{"id":"https://openalex.org/W2943869808","doi":"https://doi.org/10.1145/3322813","title":"Multigrid for Matrix-Free High-Order Finite Element Computations on Graphics Processors","display_name":"Multigrid for Matrix-Free High-Order Finite Element Computations on Graphics Processors","publication_year":2019,"publication_date":"2019-03-31","ids":{"openalex":"https://openalex.org/W2943869808","doi":"https://doi.org/10.1145/3322813","mag":"2943869808"},"language":"en","primary_location":{"id":"doi:10.1145/3322813","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3322813","pdf_url":null,"source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://mediatum.ub.tum.de/node?id=1536794","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048891988","display_name":"Martin Kronbichler","orcid":"https://orcid.org/0000-0001-8406-835X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Martin Kronbichler","raw_affiliation_strings":["Technical University of Munich, Garching, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065646574","display_name":"Karl Ljungkvist","orcid":null},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Karl Ljungkvist","raw_affiliation_strings":["Uppsala University, Uppsala, Sweden"],"affiliations":[{"raw_affiliation_string":"Uppsala University, Uppsala, Sweden","institution_ids":["https://openalex.org/I123387679"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048891988"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":7.5477,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":{"value":0.98621934,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"6","issue":"1","first_page":"1","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11416","display_name":"Numerical methods for differential equations","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7020726203918457},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6841996908187866},{"id":"https://openalex.org/keywords/multigrid-method","display_name":"Multigrid method","score":0.6452613472938538},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5809353590011597},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.5252906084060669},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4938124120235443},{"id":"https://openalex.org/keywords/gaussian-elimination","display_name":"Gaussian elimination","score":0.4806138873100281},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.43630117177963257},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.4228043854236603},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.42244765162467957},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.31099146604537964},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.3070574402809143},{"id":"https://openalex.org/keywords/partial-differential-equation","display_name":"Partial differential equation","score":0.23390164971351624},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22041746973991394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7020726203918457},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6841996908187866},{"id":"https://openalex.org/C137119250","wikidata":"https://www.wikidata.org/wiki/Q1413101","display_name":"Multigrid method","level":3,"score":0.6452613472938538},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5809353590011597},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.5252906084060669},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4938124120235443},{"id":"https://openalex.org/C126312332","wikidata":"https://www.wikidata.org/wiki/Q2658","display_name":"Gaussian elimination","level":3,"score":0.4806138873100281},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.43630117177963257},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.4228043854236603},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.42244765162467957},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31099146604537964},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3070574402809143},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.23390164971351624},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22041746973991394},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3322813","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3322813","pdf_url":null,"source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","raw_type":"journal-article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1536794","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1536794","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:98191","is_oa":false,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/98191","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1536794","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1536794","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G8411320146","display_name":null,"funder_award_id":"KR4661/2-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W51719658","https://openalex.org/W114707485","https://openalex.org/W151647068","https://openalex.org/W321261355","https://openalex.org/W579519726","https://openalex.org/W607200110","https://openalex.org/W1487563957","https://openalex.org/W1596846800","https://openalex.org/W1790356362","https://openalex.org/W1900162302","https://openalex.org/W1961751213","https://openalex.org/W1965742121","https://openalex.org/W1973032228","https://openalex.org/W1976692199","https://openalex.org/W1979677378","https://openalex.org/W1982167538","https