{"id":"https://openalex.org/W4284887185","doi":"https://doi.org/10.1177/10943420221107880","title":"Enhancing data locality of the conjugate gradient method for high-order matrix-free finite-element implementations","display_name":"Enhancing data locality of the conjugate gradient method for high-order matrix-free finite-element implementations","publication_year":2022,"publication_date":"2022-07-07","ids":{"openalex":"https://openalex.org/W4284887185","doi":"https://doi.org/10.1177/10943420221107880"},"language":"en","primary_location":{"id":"doi:10.1177/10943420221107880","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420221107880","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://mediatum.ub.tum.de/1601725","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/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]},{"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":["Department of Mathematics, University of Augsburg, Germany","Institute for Computational Mechanics, Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Institute for Computational Mechanics, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048039716","display_name":"Dmytro Sashko","orcid":null},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dmytro Sashko","raw_affiliation_strings":["School of Mechanical and Mining Engineering, The University of Queensland, Saint Lucia, QLD, Australia"],"affiliations":[{"raw_affiliation_string":"School of Mechanical and Mining Engineering, The University of Queensland, Saint Lucia, QLD, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035503454","display_name":"Peter M\u00fcnch","orcid":"https://orcid.org/0000-0003-2368-8533"},"institutions":[{"id":"https://openalex.org/I4210139239","display_name":"Helmholtz-Zentrum Hereon","ror":"https://ror.org/03qjp1d79","country_code":"DE","type":"government","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210139239"]},{"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":false,"raw_author_name":"Peter Munch","raw_affiliation_strings":["Institute for Computational Mechanics, Technical University of Munich, Germany","Institute of Material Systems Modeling, Helmholtz-Zentrum Hereon, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Computational Mechanics, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute of Material Systems Modeling, Helmholtz-Zentrum Hereon, Germany","institution_ids":["https://openalex.org/I4210139239"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048891988"],"corresponding_institution_ids":["https://openalex.org/I179225836","https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":2.5534,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.90689428,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"37","issue":"2","first_page":"61","last_page":"81"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9983999729156494,"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/T11263","display_name":"Electromagnetic Simulation and Numerical Methods","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7128382921218872},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.6877915859222412},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6862846612930298},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5106516480445862},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5084239840507507},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4954479932785034},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.4758684039115906},{"id":"https://openalex.org/keywords/dot-product","display_name":"Dot product","score":0.469970166683197},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46663957834243774},{"id":"https://openalex.org/keywords/diagonal-matrix","display_name":"Diagonal matrix","score":0.45113760232925415},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.44602668285369873},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4392584562301636},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.43362146615982056},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.42355093359947205},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.41194140911102295},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.4116131365299225},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.28993624448776245},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.2687869668006897},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23082119226455688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7128382921218872},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.6877915859222412},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6862846612930298},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5106516480445862},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5084239840507507},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4954479932785034},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.4758684039115906},{"id":"https://openalex.org/C32900221","wikidata":"https://www.wikidata.org/wiki/Q181365","display_name":"Dot product","level":2,"score":0.469970166683197},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46663957834243774},{"id":"https://openalex.org/C113313756","wikidata":"https://www.wikidata.org/wiki/Q332791","display_name":"Diagonal