{"id":"https://openalex.org/W2520594231","doi":"https://doi.org/10.1145/2938615.2938621","title":"On rounding error resilience, maximal attainable accuracy and parallel performance of the pipelined Conjugate Gradients method for large-scale linear systems in PETSc","display_name":"On rounding error resilience, maximal attainable accuracy and parallel performance of the pipelined Conjugate Gradients method for large-scale linear systems in PETSc","publication_year":2016,"publication_date":"2016-04-26","ids":{"openalex":"https://openalex.org/W2520594231","doi":"https://doi.org/10.1145/2938615.2938621","mag":"2520594231"},"language":"en","primary_location":{"id":"doi:10.1145/2938615.2938621","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2938615.2938621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Exascale Applications and Software Conference 2016","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-01734422","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087560630","display_name":"Siegfried Cools","orcid":"https://orcid.org/0000-0001-7065-4729"},"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/I4210111370","display_name":"ZNA Middelheim Hospital","ror":"https://ror.org/01z5jvj74","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I4210111370"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Siegfried Cools","raw_affiliation_strings":["Applied Mathematics Group, University of Antwerp, Middelheimlaan, Antwerp, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Mathematics Group, University of Antwerp, Middelheimlaan, Antwerp, Belgium","institution_ids":["https://openalex.org/I4210111370","https://openalex.org/I149213910"]}]},{"author_position":"middle","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/I4210111370","display_name":"ZNA Middelheim Hospital","ror":"https://ror.org/01z5jvj74","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I4210111370"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Wim Vanroose","raw_affiliation_strings":["Applied Mathematics Group, University of Antwerp, Middelheimlaan, Antwerp, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Mathematics Group, University of Antwerp, Middelheimlaan, Antwerp, Belgium","institution_ids":["https://openalex.org/I4210111370","https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064926486","display_name":"E. Fatih Yetkin","orcid":"https://orcid.org/0000-0003-1115-4454"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210131512","display_name":"Centre Inria de l'universit\u00e9 de Bordeaux","ror":"https://ror.org/03tjcj052","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210131512"]},{"id":"https://openalex.org/I86122600","display_name":"Numerical Algorithms Group (United Kingdom)","ror":"https://ror.org/04pcnys31","country_code":"GB","type":"company","lineage":["https://openalex.org/I86122600"]}],"countries":["FR","GB"],"is_corresponding":false,"raw_author_name":"Emrullah Fatih Yetkin","raw_affiliation_strings":["HiePACS, INRIA Bordeaux - Sud-Ouest, Talence, France","High-End Parallel Algorithms for Challenging Numerical Simulations"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HiePACS, INRIA Bordeaux - Sud-Ouest, Talence, France","institution_ids":["https://openalex.org/I4210131512","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"High-End Parallel Algorithms for Challenging Numerical Simulations","institution_ids":["https://openalex.org/I86122600"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074132178","display_name":"Emmanuel Agullo","orcid":"https://orcid.org/0000-0003-0655-6934"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210131512","display_name":"Centre Inria de l'universit\u00e9 de Bordeaux","ror":"https://ror.org/03tjcj052","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210131512"]},{"id":"https://openalex.org/I86122600","display_name":"Numerical Algorithms Group (United Kingdom)","ror":"https://ror.org/04pcnys31","country_code":"GB","type":"company","lineage":["https://openalex.org/I86122600"]}],"countries":["FR","GB"],"is_corresponding":false,"raw_author_name":"Emmanuel Agullo","raw_affiliation_strings":["HiePACS, INRIA Bordeaux - Sud-Ouest, Talence, France","High-End Parallel Algorithms for Challenging Numerical Simulations"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HiePACS, INRIA Bordeaux - Sud-Ouest, Talence, France","institution_ids":["https://openalex.org/I4210131512","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"High-End Parallel Algorithms for Challenging Numerical Simulations","institution_ids":["https://openalex.org/I86122600"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060047917","display_name":"Luc Giraud","orcid":"https://orcid.org/0000-0002-7062-7672"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210131512","display_name":"Centre Inria de l'universit\u00e9 de Bordeaux","ror":"https://ror.org/03tjcj052","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210131512"]},{"id":"https://openalex.org/I86122600","display_name":"Numerical Algorithms Group (United Kingdom)","ror":"https://ror.org/04pcnys31","country_code":"GB","type":"company","lineage":["https://openalex.org/I86122600"]}],"countries":["FR","GB"],"is_corresponding":false,"raw_author_name":"Luc Giraud","raw_affiliation_strings":["HiePACS, INRIA Bordeaux - Sud-Ouest, Talence, France","High-End Parallel Algorithms for Challenging Numerical Simulations"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HiePACS, INRIA Bordeaux - Sud-Ouest, Talence, France","institution_ids":["https://openalex.org/I4210131512","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"High-End Parallel Algorithms for Challenging Numerical Simulations","institution_ids":["https://openalex.org/I86122600"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1627,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.88847442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"13","issue":null,"first_page":"1","last_page":"10"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983999729156494,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9939000010490417,"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/rounding","display_name":"Rounding","score":0.8624298572540283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.825136125087738},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7559536695480347},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.6362630724906921},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5689474940299988},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5579906702041626},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5240257382392883},{"id":"https://openalex.org/keywords/krylov-subspace","display_name":"Krylov