{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:38:54Z","timestamp":1740123534484,"version":"3.37.3"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2020,5,19]],"date-time":"2020-05-19T00:00:00Z","timestamp":1589846400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,5,19]],"date-time":"2020-05-19T00:00:00Z","timestamp":1589846400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"National Key R&D Program of China","award":["2017YFB0202500"],"award-info":[{"award-number":["2017YFB0202500"]}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61971034","U1730102"],"award-info":[{"award-number":["61971034","U1730102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1007\/s11227-020-03308-9","type":"journal-article","created":{"date-parts":[[2020,5,19]],"date-time":"2020-05-19T07:03:43Z","timestamp":1589871823000},"page":"1502-1516","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Efficient parallelization of multilevel fast multipole algorithm for electromagnetic simulation on many-core SW26010 processor"],"prefix":"10.1007","volume":"77","author":[{"given":"Wei-Jia","family":"He","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0638-9526","authenticated-orcid":false,"given":"Ming-Lin","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Wu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xin-Qing","family":"Sheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,5,19]]},"reference":[{"issue":"1","key":"3308_CR1","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/MCISE.2000.814652","volume":"2","author":"J Dongarra","year":"2000","unstructured":"Dongarra J, Sullivan F (2000) Guest Editors Introduction to the top 10 algorithms. Comput Sci Eng 2(1):22\u201323","journal-title":"Comput Sci Eng"},{"issue":"10","key":"3308_CR2","doi-asserted-by":"publisher","first-page":"1488","DOI":"10.1109\/8.633855","volume":"45","author":"JM Song","year":"1997","unstructured":"Song JM, Lu CC, Chew WC (1997) Multilevel fast multipole algorithm for electromagnetic scattering by large complex objects. IEEE Trans Antennas Propag 45(10):1488\u20131493","journal-title":"IEEE Trans Antennas Propag"},{"issue":"11","key":"3308_CR3","doi-asserted-by":"publisher","first-page":"1718","DOI":"10.1109\/8.736628","volume":"46","author":"XQ Sheng","year":"1998","unstructured":"Sheng XQ, Jin JM, Song J et al (1998) Solution of combined-field integral equation using multilevel fast multipole algorithm for scattering by homogeneous bodies. IEEE Trans Antennas Propag 46(11):1718\u20131726","journal-title":"IEEE Trans Antennas Propag"},{"issue":"2","key":"3308_CR4","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/MAP.2003.1203119","volume":"45","author":"S Velamparambil","year":"2003","unstructured":"Velamparambil S, Chew WC, Song JM (2003) 10 million unknowns: Is it that big? IEEE Antennas Propag Mag 45(2):43\u201358","journal-title":"IEEE Antennas Propag Mag"},{"issue":"3","key":"3308_CR5","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/MAP.2008.4563583","volume":"50","author":"XM Pan","year":"2008","unstructured":"Pan XM, Sheng XQ (2008) A sophisticated parallel MLFMA for scattering by extremely large targets. IEEE Antennas Propag Mag 50(3):129\u2013138","journal-title":"IEEE Antennas Propag Mag"},{"issue":"6","key":"3308_CR6","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1049\/el:20082282","volume":"44","author":"O Ergul","year":"2008","unstructured":"Ergul O, Gurel L (2008) Hierarchical parallelization strategy for multilevel fast multipole algorithm in computational electromagnetics. Electron Lett 44(6):3\u20134","journal-title":"Electron Lett"},{"issue":"11","key":"3308_CR7","doi-asserted-by":"publisher","first-page":"6965","DOI":"10.1109\/TAP.2019.2927660","volume":"67","author":"ML Yang","year":"2008","unstructured":"Yang ML, Wu BY, Gao HW et al (2008) A ternary