{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:38:02Z","timestamp":1740123482930,"version":"3.37.3"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2018,6,23]],"date-time":"2018-06-23T00:00:00Z","timestamp":1529712000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004281","name":"Narodowe Centrum Nauki","doi-asserted-by":"publisher","award":["UMO-2017\/26\/D\/ST6\/00687"],"award-info":[{"award-number":["UMO-2017\/26\/D\/ST6\/00687"]}],"id":[{"id":"10.13039\/501100004281","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1007\/s11227-018-2460-0","type":"journal-article","created":{"date-parts":[[2018,6,23]],"date-time":"2018-06-23T08:11:02Z","timestamp":1529741462000},"page":"7765-7777","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Unleashing the performance of ccNUMA multiprocessor architectures in heterogeneous stencil computations"],"prefix":"10.1007","volume":"75","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7429-6981","authenticated-orcid":false,"given":"Lukasz","family":"Szustak","sequence":"first","affiliation":[]},{"given":"Kamil","family":"Halbiniak","sequence":"additional","affiliation":[]},{"given":"Roman","family":"Wyrzykowski","sequence":"additional","affiliation":[]},{"given":"Ond\u0159ej","family":"Jakl","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,6,23]]},"reference":[{"issue":"4","key":"2460_CR1","first-page":"122","volume":"48","author":"X Cao","year":"2016","unstructured":"Cao X, Panchputre K, Du D (2016) Accelerating data shuffling in MapReduce framework with a scale-up NUMA computing architecture. Simul Ser 48(4):122\u2013129","journal-title":"Simul Ser"},{"key":"2460_CR2","doi-asserted-by":"crossref","unstructured":"Castro M, Francesquini E, Ngu\u00e9l\u00e9 T.M, M\u00e9haut J.F (2013) Analysis of computing and energy performance of multicore, NUMA, and manycore platforms for an irregular application. In: Proceedings of 3rd Workshop on Irregular Applications: Architectures and Algorithms. ACM","DOI":"10.1145\/2535753.2535757"},{"key":"2460_CR3","first-page":"24","volume":"2015","author":"M Ciznicki","year":"2015","unstructured":"Ciznicki M, Kulczewski M, Kopta P, Kurowski K (2015) Methods to load balance a GCR pressure solver using a stencil framework on multi-and many-core architectures. Sci Program 2015:24","journal-title":"Sci Program"},{"key":"2460_CR4","volume-title":"Parallel computer architecture: a hardware\/software approach","author":"D Culler","year":"1999","unstructured":"Culler D, Pal Singh J, Gupta A (1999) Parallel computer architecture: a hardware\/software approach. Morgan Kaufmann Publishers Inc., Burlington"},{"key":"2460_CR5","volume-title":"Capabilities of Intel AVX-512 in Intel Xeon scalable processors (Skylake)","author":"A Eltablawy","year":"2015","unstructured":"Eltablawy A, Vladimirov A (2015) Capabilities of Intel AVX-512 in Intel Xeon scalable processors (Skylake). Colfax International, Sunnyvale"},{"key":"2460_CR6","unstructured":"Ferretti M (2017) Advanced computer architecture. Shared memory mutiprocessor. \nhttp:\/\/www-5.unipv.it\/mferretti\/cdol\/aca\/Charts\/07-multiprocessors-MF.pdf\n\n. Accessed Mar 2018"},{"issue":"1","key":"2460_CR7","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1002\/cpe.1340","volume":"21","author":"J Guo","year":"2009","unstructured":"Guo J, Bikshandi G, Fraguela BB, Padua D (2009) Writing productive stencil codes with overlapped tiling. Concurr Comput Pract Exp 21(1):25\u201339","journal-title":"Concurr Comput Pract Exp"},{"key":"2460_CR8","doi-asserted-by":"crossref","unstructured":"Hagedorn B, Stoltzfus L, Steuwer M, Gorlatch S, Dubach C (2018) High performance stencil code generation with LIFT. In: Proceedings of 2018 IEEE\/ACM International Symposium Code Generation and Optimization (CGO\u201918)","DOI":"10.1145\/3179541.3168824"},{"key":"2460_CR9","unstructured":"HPE Servers and Server Systems (2018) \nhttps:\/\/www.hpe.com\/us\/en\/servers.html\n\n. Accessed Mar 2018"},{"key":"2460_CR10","unstructured":"Intel 64 and IA-32 Architectures Optimization Reference Manual (2017) \nhttps:\/\/software.intel.com\/sites\/default\/files\/managed\/9e\/bc\/64-ia-32-architectures-optimization-manual.pdf\n\n. Accessed Mar 2018"},{"key":"2460_CR11","unstructured":"Intel Xeon Platinum 8176 Scalable Processor Review (2018) \nhttps:\/\/www.tomshardware.com\/reviews\/intel-xeon-platinum-8176-scalable-cpu,5120.html\n\n. Accessed Mar 2018"},{"issue":"3","key":"2460_CR12","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1109\/TPDS.2016.2599527","volume":"28","author":"A Lastovetsky","year":"2017","unstructured":"Lastovetsky A, Szustak