{"id":"https://openalex.org/W2080225225","doi":"https://doi.org/10.1137/12086563x","title":"Hiding Global Communication Latency in the GMRES Algorithm on Massively Parallel Machines","display_name":"Hiding Global Communication Latency in the GMRES Algorithm on Massively Parallel Machines","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2080225225","doi":"https://doi.org/10.1137/12086563x","mag":"2080225225"},"language":"en","primary_location":{"id":"doi:10.1137/12086563x","is_oa":false,"landing_page_url":"https://doi.org/10.1137/12086563x","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":true,"oa_status":"green","oa_url":"https://lirias.kuleuven.be/handle/123456789/629721","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043775275","display_name":"Pieter Ghysels","orcid":"https://orcid.org/0000-0002-5981-5234"},"institutions":[{"id":"https://openalex.org/I4210114974","display_name":"IMEC","ror":"https://ror.org/02kcbn207","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I4210114974"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"P. Ghysels","raw_affiliation_strings":["Intel ExaScience Lab -Kapeldreef 75, B-3001 Leuven -Belgium \u2021 Imec vzw -Kapeldreef 75, B-3001 Leuven -Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel ExaScience Lab -Kapeldreef 75, B-3001 Leuven -Belgium \u2021 Imec vzw -Kapeldreef 75, B-3001 Leuven -Belgium","institution_ids":["https://openalex.org/I4210114974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004692639","display_name":"Thomas J. Ashby","orcid":"https://orcid.org/0000-0002-9259-6475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T. J. Ashby","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079388991","display_name":"Karl Meerbergen","orcid":"https://orcid.org/0000-0002-1508-0248"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]},{"id":"https://openalex.org/I4210114974","display_name":"IMEC","ror":"https://ror.org/02kcbn207","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I4210114974"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"K. Meerbergen","raw_affiliation_strings":["Intel ExaScience Lab -Kapeldreef 75, B-3001 Leuven -Belgium \u2021 Imec vzw -Kapeldreef 75, B-3001 Leuven -Belgium","University of Antwerp -Department of Mathematics and Computer Science, Middelheimlaan 1, B-2020 Antwerp -Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel ExaScience Lab -Kapeldreef 75, B-3001 Leuven -Belgium \u2021 Imec vzw -Kapeldreef 75, B-3001 Leuven -Belgium","institution_ids":["https://openalex.org/I4210114974"]},{"raw_affiliation_string":"University of Antwerp -Department of Mathematics and Computer Science, Middelheimlaan 1, B-2020 Antwerp -Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064358152","display_name":"Wim Vanroose","orcid":"https://orcid.org/0000-0001-8349-1391"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]},{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"W. Vanroose","raw_affiliation_strings":["University of Antwerp -Department of Mathematics and Computer Science, Middelheimlaan 1, B-2020 Antwerp -Belgium","KU Leuven -Department of Computer Science, Celestijnenlaan 200A -bus 2402, B-3001 Leuven -Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Antwerp -Department of Mathematics and Computer Science, Middelheimlaan 1, B-2020 Antwerp -Belgium","institution_ids":["https://openalex.org/I149213910"]},{"raw_affiliation_string":"KU Leuven -Department of Computer Science, Celestijnenlaan 200A -bus 2402, B-3001 Leuven -Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043775275"],"corresponding_institution_ids":["https://openalex.org/I4210114974"],"apc_list":null,"apc_paid":null,"fwci":16.3852,"has_fulltext":false,"cited_by_count":127,"citation_normalized_percentile":{"value":0.99420299,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"35","issue":"1","first_page":"C48","last_page":"C71"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9998999834060669,"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":0.9998999834060669,"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/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.996999979019165,"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/generalized-minimal-residual-method","display_name":"Generalized minimal residual method","score":0.7893291711807251},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7285842895507812},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.6148080825805664},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6037114262580872},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5465086698532104},{"id":"https://openalex.org/keywords/orthogonalization","display_name":"Orthogonalization","score":0.5140784978866577},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4826379418373108},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.4309028089046478},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.42717570066452026},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42664164304733276},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.3210493326187134},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10339391231536865}],"concepts":[{"id":"https://openalex.org/C155332342","wikidata":"https://www.wikidata.org/wiki/Q1432976","display_name":"Generalized minimal residual