://openalex.org/W1985144286","https://openalex.org/W1991369214","https://openalex.org/W1999534369","https://openalex.org/W2008060144","https://openalex.org/W2011664413","https://openalex.org/W2018225490","https://openalex.org/W2022916138","https://openalex.org/W2026386568","https://openalex.org/W2031149877","https://openalex.org/W2040651749","https://openalex.org/W2046273006","https://openalex.org/W2047352485","https://openalex.org/W2049415037","https://openalex.org/W2053486661","https://openalex.org/W2053572944","https://openalex.org/W2057630513","https://openalex.org/W2059340658","https://openalex.org/W2069662345","https://openalex.org/W2072132691","https://openalex.org/W2079118382","https://openalex.org/W2083322338","https://openalex.org/W2084658840","https://openalex.org/W2101511474","https://openalex.org/W2104736438","https://openalex.org/W2105729768","https://openalex.org/W2117752372","https://openalex.org/W2120919211","https://openalex.org/W2134329553","https://openalex.org/W2151317657","https://openalex.org/W2154555766","https://openalex.org/W2159270985","https://openalex.org/W2165804517","https://openalex.org/W2166122567","https://openalex.org/W2315004628","https://openalex.org/W2474724963","https://openalex.org/W2509141630","https://openalex.org/W2561675875","https://openalex.org/W2592996154","https://openalex.org/W2597480328","https://openalex.org/W2614048889","https://openalex.org/W2622491854","https://openalex.org/W2746871167","https://openalex.org/W2767520933","https://openalex.org/W2786313222","https://openalex.org/W2796649226","https://openalex.org/W2806102590","https://openalex.org/W2916303624","https://openalex.org/W2922419788","https://openalex.org/W2950866379","https://openalex.org/W2963610942","https://openalex.org/W2963867113","https://openalex.org/W2964108306","https://openalex.org/W2964116207","https://openalex.org/W3002206487","https://openalex.org/W3103023519","https://openalex.org/W3103104567","https://openalex.org/W3104266598","https://openalex.org/W3105115110","https://openalex.org/W3122098538","https://openalex.org/W3122718397","https://openalex.org/W3124354733","https://openalex.org/W4233549502"],"related_works":["https://openalex.org/W2022666014","https://openalex.org/W2040165403","https://openalex.org/W2804034492","https://openalex.org/W2543276709","https://openalex.org/W2494722835","https://openalex.org/W2909436937","https://openalex.org/W4385164339","https://openalex.org/W2186034941","https://openalex.org/W4214765606","https://openalex.org/W2168689950"],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"matrix-free":[3,27,57],"finite-element":[4],"techniques":[5],"for":[6,40,138,186,214],"efficiently":[7],"solving":[8],"partial":[9],"differential":[10],"equations":[11],"on":[12,72,85],"modern":[13],"many-core":[14],"processors,":[15],"such":[16],"as":[17],"graphics":[18],"cards.":[19],"We":[20,63],"develop":[21],"a":[22,26,79,118,183],"GPU":[23,77,100,155],"parallelization":[24],"of":[25,68,113,120,134,153,173],"geometric":[28],"multigrid":[29,221],"iterative":[30],"solver":[31,211],"targeting":[32],"moderate":[33,139],"and":[34,43,90,117,125,144,157,206],"high":[35],"polynomial":[36,140],"degrees,":[37],"with":[38,48,60,162,168,226],"support":[39],"general":[41],"curved":[42],"adaptively":[44],"refined":[45],"hexahedral":[46],"meshes":[47],"hanging":[49],"nodes.":[50],"The":[51,127],"central":[52],"algorithmic":[53],"component":[54],"is":[55,102,136],"the":[56,65,99,114,151,154,158,165,171,174,188,194,198,210,220],"operator":[58],"evaluation":[59,172],"sum":[61],"factorization.":[62],"compare":[64],"node-level":[66],"performance":[67,148],"our":[69],"implementation":[70,83,101],"running":[71,84],"an":[73,91,227],"Nvidia":[74],"Pascal":[75],"P100":[76],"to":[78,105,130,170,181,202,237],"highly":[80],"optimized":[81],"multicore":[82],"comparable":[86],"Intel":[87,92],"Broadwell":[88],"CPUs":[89],"Xeon":[93],"Phi.":[94],"Our":[95],"experiments":[96],"show":[97],"that":[98,218],"approximately":[103],"1.5":[104],"2":[106],"times":[107],"faster":[108],"across":[109],"four":[110],"different":[111],"scenarios":[112],"Poisson":[115],"equation":[116],"variety":[119],"element":[121],"degrees":[122,141],"in":[123,192,223,230],"2D":[124],"3D.":[126],"lowest":[128],"time":[129],"solution":[131],"per":[132],"degree":[133],"freedom":[135],"recorded":[137],"between":[142],"3":[143],"5.":[145],"A":[146],"detailed":[147],"analysis":[149],"highlights":[150],"capabilities":[152],"architecture":[156],"chosen":[159],"execution":[160],"model":[161],"threading":[163],"within":[164],"element,":[166],"particularly":[167],"respect":[169],"matrix-vector":[175],"product.":[176],"Atomic":[177],"intrinsics":[178],"are":[179],"shown":[180],"provide":[182],"fast":[184],"way":[185],"avoiding":[187],"possible":[189],"race":[190],"conditions":[191],"summing":[193],"elemental":[195],"residuals":[196],"into":[197],"global":[199],"vector":[200],"associated":[201],"shared":[203],"vertices,":[204],"edges,":[205],"surfaces.":[207],"In":[208],"addition,":[209],"infrastructure":[212],"allows":[213],"using":[215],"mixed-precision":[216],"arithmetic":[217],"performs":[219],"V-cycle":[222],"single":[224],"precision":[225],"outer":[228],"correction":[229],"double":[231],"precision,":[232],"increasing":[233],"throughput":[234],"by":[235],"up":[236],"83%.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-30T08:08:38.191290","created_date":"2025-10-10T00:00:00"}
