{"id":"https://openalex.org/W4389451650","doi":"https://doi.org/10.1177/10943420231217221","title":"Cache-optimized and low-overhead implementations of additive Schwarz methods for high-order FEM multigrid computations","display_name":"Cache-optimized and low-overhead implementations of additive Schwarz methods for high-order FEM multigrid computations","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4389451650","doi":"https://doi.org/10.1177/10943420231217221"},"language":"en","primary_location":{"id":"doi:10.1177/10943420231217221","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420231217221","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035503454","display_name":"Peter M\u00fcnch","orcid":"https://orcid.org/0000-0003-2368-8533"},"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"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Peter Munch","raw_affiliation_strings":["High-Performance Scientific Computing, University of Augsburg, Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"High-Performance Scientific Computing, University of Augsburg, Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"last","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/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Kronbichler","raw_affiliation_strings":["Applied Numerics, Faculty of Mathematics, Ruhr University Bochum, Bochum, Germany","High-Performance Scientific Computing, University of Augsburg, Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"Applied Numerics, Faculty of Mathematics, Ruhr University Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]},{"raw_affiliation_string":"High-Performance Scientific Computing, University of Augsburg, Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035503454"],"corresponding_institution_ids":["https://openalex.org/I179225836"],"apc_list":null,"apc_paid":null,"fwci":1.273,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7683368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"38","issue":"3","first_page":"192","last_page":"209"},"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":0.9995999932289124,"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":0.9995999932289124,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9991999864578247,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/multigrid-method","display_name":"Multigrid method","score":0.7097436189651489},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6421099305152893},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5505328178405762},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4819655120372772},{"id":"https://openalex.org/keywords/polygon-mesh","display_name":"Polygon mesh","score":0.4366661310195923},{"id":"https://openalex.org/keywords/preconditioner","display_name":"Preconditioner","score":0.4232533872127533},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36716169118881226},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.34176719188690186},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33367282152175903},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.3114366829395294},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27249962091445923},{"id":"https://openalex.org/keywords/partial-differential-equation","display_name":"Partial differential equation","score":0.1340881586074829}],"concepts":[{"id":"https://openalex.org/C137119250","wikidata":"https://www.wikidata.org/wiki/Q1413101","display_name":"Multigrid method","level":3,"score":0.7097436189651489},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6421099305152893},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5505328178405762},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4819655120372772},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.4366661310195923},{"id":"https://openalex.org/C167431342","wikidata":"https://www.wikidata.org/wiki/Q1754327","display_name":"Preconditioner","level":3,"score":0.4232533872127533},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36716169118881226},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.34176719188690186},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33367282152175903},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.3114366829395294},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27249962091445923},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.1340881586074829},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/10943420231217221","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420231217221","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:uni-augsburg.opus-bayern.de:110521","is_oa":false,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