L, Wyrzykowski R (2017) Model-based optimization of EULAG kernel on Intel Xeon Phi through load imbalancing. IEEE Trans Parallel Distrib Syst 28(3):787\u2013797","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"2460_CR13","unstructured":"SGI UV 3000, UV 30 (2016) \nhttps:\/\/www.risc.jku.at\/projects\/mach2\/4555.pdf\n\n. Accessed Mar 2018"},{"key":"2460_CR14","unstructured":"SGI UV 3000 Sets New Throughput Records (2016) \nhttps:\/\/www.hpcwire.com\/2016\/03\/25\/sgi-posts-new-spec-cpu2006-results\/\n\n. Accessed Mar 2018"},{"issue":"10","key":"2460_CR15","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1002\/fld.1071","volume":"50","author":"P Smolarkiewicz","year":"2006","unstructured":"Smolarkiewicz P (2006) Multidimensional Positive Definite Advection Transport Algorithm: an overview. Int J Numer Meth Fluids 50(10):1123\u20131144","journal-title":"Int J Numer Meth Fluids"},{"issue":"8","key":"2460_CR16","doi-asserted-by":"publisher","first-page":"1538","DOI":"10.1016\/j.asr.2016.05.043","volume":"58","author":"A Strugarek","year":"2016","unstructured":"Strugarek A, Beaudoin P, Brun AS, Charbonneau P, Mathis S, Smolarkiewicz PK (2016) Modeling turbulent stellar convection zones: sub-grid scales effects. Adv Space Res 58(8):1538\u20131553","journal-title":"Adv Space Res"},{"issue":"4","key":"2460_CR17","doi-asserted-by":"publisher","first-page":"1534","DOI":"10.1007\/s11227-018-2239-3","volume":"74","author":"L Szustak","year":"2018","unstructured":"Szustak L (2018) Strategy for data-flow synchronizations in stencil parallel computations on multi-\/manycore systems. J Supercomput 74(4):1534\u20131546","journal-title":"J Supercomput"},{"key":"2460_CR18","first-page":"351","volume-title":"Lecture Notes in Computer Science","author":"Lukasz Szustak","year":"2017","unstructured":"Szustak L, Jakl O, Wyrzykowski R (2017) Islands-of-cores approach for harnessing SMP\/NUMA architectures in heterogeneous stencil computations. In: PaCT 2017, vol 10421. Lecture Notes in Computer Science, pp 351\u2013364"},{"key":"2460_CR19","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1007\/978-3-642-55224-3_54","volume-title":"Parallel Processing and Applied Mathematics","author":"Lukasz Szustak","year":"2014","unstructured":"Szustak L, Rojek K, Gepner P (2014) Using Intel Xeon Phi coprocessor to accelerate computations in MPDATA algorithm. In: PPAM 2013, vol 8384. Lecture Notes in Computer Science, pp 582\u2013592"},{"key":"2460_CR20","first-page":"10","volume":"2015","author":"L Szustak","year":"2015","unstructured":"Szustak L, Rojek K, Olas T, Kuczynski L, Halbiniak K, Gepner P (2015) Adaptation of MPDATA heterogeneous stencil computation to Intel Xeon Phi coprocessor. Sci Program 2015:10","journal-title":"Sci Program"},{"key":"2460_CR21","unstructured":"Szustak L, Rojek K, Wyrzykowski R, Gepner P (2014) Toward efficient distribution of MPDATA stencil computation on Intel MIC architecture. In: Proceedings of 1st International Workshop on High-Performance Stencil Computations\u2014HiStencils 2014. In conjunction with HiPEAC 2014, pp 51\u201356"},{"key":"2460_CR22","unstructured":"Unat D et al (eds) (2014) Programming abstractions for data locality. \nhttp:\/\/web.eecs.umich.edu\/~akamil\/papers\/padal14report.pdf\n\n. Accessed Mar 2018"},{"key":"2460_CR23","doi-asserted-by":"crossref","unstructured":"Yasui Y, Fujisawa K, Goh E.L, Baron J, Sugiura A, Uchiyama T (2016) NUMA-aware scalable graph traversal on SGI UV systems. In: Proceedings of ACM Workshop on High Performance Graph Processing. ACM, pp 19\u201326","DOI":"10.1145\/2915516.2915522"},{"key":"2460_CR24","doi-asserted-by":"crossref","unstructured":"Zhou X, Giacalone J.P, Garzar\u00e1n M.J, Kuhn R, Ni Y, Padua D (2012) Hierarchical overlapped tiling. In: Proceedings of 10th International Symposium on Code Generation and Optimization. ACM, pp 207\u2013218","DOI":"10.1145\/2259016.2259044"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-018-2460-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-018-2460-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-018-2460-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,20]],"date-time":"2019-11-20T04:16:56Z","timestamp":1574223416000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-018-2460-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,23]]},"references-count":24,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["2460"],"URL":"https:\/\/doi.org\/10.1007\/s11227-018-2460-0","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2018,6,23]]},"assertion":[{"value":"23 June 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}