matrix","level":3,"score":0.45113760232925415},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44602668285369873},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4392584562301636},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.43362146615982056},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.42355093359947205},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.41194140911102295},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.4116131365299225},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.28993624448776245},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.2687869668006897},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23082119226455688},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1177/10943420221107880","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420221107880","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1601725","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1601725","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of 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:97487","is_oa":false,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/97487","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":null,"raw_type":"doc-type:article"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1601725","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1601725","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of 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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G8135715902","display_name":null,"funder_award_id":"pr83te","funder_id":"https://openalex.org/F4320331625","funder_display_name":"Gauss Centre for Supercomputing"}],"funders":[{"id":"https://openalex.org/F4320331625","display_name":"Gauss Centre for Supercomputing","ror":"https://ror.org/0585fsj26"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1522241184","https://openalex.org/W1961751213","https://openalex.org/W1967468998","https://openalex.org/W1976990532","https://openalex.org/W1985144286","https://openalex.org/W2018225490","https://openalex.org/W2029830594","https://openalex.org/W2031149877","https://openalex.org/W2047352485","https://openalex.org/W2053237925","https://openalex.org/W2066692739","https://openalex.org/W2072132691","https://openalex.org/W2092990259","https://openalex.org/W2096714979","https://openalex.org/W2111389017","https://openalex.org/W2168276615","https://openalex.org/W2180959024","https://openalex.org/W2465804403","https://openalex.org/W2528941705","https://openalex.org/W2597480328","https://openalex.org/W2767520933","https://openalex.org/W2786313222","https://openalex.org/W2896439732","https://openalex.org/W2896548519","https://openalex.org/W2898759154","https://openalex.org/W2923328826","https://openalex.org/W2943869808","https://openalex.org/W2952622072","https://openalex.org/W2962978274","https://openalex.org/W2963610942","https://openalex.org/W2963706349","https://openalex.org/W2969262004","https://openalex.org/W3000936750","https://openalex.org/W3011811412","https://openalex.org/W3016268593","https://openalex.org/W3046774627","https://openalex.org/W3048757510","https://openalex.org/W3086430718","https://openalex.org/W3103765407","https://openalex.org/W3105886089","https://openalex.org/W3112246944","https://openalex.org/W3122714673","https://openalex.org/W3123231012","https://openalex.org/W3124354733","https://openalex.org/W3167826856","https://openalex.org/W3202306556","https://openalex.org/W4316813731","https://openalex.org/W6738593828"],"related_works":["https://openalex.org/W1509211761","https://openalex.org/W2730282969","https://openalex.org/W2343404593","https://openalex.org/W2141331848","https://openalex.org/W2963483698","https://openalex.org/W2163457938","https://openalex.org/W1946946319","https://openalex.org/W2206383384","https://openalex.org/W2041999884","https://openalex.org/W4284887185"],"abstract_inverted_index":{"This":[0],"work":[1],"investigates":[2],"a":[3,35,54,67,129],"variant":[4],"of":[5,17,41,43,71,75,80],"the":[6,15,30,47,58,72,76,81,115,119,155],"conjugate":[7],"gradient":[8],"(CG)":[9],"method":[10,83,117],"and":[11,26,38,50,105,139,150],"embeds":[12],"it":[13],"into":[14],"context":[16],"high-order":[18],"finite-element":[19],"schemes":[20],"with":[21,57,61,94,118],"fast":[22,99],"matrix-free":[23],"operator":[24],"evaluation":[25],"cheap":[27],"preconditioners":[28],"like":[29],"matrix":[31],"diagonal.":[32],"Relying":[33],"on":[34,108],"data-dependency":[36],"analysis":[37],"appropriate":[39],"enumeration":[40],"degrees":[42],"freedom,":[44],"we":[45],"interleave":[46],"vector":[48,73],"updates":[49],"inner":[51],"products":[52],"in":[53],"CG":[55,82,116,131,138,141],"iteration":[56],"matrix-vector":[59],"product":[60],"only":[62],"minor":[63],"organizational":[64],"overhead.":[65],"As":[66],"result,":[68],"around":[69,124],"90%":[70],"entries":[74],"three":[77],"active":[78],"vectors":[79],"are":[84],"transferred":[85],"from":[86],"slow":[87],"RAM":[88],"memory":[89],"exactly":[90],"once":[91],"per":[92],"iteration,":[93],"all":[95],"additional":[96],"access":[97],"hitting":[98],"cache":[100],"memory.":[101],"Node-level":[102],"performance":[103,121,153],"analyses":[104],"scaling":[106,157],"studies":[107],"up":[109],"to":[110],"147k":[111],"cores":[112],"show":[113],"that":[114,146],"proposed":[120],"optimizations":[122],"is":[123],"two":[125],"times":[126],"faster":[127],"than":[128],"standard":[130],"solver":[132],"as":[133,135],"well":[134],"optimized":[136],"pipelined":[137],"s-step":[140],"methods":[142],"for":[143],"large":[144],"sizes":[145],"exceed":[147],"processor":[148],"caches,":[149],"provides":[151],"similar":[152],"near":[154],"strong":[156],"limit.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2022-07-09T00:00:00"}
