2013)","journal-title":"J. Comput. Phys."},{"issue":"C","key":"34_CR16","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1016\/j.jcp.2016.06.048","volume":"322","author":"PK Smolarkiewicz","year":"2016","unstructured":"Smolarkiewicz, P.K., Szmelter, J., Xiao, F.: Simulation of all-scale atmospheric dynamics on unstructured meshes. J. Comput. Phys. 322(C), 267\u2013287 (2016)","journal-title":"J. Comput. Phys."},{"issue":"8","key":"34_CR17","doi-asserted-by":"crossref","first-page":"1538","DOI":"10.1016\/j.asr.2016.05.043","volume":"58","author":"A Strugarek","year":"2016","unstructured":"Strugarek, A., Beaudoin, P., Brun, A., Charbonneau, P., Mathis, S., Smolarkiewicz, P.: Modeling turbulent stellar convection zones: sub-grid scales effects. Adv. Space Res. 58(8), 1538\u20131553 (2016)","journal-title":"Adv. Space Res."},{"key":"34_CR18","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. LNCS, vol. 8384, pp. 582\u2013592. Springer, Heidelberg (2014). doi: 10.1007\/978-3-642-55224-3_54"},{"key":"34_CR19","doi-asserted-by":"publisher","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","DOI":"10.1155\/2015\/642705"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Szustak, L., Rojek, K., Wyrzykowski, R., Gepner, P.: Toward efficient distribution of MPDATA stencil computation on Intel MIC architecture. In: Proceedings of the 1st International Workshop on High-Performance Stencil Computations, HiStencils 2014, pp. 51\u201356 (2014)","DOI":"10.1155\/2015\/642705"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Treibig, J., Hager, G., Wellein, G.: LIKWID: a lightweight performance-oriented tool suite for x86 multicore environments. In: Proceedings of the First International Workshop on Parallel Software Tools and Tool Infrastructures, PSTI 2010, San Diego, CA (2010)","DOI":"10.1109\/ICPPW.2010.38"},{"key":"34_CR22","unstructured":"Unat, D., et al.: Programming abstractions for data locality. (2014). http:\/\/web.eecs.umich.edu\/akamil\/papers\/padal14report.pdf"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Utrera, G., Gil, M., Martorell, X.: In search of the best MPI-OpenMP distribution for optimum Intel-MIC cluster performance. In: 2015 International Conference on High Performance Computing and Simulation (HPCS), pp. 429\u2013435. IEEE (2015)","DOI":"10.1109\/HPCSim.2015.7237072"},{"issue":"8","key":"34_CR24","doi-asserted-by":"crossref","first-page":"2382","DOI":"10.1109\/TC.2014.2366754","volume":"64","author":"W Xue","year":"2015","unstructured":"Xue, W., et al.: Ultra-scalable CPU-MIC acceleration of mesoscale atmospheric modeling on Tianhe-2. IEEE Trans. Comput. 64(8), 2382\u20132393 (2015)","journal-title":"IEEE Trans. Comput."},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Yasui, Y., Fujisawa, K., Goh, E.L., Baron, J., Sugiura, A., Uchiyama, T.: NUMA-aware scalable graph traversal on SGI UV systems. In: Proceedings of the ACM Workshop on High Performance Graph Processing, pp. 19\u201326. ACM (2016)","DOI":"10.1145\/2915516.2915522"},{"key":"34_CR26","doi-asserted-by":"crossref","unstructured":"Zhou, X., Giacalone, J.P., Garzar\u00e1n, M.J., Kuhn, R.H., Ni, Y., Padua, D.: Hierarchical overlapped tiling. In: Proceedings of the Tenth International Symposium on Code Generation and Optimization, pp. 207\u2013218. ACM (2012)","DOI":"10.1145\/2259016.2259044"}],"container-title":["Lecture Notes in Computer Science","Parallel Computing Technologies"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-62932-2_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T19:05:17Z","timestamp":1692903917000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-62932-2_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319629315","9783319629322"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-62932-2_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}