{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:39:01Z","timestamp":1740123541285,"version":"3.37.3"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2020,5,30]],"date-time":"2020-05-30T00:00:00Z","timestamp":1590796800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,5,30]],"date-time":"2020-05-30T00:00:00Z","timestamp":1590796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100000104","name":"National Aeronautics and Space Administration","doi-asserted-by":"crossref","award":["NNX15AU66A"],"award-info":[{"award-number":["NNX15AU66A"]}],"id":[{"id":"10.13039\/100000104","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\/s11227-020-03340-9","type":"journal-article","created":{"date-parts":[[2020,5,30]],"date-time":"2020-05-30T17:02:31Z","timestamp":1590858151000},"page":"1976-1997","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Applying the swept rule for solving explicit partial differential equations on heterogeneous computing systems"],"prefix":"10.1007","volume":"77","author":[{"given":"Daniel J.","family":"Magee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anthony S.","family":"Walker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4425-7097","authenticated-orcid":false,"given":"Kyle E.","family":"Niemeyer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,5,30]]},"reference":[{"key":"3340_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jocs.2016.04.014","volume":"14","author":"V Alexandrov","year":"2016","unstructured":"Alexandrov V (2016) Route to exascale: novel mathematical methods, scalable algorithms and computational science skills. J Comput Sci 14:1\u20134. https:\/\/doi.org\/10.1016\/j.jocs.2016.04.014","journal-title":"J Comput Sci"},{"key":"3340_CR2","unstructured":"Alhubail M, Wang Q (2015) K-S_1D_Swept, git commit e575d73. https:\/\/github.com\/hubailmm\/K-S_1D_Swept"},{"key":"3340_CR3","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.jcp.2015.11.026","volume":"307","author":"M Alhubail","year":"2016","unstructured":"Alhubail M, Wang Q (2016) The swept rule for breaking the latency barrier in time advancing PDEs. J Comput Phys 307:110\u2013121. https:\/\/doi.org\/10.1016\/j.jcp.2015.11.026","journal-title":"J Comput Phys"},{"key":"3340_CR4","doi-asserted-by":"publisher","unstructured":"Alhubail M, Wang Q (2017) Improving the strong parallel scalability of CFD schemes via the swept domain decomposition rule. In: 55th AIAA Aerospace Sciences Meeting, Grapevine, Texas, American Institute of Aeronautics and Astronautics, January 2017. https:\/\/doi.org\/10.2514\/6.2017-1218","DOI":"10.2514\/6.2017-1218"},{"key":"3340_CR5","doi-asserted-by":"crossref","unstructured":"Alhubail MM, Wang Q, Williams J (2016) The swept rule for breaking the latency barrier in time advancing two-dimensional PDEs. arXiv:1602.07558 [cs.NA]","DOI":"10.1016\/j.jcp.2015.11.026"},{"key":"3340_CR6","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.procs.2012.04.003","volume":"9","author":"M Baboulin","year":"2012","unstructured":"Baboulin M, Donfack S, Dongarra J, Grigori L, R\u00e9my A, Tomov S (2012) A class of communication-avoiding algorithms for solving general dense linear systems on CPU\/GPU parallel machines. Procedia Comput Sci 9:17\u201326. https:\/\/doi.org\/10.1016\/j.procs.2012.04.003","journal-title":"Procedia Comput Sci"},{"issue":"3","key":"3340_CR7","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1137\/090769156","volume":"32","author":"G Ballard","year":"2011","unstructured":"Ballard G, Demmel J, Holtz O, Schwartz O (2011) Minimizing communication in numerical linear algebra. SIAM J Matrix Anal Appl 32(3):866\u2013901","journal-title":"SIAM J Matrix Anal Appl"},{"key":"3340_CR8","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-0348-8534-8_21","volume-title":"Programming environments for massively parallel distributed systems","author":"L Clarke","year":"1994","unstructured":"Clarke L, Glendinning I, Hempel R (1994) The MPI message passing interface standard. Programming environments for massively parallel distributed systems. Birkh\u00e4user, Basel, pp 213\u2013218. https:\/\/doi.org\/10.1007\/978-3-0348-8534-8_21"},{"key":"3340_CR9","doi-asserted-by":"crossref","unstructured":"Datta K, Murphy M, Volkov V, Williams S, Carter J, Oliker L, Patterson D, Shalf J, Yelick K (2008) Stencil computation