{"id":"https://openalex.org/W4212963642","doi":"https://doi.org/10.1137/21m1414644","title":"MG-FIM: A Multi-GPU Fast Iterative Method Using Adaptive Domain Decomposition","display_name":"MG-FIM: A Multi-GPU Fast Iterative Method Using Adaptive Domain Decomposition","publication_year":2022,"publication_date":"2022-02-01","ids":{"openalex":"https://openalex.org/W4212963642","doi":"https://doi.org/10.1137/21m1414644"},"language":"en","primary_location":{"id":"doi:10.1137/21m1414644","is_oa":false,"landing_page_url":"https://doi.org/10.1137/21m1414644","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","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/A5055756152","display_name":"Sumin Hong","orcid":"https://orcid.org/0000-0002-3321-2072"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sumin Hong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065002811","display_name":"Ganghee Jang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ganghee Jang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5025485089","display_name":"Won\u2010Ki Jeong","orcid":"https://orcid.org/0000-0002-9393-6451"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Won-Ki Jeong","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9393-6451","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1172,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.26618705,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"44","issue":"1","first_page":"C54","last_page":"C76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9916999936103821,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.851432204246521},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8337175250053406},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7290486693382263},{"id":"https://openalex.org/keywords/domain-decomposition-methods","display_name":"Domain decomposition methods","score":0.612986147403717},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5425830483436584},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5125886797904968},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.49590644240379333},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4598380923271179},{"id":"https://openalex.org/keywords/eikonal-equation","display_name":"Eikonal equation","score":0.43374770879745483},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.42436864972114563},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4220653772354126},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.1973610520362854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1030268669128418},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.0718376636505127}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.851432204246521},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8337175250053406},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7290486693382263},{"id":"https://openalex.org/C198880260","wikidata":"https://www.wikidata.org/wiki/Q5289813","display_name":"Domain decomposition methods","level":3,"score":0.612986147403717},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5425830483436584},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5125886797904968},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.49590644240379333},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4598380923271179},{"id":"https://openalex.org/C40375134","wikidata":"https://www.wikidata.org/wiki/Q1303846","display_name":"Eikonal equation","level":2,"score":0.43374770879745483},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.42436864972114563},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4220653772354126},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.1973610520362854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1030268669128418},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.0718376636505127},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"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/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/21m1414644","is_oa":false,"landing_page_url":"https://doi.org/10.1137/21m1414644","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W848723816","https://openalex.org/W1535896976","https://openalex.org/W1581532933","https://openalex.org/W1970390879","https://openalex.org/W1991055573","https://openalex.org/W1999244633","https://openalex.org/W2012872284","https://openalex.org/W2021092589","https://openalex.org/W2049391017","https://openalex.org/W2089853005","https://openalex.org/W2113566579","https://openalex.org/W2132202988","https://openalex.org/W2139822104","https://openalex.org/W2139972929","https://openalex.org/W2141409037","https://openalex.org/W2156511674","https://openalex.org/W2159786075","https://openalex.org/W2165221050","https://openalex.org/W2466975439","https://openalex.org/W2472583304","https://openalex.org/W2801227182","https://openalex.org/W2963823948","https://openalex.org/W2974193147","https://openalex.org/W3111357769","https://openalex.org/W3132680633","https://openalex.org/W3161445736"],"related_works":["https://openalex.org/W2071296827","https://openalex.org/W2030707850","https://openalex.org/W2012928711","https://openalex.org/W2294001614","https://openalex.org/W4288452443","https://openalex.org/W1827514603","https://openalex.org/W3165899388","https://openalex.org/W3013198907","https://openalex.org/W1983385707","https://openalex.org/W4231763094"],"abstract_inverted_index":{"Applying":[0],"the":[1,67,80,136,162],"latest":[2],"parallel":[3,159],"computing":[4],"technology":[5],"has":[6],"become":[7],"a":[8,55,93,140],"recent":[9,16],"trend":[10],"in":[11,43,135,168],"Eikonal":[12,23,34],"equation":[13],"solvers.":[14],"Many":[15],"studies":[17],"have":[18],"focused":[19],"on":[20,72],"parallelization":[21,138],"of":[22,45,66,161],"solvers":[24,35],"for":[25,111,151],"multithreaded":[26],"CPUs":[27],"or":[28],"single":[29],"GPU":[30,86,112,119],"systems.":[31],"However,":[32],"multi-GPU":[33],"are":[36],"largely":[37],"underresearched":[38],"owing":[39],"to":[40,61,84,87,97,149],"their":[41],"complexity":[42],"terms":[44],"data":[46,123],"and":[47,91,107,118,121],"task":[48],"management.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,130],"propose":[54,104],"novel":[56],"adaptive":[57],"domain":[58,82],"decomposition":[59,142],"method":[60,71,77,146,164],"realize":[62],"an":[63,166],"efficient":[64,158],"implementation":[65,160],"block-based":[68],"fast":[69],"iterative":[70],"multiple":[73,126],"GPUs.":[74,153],"The":[75,144],"proposed":[76,145,163],"progressively":[78],"expands":[79],"computational":[81],"assigned":[83],"each":[85],"maximize":[88],"load":[89],"balancing":[90],"employs":[92],"locality-aware":[94],"clustering":[95],"algorithm":[96],"minimize":[98],"inter-GPU":[99,122],"communication":[100],"overhead.":[101],"We":[102,154],"also":[103],"various":[105,172],"low-":[106],"high-level":[108],"optimization":[109],"techniques":[110],"computing,":[113],"such":[114],"as":[115],"overlapping":[116],"CPU":[117],"computation":[120],"transfer":[124],"using":[125,139],"CUDA":[127],"streams.":[128],"Thus,":[129],"effectively":[131],"circumvent":[132],"performance":[133,170],"issues":[134],"na\u00efve":[137],"regular":[141],"method.":[143],"scales":[147],"up":[148],"6.6x":[150],"eight":[152],"demonstrate":[155],"that":[156],"our":[157],"achieves":[165],"improvement":[167],"runtime":[169],"under":[171],"experimental":[173],"setups.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}