method","level":3,"score":0.7893291711807251},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7285842895507812},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.6148080825805664},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6037114262580872},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5465086698532104},{"id":"https://openalex.org/C47559304","wikidata":"https://www.wikidata.org/wiki/Q1702189","display_name":"Orthogonalization","level":2,"score":0.5140784978866577},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4826379418373108},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.4309028089046478},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.42717570066452026},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42664164304733276},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.3210493326187134},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10339391231536865},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1137/12086563x","is_oa":false,"landing_page_url":"https://doi.org/10.1137/12086563x","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"},{"id":"pmh:c:irua:105080","is_oa":false,"landing_page_url":"https://hdl.handle.net/10067/1050800151162165141","pdf_url":null,"source":{"id":"https://openalex.org/S4377196495","display_name":"Anet (University of Antwerp)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149213910","host_organization_name":"University of Antwerp","host_organization_lineage":["https://openalex.org/I149213910"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.474.3327","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.474.3327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://twna.ua.ac.be/sites/twna.ua.ac.be/files/latency_gmres.pdf","raw_type":"text"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/629721","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/629721","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"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":"SIAM Journal on Scientific Computing, vol. 35 (1), Art.No. 1, (C48-C71)","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/629721","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/629721","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"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":"SIAM Journal on Scientific Computing, vol. 35 (1), Art.No. 1, (C48-C71)","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W70545388","https://openalex.org/W98259598","https://openalex.org/W308651360","https://openalex.org/W1507702133","https://openalex.org/W1513772264","https://openalex.org/W1547502462","https://openalex.org/W1605603992","https://openalex.org/W1813030236","https://openalex.org/W1825532946","https://openalex.org/W1907157228","https://openalex.org/W1976125183","https://openalex.org/W1984284159","https://openalex.org/W1997245285","https://openalex.org/W2016279572","https://openalex.org/W2026991672","https://openalex.org/W2029023406","https://openalex.org/W2041876368","https://openalex.org/W2052087587","https://openalex.org/W2062011830","https://openalex.org/W2066692739","https://openalex.org/W2085752304","https://openalex.org/W2089735355","https://openalex.org/W2095222360","https://openalex.org/W2104992285","https://openalex.org/W2105745683","https://openalex.org/W2127022449","https://openalex.org/W2131613942","https://openalex.org/W2140153041","https://openalex.org/W2141700117","https://openalex.org/W2145194992","https://openalex.org/W2161708191","https://openalex.org/W2170902912","https://openalex.org/W2185321367","https://openalex.org/W2208101261","https://openalex.org/W2534577245","https://openalex.org/W2919260387"],"related_works":["https://openalex.org/W2002097440","https://openalex.org/W2000690703","https://openalex.org/W3152060313","https://openalex.org/W2484832770","https://openalex.org/W2103271089","https://openalex.org/W2028770117","https://openalex.org/W1995841910","https://openalex.org/W1990351032","https://openalex.org/W2127147063","https://openalex.org/W1596285621"],"abstract_inverted_index":{"In":[0,50],"the":[1,7,20,55,86,100,117,131,137,162,176],"generalized":[2],"minimal":[3],"residual":[4],"method":[5],"(GMRES),":[6],"global":[8,42,48,61,66,90,107],"all-to-all":[9],"communication":[10,67,101],"required":[11],"in":[12,84],"each":[13],"iteration":[14],"for":[15],"orthogonalization":[16],"and":[17,37,75,111,141],"normalization":[18],"of":[19,57,80,88,119,161],"Krylov":[21],"base":[22],"vectors":[23],"is":[24,82,92,109,113,172],"becoming":[25],"a":[26,89,155],"performance":[27,177],"bottleneck":[28],"on":[29,154],"massively":[30],"parallel":[31,152],"machines.":[32],"Long":[33],"latencies,":[34],"system":[35],"noise,":[36],"load":[38],"imbalance":[39],"cause":[40],"these":[41,65],"reductions":[43,62],"to":[44,63,130,166,174,178],"become":[45],"very":[46],"costly":[47],"synchronizations.":[49],"this":[51],"work,":[52],"we":[53],"propose":[54],"use":[56],"nonblocking":[58],"or":[59,96,147],"asynchronous":[60],"hide":[64],"latencies":[68],"by":[69,135,144],"overlapping":[70],"them":[71],"with":[72],"other":[73],"communications":[74],"calculations.":[76],"A":[77],"pipelined":[78,163],"variation":[79],"GMRES":[81],"presented":[83],"which":[85],"result":[87],"reduction":[91],"used":[93,173],"only":[94],"one":[95],"more":[97],"iterations":[98],"after":[99],"phase":[102],"has":[103],"started.":[104],"This":[105],"way,":[106],"synchronization":[108],"relaxed":[110],"scalability":[112],"much":[114],"improved":[115],"at":[116],"expense":[118],"some":[120],"extra":[121],"computations.":[122],"The":[123],"numerical":[124],"instabilities":[125],"that":[126],"inevitably":[127],"arise":[128],"due":[129],"typical":[132],"monomial":[133],"basis":[134],"powering":[136],"matrix":[138],"are":[139],"reduced":[140],"often":[142],"annihilated":[143],"using":[145],"Newton":[146],"Chebyshev":[148],"bases":[149],"instead.":[150],"Our":[151],"experiments":[153],"medium-sized":[156],"cluster":[157],"show":[158],"significant":[159],"speedups":[160],"solvers":[164],"compared":[165],"standard":[167],"GMRES.":[168],"An":[169],"analytical":[170],"model":[171],"extrapolate":[175],"future":[179],"exascale":[180],"systems.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":20},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":2}],"updated_date":"2026-05-17T08:19:37.847499","created_date":"2025-10-10T00:00:00"}