optimization and auto-tuning on state-of-the-art multicore architectures. In: Proceedings of the 2008 ACM\/IEEE Conference on Supercomputing, SC \u201908, IEEE Press, Piscataway, NJ, USA, pp 4:1\u20134:12","DOI":"10.1109\/SC.2008.5222004"},{"key":"3340_CR10","doi-asserted-by":"crossref","unstructured":"Demmel J, Hoemmen M, Mohiyuddin M, Yelick K (2008) Avoiding communication in sparse matrix computations. In: 2008 IEEE International Symposium on Parallel and Distributed Processing, IEEE, pp 1\u201312","DOI":"10.1109\/IPDPS.2008.4536305"},{"issue":"1","key":"3340_CR11","doi-asserted-by":"publisher","first-page":"105","DOI":"10.2140\/camcos.2012.7.105","volume":"7","author":"M Emmett","year":"2012","unstructured":"Emmett M, Minion M (2012) Toward an efficient parallel in time method for partial differential equations. Commun Appl Math Comput Sci 7(1):105\u2013132","journal-title":"Commun Appl Math Comput Sci"},{"issue":"5","key":"3340_CR12","doi-asserted-by":"publisher","first-page":"S298","DOI":"10.1137\/16M1082330","volume":"39","author":"RD Falgout","year":"2017","unstructured":"Falgout RD, Manteuffel TA, O\u2019Neill B, Schroder JB (2017) Multigrid reduction in time for nonlinear parabolic problems: a case study. SIAM J Sci Comput 39(5):S298\u2013S322. https:\/\/doi.org\/10.1137\/16M1082330","journal-title":"SIAM J Sci Comput"},{"issue":"6","key":"3340_CR13","doi-asserted-by":"publisher","first-page":"C635","DOI":"10.1137\/130944230","volume":"36","author":"RD Falgout","year":"2014","unstructured":"Falgout RD, Friedhoff S, Kolev TV, MacLachlan SP, Schroder JB (2014) Parallel time integration with multigrid. SIAM J Sci Comput 36(6):C635\u2013C661","journal-title":"SIAM J Sci Comput"},{"key":"3340_CR14","series-title":"Contributions in Mathematical and Computational Sciences","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-23321-5_3","volume-title":"Multiple Shooting and Time Domain Decomposition Methods","author":"MJ Gander","year":"2015","unstructured":"Gander MJ (2015) 50 years of time parallel time integration. In: Carraro T, Geiger M, K\u00f6rkel S, Rannacher R (eds) Multiple Shooting and Time Domain Decomposition Methods, vol 9. Contributions in Mathematical and Computational Sciences. Cham, Springer, pp 69\u2013113. https:\/\/doi.org\/10.1007\/978-3-319-23321-5_3"},{"issue":"2","key":"3340_CR15","doi-asserted-by":"publisher","first-page":"C123","DOI":"10.1137\/110856137","volume":"35","author":"MJ Gander","year":"2013","unstructured":"Gander MJ, G\u00fcttel S (2013) Paraexp: a parallel integrator for linear initial-value problems. SIAM J Sci Comput 35(2):C123\u2013C142","journal-title":"SIAM J Sci Comput"},{"issue":"4","key":"3340_CR16","doi-asserted-by":"publisher","first-page":"A2173","DOI":"10.1137\/15M1046605","volume":"38","author":"MJ Gander","year":"2016","unstructured":"Gander MJ, Neumuller M (2016) Analysis of a new space-time parallel multigrid algorithm for parabolic problems. SIAM J Sci Comput 38(4):A2173\u2013A2208","journal-title":"SIAM J Sci Comput"},{"key":"3340_CR17","doi-asserted-by":"publisher","unstructured":"Huerta YA, Swartz B, Lilja DJ (2017) Determining work partitioning on closely coupled heterogeneous computing systems using statistical design of experiments. In: 2017 IEEE International Symposium on Workload Characterization (IISWC), October 2017, pp 118\u2013119. https:\/\/doi.org\/10.1109\/IISWC.2017.8167766","DOI":"10.1109\/IISWC.2017.8167766"},{"issue":"1","key":"3340_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.parco.2012.10.002","volume":"39","author":"DA Jacobsen","year":"2013","unstructured":"Jacobsen DA, Senocak I (2013) Multi-level parallelism for incompressible flow computations on GPU clusters. Parallel Comput 39(1):1\u201320. https:\/\/doi.org\/10.1016\/j.parco.2012.10.002","journal-title":"Parallel Comput"},{"issue":"3","key":"3340_CR19","doi-asserted-by":"publisher","first-page":"1401","DOI":"10.1137\/120863691","volume":"34","author":"A Khabou","year":"2013","unstructured":"Khabou A, Demmel JW, Grigori L, Gu M (2013) LU factorization with panel rank revealing pivoting and its communication avoiding version. SIAM J Matrix Anal Appl 34(3):1401\u20131429","journal-title":"SIAM J Matrix Anal Appl"},{"issue":"7","key":"3340_CR20","first-page":"661","volume":"332","author":"J-L Lions","year":"2001","unstructured":"Lions