/110521","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":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1565416348","https://openalex.org/W1961751213","https://openalex.org/W1980005758","https://openalex.org/W1985144286","https://openalex.org/W2002555321","https://openalex.org/W2018225490","https://openalex.org/W2031149877","https://openalex.org/W2040651749","https://openalex.org/W2053486661","https://openalex.org/W2053572944","https://openalex.org/W2068730714","https://openalex.org/W2078842791","https://openalex.org/W2084073638","https://openalex.org/W2474724963","https://openalex.org/W2597480328","https://openalex.org/W2767520933","https://openalex.org/W2898759154","https://openalex.org/W2943869808","https://openalex.org/W2962978274","https://openalex.org/W2963867113","https://openalex.org/W2969262004","https://openalex.org/W2978939434","https://openalex.org/W2981341148","https://openalex.org/W3000936750","https://openalex.org/W3040786754","https://openalex.org/W3048757510","https://openalex.org/W3099299211","https://openalex.org/W3104266598","https://openalex.org/W3122714673","https://openalex.org/W3130373099","https://openalex.org/W3155036733","https://openalex.org/W3162762987","https://openalex.org/W3167826856","https://openalex.org/W3202306556","https://openalex.org/W3205300732","https://openalex.org/W4210857846","https://openalex.org/W4212813033","https://openalex.org/W4284887185","https://openalex.org/W4285292487","https://openalex.org/W4285586698","https://openalex.org/W4317884298","https://openalex.org/W4378803429"],"related_works":["https://openalex.org/W4389317411","https://openalex.org/W1492522302","https://openalex.org/W2096454229","https://openalex.org/W2042199958","https://openalex.org/W2120298265","https://openalex.org/W2103149966","https://openalex.org/W2177482563","https://openalex.org/W2016008514","https://openalex.org/W2464766188","https://openalex.org/W1537807642"],"abstract_inverted_index":{"This":[0],"contribution":[1],"presents":[2],"data-locality":[3],"optimizations":[4],"of":[5,26,43,49,62,78,87,139,162,198],"the":[6,13,24,44,47,76,84,102,108,115,120,137,155,163,195,211,214],"additive":[7,164],"Schwarz":[8,165],"method":[9,15,166],"(ASM)":[10],"based":[11],"on":[12,17,31,144],"fast-diagonalization":[14],"defined":[16],"overlapping":[18],"cell-centric":[19],"and":[20,83,90,113,148],"vertex-star":[21],"patches":[22],"in":[23,46,74,130],"context":[25,48],"high-order":[27],"matrix-free":[28],"finite-element":[29],"computations":[30],"modern":[32],"CPU-based":[33],"hardware.":[34],"The":[35,58],"developments":[36],"are":[37,124,216],"guided":[38],"by":[39,111,119],"detailed":[40],"performance":[41],"models":[42],"ASM":[45,63,112,187],"Chebyshev":[50,121],"iterations":[51,199],"when":[52],"used":[53],"as":[54,93,181],"smoothers":[55,157],"for":[56,70,105,173,206],"p-multigrid.":[57],"proposed":[59],"efficient":[60,71,133,160],"implementation":[61],"adopts":[64],"concepts":[65],"known":[66],"from":[67],"cell-loop":[68],"infrastructures":[69],"operator":[72,134],"evaluation,":[73],"particular,":[75],"storage":[77],"information":[79],"per":[80,183,192],"geometric":[81],"entity":[82],"cache-friendly":[85],"interleaving":[86],"cell":[88],"loops":[89],"vector":[91,116],"updates":[92,117],"a":[94,140,145],"means":[95],"to":[96,132,202,219],"increase":[97],"data":[98],"locality.":[99],"We":[100],"use":[101],"latter":[103],"concept":[104],"both":[106],"applying":[107],"weights":[109],"required":[110,118],"performing":[114],"iteration,":[122],"which":[123],"memory-bound":[125],"operations":[126],"with":[127,152],"non-negligible":[128],"costs":[129],"comparison":[131],"evaluation.":[135],"Furthermore,":[136],"solution":[138],"scalar":[141],"Poisson":[142],"problem":[143,208],"highly":[146],"anisotropic":[147],"an":[149],"unstructured":[150],"mesh":[151],"p-multigrid":[153],"using":[154],"developed":[156],"indicates":[158],"that":[159],"implementations":[161],"can":[167,200],"outperform":[168],"optimized":[169],"point-Jacobi":[170],"preconditioners":[171],"already":[172],"simple":[174],"problems":[175],"despite":[176],"being":[177],"more":[178],"than":[179],"twice":[180],"expensive":[182],"iteration.":[184],"Even":[185],"though":[186],"introduces":[188],"additional":[189],"communication":[190],"steps":[191],"smoother":[193],"application,":[194],"reduced":[196],"number":[197],"lead":[201],"improved":[203],"parallel":[204],"scalability":[205],"intermediate":[207],"sizes.":[209],"At":[210],"scaling":[212],"limit,":[213],"results":[215],"inconclusive":[217],"due":[218],"these":[220],"two":[221],"opposing":[222],"effects.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}