parallelization approach of MLFMA for solving electromagnetic scattering problems with over 10 billion unknowns. IEEE Trans Antennas Propag 67(11):6965\u20136978","journal-title":"IEEE Trans Antennas Propag"},{"issue":"4","key":"3308_CR8","first-page":"381","volume":"25","author":"FJ Hu","year":"2010","unstructured":"Hu FJ, Nie ZP, Hu J (2010) An efficient parallel multilevel fast multipole algorithm for large-scale scattering problems. Appl Comput Electromagn Soc J 25(4):381\u2013387","journal-title":"Appl Comput Electromagn Soc J"},{"issue":"2","key":"3308_CR9","first-page":"167","volume":"25","author":"HP Zhao","year":"2010","unstructured":"Zhao HP, Hu J, Nie ZP (2010) Parallelization of MLFMA with composite load partition criteria and asynchronous communication. Appl Comput Electromag Soc J 25(2):167\u2013173","journal-title":"Appl Comput Electromag Soc J"},{"issue":"5","key":"3308_CR10","doi-asserted-by":"publisher","first-page":"2571","DOI":"10.1109\/TAP.2012.2189746","volume":"60","author":"XM Pan","year":"2012","unstructured":"Pan XM, Pi WC, Yang ML et al (2012) Solving problems with over one billion unknowns by the MLFMA. IEEE Trans Antennas Propag 60(5):2571\u20132574","journal-title":"IEEE Trans Antennas Propag"},{"issue":"3","key":"3308_CR11","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1109\/MAP.2010.5586593","volume":"53","author":"DD Donno","year":"2010","unstructured":"Donno DD, Esposito A, Tarricone LCL (2010) Introduction to GPU computing and CUDA programming: a case study on FDTD. IEEE Antennas Propag Mag 53(3):116\u2013122","journal-title":"IEEE Antennas Propag Mag"},{"key":"3308_CR12","unstructured":"Corp NVIDIA (2011) NVIDIA CUDA C Programming Guide. Santa Clara, CA, USA"},{"key":"3308_CR13","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1016\/j.procs.2013.05.219","volume":"18","author":"G Crimi","year":"2013","unstructured":"Crimi G, Mantovani F, Pivanti M et al (2013) Early experience on porting and running a Lattice Boltzmann code on the Xeon-Phi co-processor. Proc Comput Sci 18:551\u2013560","journal-title":"Proc Comput Sci"},{"issue":"10","key":"3308_CR14","doi-asserted-by":"publisher","first-page":"2742","DOI":"10.1016\/j.cpc.2014.06.010","volume":"185","author":"K Murano","year":"2014","unstructured":"Murano K, Shimobaba T, Sugiyama A et al (2014) Fast computation of computer-generated hologram using Xeon Phi coprocessor. Comput Phys Commun 185(10):2742\u20132757","journal-title":"Comput Phys Commun"},{"key":"3308_CR15","first-page":"1063","volume":"2014","author":"G Teodoro","year":"2014","unstructured":"Teodoro G, Kurc T, Kong J et al (2014) Comparative performance analysis of Intel Xeon Phi, GPU, and CPU: a case study from microscopy image analysis. IEEE Trans Parallel Distrib Syst 2014:1063\u20131072","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"1","key":"3308_CR16","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/s11390-015-1510-9","volume":"30","author":"F Zheng","year":"2015","unstructured":"Zheng F, Li HL, Lv H et al (2015) Cooperative computing techniques for a deeply fused and heterogeneous many-core processor architecture. J Comput Sci Technol 30(1):145\u2013162","journal-title":"J Comput Sci Technol"},{"key":"3308_CR17","doi-asserted-by":"crossref","unstructured":"Jiang L, Yang C, Ao Y et\u00a0al (2017) Towards Highly Efficient DGEMM on the Emerging SW26010 Many-Core Processor. In: 46th International Conference on Parallel Processing (ICPP), IEEE computer society","DOI":"10.1109\/ICPP.2017.51"},{"issue":"3","key":"3308_CR18","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1002\/mop.24963","volume":"52","author":"K Xu","year":"2010","unstructured":"Xu K, Ding DZ, Fan ZH et al (2010) Multilevel fast multipole algorithm enhanced by GPU parallel technique for electromagnetic scattering problems. Microw Opt Technol