J-L, Maday Y, Turinici G (2001) R \u2019e solution of edp by a sch \u00e9 ma en temps guillemotleft parar \u2019e el guillemotright. Proc Acad Sci Ser I Math 332(7):661\u2013668","journal-title":"Proc Acad Sci Ser I Math"},{"issue":"6","key":"3340_CR21","doi-asserted-by":"publisher","first-page":"1172","DOI":"10.1016\/j.cpc.2012.01.019","volume":"183","author":"F Lu","year":"2012","unstructured":"Lu F, Song J, Yin F, Zhu X (2012) Performance evaluation of hybrid programming patterns for large CPU\/GPU heterogeneous clusters. Comput Phys Commun 183(6):1172\u20131181. https:\/\/doi.org\/10.1016\/j.cpc.2012.01.019","journal-title":"Comput Phys Commun"},{"key":"3340_CR22","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1016\/j.jcp.2017.12.028","volume":"357","author":"DJ Magee","year":"2018","unstructured":"Magee DJ, Niemeyer KE (2018) Accelerating solutions of one-dimensional unsteady PDEs with GPU-based swept time-space decomposition. J Comput Phys 357:338\u2013352. https:\/\/doi.org\/10.1016\/j.jcp.2017.12.028","journal-title":"J Comput Phys"},{"key":"3340_CR23","doi-asserted-by":"publisher","unstructured":"Magee DJ, Niemeyer KE (2018) Niemeyer-Research-Group\/hSweep: MS Thesis Official, June 2018. https:\/\/doi.org\/10.5281\/zenodo.1291212","DOI":"10.5281\/zenodo.1291212"},{"key":"3340_CR24","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.3787144","author":"DJ Magee","year":"2020","unstructured":"Magee DJ, Walker AS, Niemeyer KE (2020) Data, plotting scripts, and figures for \u201cApplying the swept rule for explicit partial differential equation solutions on heterogeneous computing systems\u2019. Zenodo. https:\/\/doi.org\/10.5281\/zenodo.3787144","journal-title":"Zenodo"},{"issue":"4","key":"3340_CR25","doi-asserted-by":"publisher","first-page":"C439","DOI":"10.1137\/140991133","volume":"37","author":"T Malas","year":"2015","unstructured":"Malas T, Hager G, Ltaief H, Stengel H, Wellein G, Keyes D (2015) Multicore-optimized wavefront diamond blocking for optimizing stencil updates. SIAM J Sci Comput 37(4):C439\u2013C464. https:\/\/doi.org\/10.1137\/140991133","journal-title":"SIAM J Sci Comput"},{"key":"3340_CR26","unstructured":"Mills RT, Rupp K, Adams M, Brown J, Isaac T, Knepley M, Smith B, Zhang H (2017) Software strategy and experiences with manycore processor support in PETSc. In: SIAM Pacific Northwest Regional Conference, October 2017"},{"issue":"5","key":"3340_CR27","doi-asserted-by":"publisher","first-page":"S244","DOI":"10.1137\/14097536X","volume":"37","author":"ML Minion","year":"2015","unstructured":"Minion ML, Speck R, Bolten M, Emmett M, Ruprecht D (2015) Interweaving PFASST and parallel multigrid. SIAM J Sci Comput 37(5):S244\u2013S263","journal-title":"SIAM J Sci Comput"},{"key":"3340_CR28","doi-asserted-by":"crossref","unstructured":"Solomonik E, Ballard G, Demmel J, Hoefler T (2017) A communication-avoiding parallel algorithm for the symmetric eigenvalue problem. In: Proceedings of the 29th ACM Symposium on Parallelism in Algorithms and Architectures, pp 111\u2013121","DOI":"10.1145\/3087556.3087561"},{"key":"3340_CR29","unstructured":"Wang Q (2017) Decomposition of stencil update formula into atomic stages. arXiv:1606.00721 [math.NA]"},{"key":"3340_CR30","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.jcp.2017.12.029","volume":"358","author":"S-L Wu","year":"2018","unstructured":"Wu S-L, Zhou T (2018) Parareal algorithms with local time-integrators for time fractional differential equations. J Comput Phys 358:135\u2013149. https:\/\/doi.org\/10.1016\/j.jcp.2017.12.029","journal-title":"J Comput Phys"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03340-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-020-03340-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03340-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,29]],"date-time":"2021-05-29T23:22:04Z","timestamp":1622330524000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-020-03340-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,30]]},"references-count":30,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,2]]}},"alternative-id":["3340"],"URL":"https:\/\/doi.org\/10.1007\/s11227-020-03340-9","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2020,5,30]]},"assertion":[{"value":"30 May 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}