subspace","score":0.46616131067276},{"id":"https://openalex.org/keywords/linear-scale","display_name":"Linear scale","score":0.4584403336048126},{"id":"https://openalex.org/keywords/round-off-error","display_name":"Round-off error","score":0.44000864028930664},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.4336357116699219},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.4301034212112427},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.4133397936820984},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38961029052734375},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.2673211097717285},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.1311292052268982}],"concepts":[{"id":"https://openalex.org/C136625980","wikidata":"https://www.wikidata.org/wiki/Q663208","display_name":"Rounding","level":2,"score":0.8624298572540283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.825136125087738},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7559536695480347},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.6362630724906921},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5689474940299988},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5579906702041626},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5240257382392883},{"id":"https://openalex.org/C147060835","wikidata":"https://www.wikidata.org/wiki/Q1757151","display_name":"Krylov subspace","level":3,"score":0.46616131067276},{"id":"https://openalex.org/C170122806","wikidata":"https://www.wikidata.org/wiki/Q1914828","display_name":"Linear scale","level":2,"score":0.4584403336048126},{"id":"https://openalex.org/C61005703","wikidata":"https://www.wikidata.org/wiki/Q2145211","display_name":"Round-off error","level":2,"score":0.44000864028930664},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.4336357116699219},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.4301034212112427},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.4133397936820984},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38961029052734375},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.2673211097717285},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.1311292052268982},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2938615.2938621","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2938615.2938621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Exascale Applications and Software Conference 2016","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01734422v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01734422","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"EASC 2016 - Exascale Applications and Software Conference, Apr 2016, Stockholm, Sweden. pp.1-10, &#x27E8;10.1145/2938615.2938621&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01734422v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01734422","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"EASC 2016 - Exascale Applications and Software Conference, Apr 2016, Stockholm, Sweden. pp.1-10, &#x27E8;10.1145/2938615.2938621&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G4138220520","display_name":null,"funder_award_id":"610741","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1507702133","https://openalex.org/W1575701986","https://openalex.org/W1980677368","https://openalex.org/W1983609845","https://openalex.org/W2002054778","https://openalex.org/W2041792040","https://openalex.org/W2060710554","https://openalex.org/W2066692739","https://openalex.org/W2075351838","https://openalex.org/W2080225225","https://openalex.org/W2096714979","https://openalex.org/W2106833662","https://openalex.org/W2316564661","https://openalex.org/W2509792706","https://openalex.org/W2611638643","https://openalex.org/W2736042498"],"related_works":["https://openalex.org/W2475524688","https://openalex.org/W2739740241","https://openalex.org/W2085105049","https://openalex.org/W2592417500","https://openalex.org/W1974923383","https://openalex.org/W2526069705","https://openalex.org/W2024016913","https://openalex.org/W2019153376","https://openalex.org/W2796552083","https://openalex.org/W2949197156"],"abstract_inverted_index":{"Pipelined":[0],"Krylov":[1,11],"solvers":[2],"typically":[3],"display":[4],"better":[5],"strong":[6],"scaling":[7],"compared":[8],"to":[9,86,123],"standard":[10],"methods":[12,36],"for":[13,65],"large":[14],"linear":[15],"systems.":[16],"The":[17],"synchronization":[18],"bottleneck":[19],"is":[20,76,84,120],"mitigated":[21],"by":[22,133],"overlapping":[23],"time-consuming":[24],"global":[25],"communications":[26],"with":[27,116],"computations.":[28],"To":[29],"achieve":[30],"this":[31],"hiding":[32],"of":[33,59,68,90],"communication,":[34],"pipelined":[35,60,113],"feature":[37],"additional":[38],"recurrence":[39],"relations":[40],"on":[41,56,93,104],"auxiliary":[42],"variables.":[43],"This":[44],"paper":[45],"analyzes":[46],"why":[47],"rounding":[48,69,91,124],"error":[49],"effects":[50],"have":[51],"a":[52],"significantly":[53],"larger":[54],"impact":[55],"the":[57,66,72,88,94,112,128],"accuracy":[58],"algorithms.":[61],"An":[62],"algebraic":[63],"model":[64],"accumulation":[67],"errors":[70,92,125],"in":[71,102],"(pipelined)":[73],"CG":[74,114],"algorithm":[75],"derived.":[77],"Furthermore,":[78],"an":[79,105],"automated":[80,117],"residual":[81,118],"replacement":[82,119],"strategy":[83],"proposed":[85],"reduce":[87],"effect":[89],"final":[95],"solution.":[96],"MPI":[97],"parallel":[98,130],"performance":[99,131],"tests":[100],"implemented":[101],"PETSc":[103],"Intel":[106],"Xeon":[107],"X5660":[108],"cluster":[109],"show":[110],"that":[111],"method":[115],"more":[121],"resilient":[122],"while":[126],"maintaining":[127],"efficient":[129],"obtained":[132],"pipelining.":[134]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