Lett 52(3):502\u2013507","journal-title":"Microw Opt Technol Lett"},{"issue":"7","key":"3308_CR19","doi-asserted-by":"publisher","first-page":"3607","DOI":"10.1109\/TAP.2013.2258882","volume":"61","author":"J Guan","year":"2013","unstructured":"Guan J, Yan S, Jin JM (2013) An OpenMP-CUDA implementation of multilevel fast multipole algorithm for electromagnetic simulation on multi-GPU computing systems. IEEE Trans Antennas Propag 61(7):3607\u20133616","journal-title":"IEEE Trans Antennas Propag"},{"issue":"11","key":"3308_CR20","doi-asserted-by":"publisher","first-page":"5634","DOI":"10.1109\/TAP.2014.2350536","volume":"62","author":"X Mu","year":"2014","unstructured":"Mu X, Zhou HX, Chen K et al (2014) Higher order method of moments with a parallel out-of-core LU solver on GPU\/CPU platform. IEEE Trans Antennas Propag 62(11):5634\u20135646","journal-title":"IEEE Trans Antennas Propag"},{"issue":"4","key":"3308_CR21","first-page":"145","volume":"1","author":"N Tran","year":"2016","unstructured":"Tran N, Kilic O (2016) Parallel implementations of multilevel fast multipole algorithm on graphical processing unit cluster for large-scale electromagnetics objects. Appl Comput Electromag Soc J 1(4):145\u2013148","journal-title":"Appl Comput Electromag Soc J"},{"issue":"3","key":"3308_CR22","first-page":"335","volume":"33","author":"T Phan","year":"2018","unstructured":"Phan T, Tran N, Kilic O (2018) Multi-level fast multipole algorithm for 3-D homogeneous dielectric objects using MPI-CUDA on GPU cluster. Appl Comput Electromag Soc J 33(3):335\u2013338","journal-title":"Appl Comput Electromag Soc J"},{"issue":"3","key":"3308_CR23","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1109\/TAP.1982.1142818","volume":"30","author":"S Rao","year":"1982","unstructured":"Rao S, Wilton D, Glisson A (1982) Electromagnetic scattering by surfaces of arbitrary shape. IEEE Trans Antennas Propag 30(3):409\u2013418","journal-title":"IEEE Trans Antennas Propag"},{"issue":"7","key":"3308_CR24","doi-asserted-by":"publisher","first-page":"072001","DOI":"10.1007\/s11432-016-5588-7","volume":"59","author":"H Fu","year":"2016","unstructured":"Fu H, Liao JF, Yang JZ et al (2016) The Sunway TaihuLight supercomputer: system and applications. Sci China Inf Sci 59(7):072001","journal-title":"Sci China Inf Sci"},{"issue":"3","key":"3308_CR25","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1093\/nsr\/nww044","volume":"3","author":"J Dongarra","year":"2016","unstructured":"Dongarra J (2016) Sunway TaihuLight supercomputer makes its appearance. Natl Sci Rev 3(3):265\u2013266","journal-title":"Natl Sci Rev"},{"key":"3308_CR26","doi-asserted-by":"crossref","unstructured":"Xu Z, Lin J, Matsuoka S (2017) Benchmarking SW26010 Many-Core processor. In: IEEE International parallel and distributed processing symposium workshops","DOI":"10.1109\/IPDPSW.2017.9"},{"key":"3308_CR27","unstructured":"OpenACC-Standard.org (2018) The OpenACC Application Programming Interface"},{"key":"3308_CR28","unstructured":"National Supercomputing Center in Wuxi (2016) The Compiling System User Guide of Sunway TighthuLight"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03308-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-020-03308-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03308-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,18]],"date-time":"2021-05-18T23:52:27Z","timestamp":1621381947000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-020-03308-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,19]]},"references-count":28,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,2]]}},"alternative-id":["3308"],"URL":"https:\/\/doi.org\/10.1007\/s11227-020-03308-9","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2020,5,19]]},"assertion":[{"value":"19 May 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}