{"id":"https://openalex.org/W3120677723","doi":"https://doi.org/10.1145/3432261.3432270","title":"Conjugate Gradient Solvers with High Accuracy and Bit-wise Reproducibility between CPU and GPU using Ozaki scheme","display_name":"Conjugate Gradient Solvers with High Accuracy and Bit-wise Reproducibility between CPU and GPU using Ozaki scheme","publication_year":2021,"publication_date":"2021-01-14","ids":{"openalex":"https://openalex.org/W3120677723","doi":"https://doi.org/10.1145/3432261.3432270","mag":"3120677723"},"language":"en","primary_location":{"id":"doi:10.1145/3432261.3432270","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3432261.3432270","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3432261.3432270","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Conference on High Performance Computing in Asia-Pacific Region","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3432261.3432270","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035972892","display_name":"Daichi Mukunoki","orcid":"https://orcid.org/0000-0002-0051-6811"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daichi Mukunoki","raw_affiliation_strings":["RIKEN Center for Computational Science, Hyogo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Hyogo","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042608261","display_name":"Katsuhisa Ozaki","orcid":"https://orcid.org/0000-0003-0431-6232"},"institutions":[{"id":"https://openalex.org/I171481255","display_name":"Shibaura Institute of Technology","ror":"https://ror.org/020wjcq07","country_code":"JP","type":"education","lineage":["https://openalex.org/I171481255"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsuhisa Ozaki","raw_affiliation_strings":["Shibaura Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shibaura Institute of Technology, Japan","institution_ids":["https://openalex.org/I171481255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028381863","display_name":"Takeshi Ogita","orcid":"https://orcid.org/0000-0002-9346-2452"},"institutions":[{"id":"https://openalex.org/I20560788","display_name":"Tokyo Woman's Christian University","ror":"https://ror.org/03mb27p64","country_code":"JP","type":"education","lineage":["https://openalex.org/I20560788"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Ogita","raw_affiliation_strings":["Tokyo Woman\u2019s Christian University, Japan","Tokyo Woman's Christian University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Woman\u2019s Christian University, Japan","institution_ids":["https://openalex.org/I20560788"]},{"raw_affiliation_string":"Tokyo Woman's Christian University, Japan","institution_ids":["https://openalex.org/I20560788"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018682944","display_name":"Roman Iakymchuk","orcid":"https://orcid.org/0000-0003-2414-700X"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Roman Iakymchuk","raw_affiliation_strings":["Sorbonne University, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne University, France","institution_ids":["https://openalex.org/I39804081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6346,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80151455,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"100","last_page":"109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9995999932289124,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9995999932289124,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9987999796867371,"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":0.9940999746322632,"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/computer-science","display_name":"Computer science","score":0.8192914724349976},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.642326831817627},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6400489807128906},{"id":"https://openalex.org/keywords/krylov-subspace","display_name":"Krylov subspace","score":0.635718822479248},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6299226880073547},{"id":"https://openalex.org/keywords/rounding","display_name":"Rounding","score":0.6045644283294678},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5354848504066467},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.5269913077354431},{"id":"https://openalex.org/keywords/dot-product","display_name":"Dot product","score":0.5224891304969788},{"id":"https://openalex.org/keywords/generalized-minimal-residual-method","display_name":"Generalized minimal residual method","score":0.49072563648223877},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47921258211135864},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.4383629858493805},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4269601106643677},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.27291572093963623},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16546732187271118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8192914724349976},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.642326831817627},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6400489807128906},{"id":"https://openalex.org/C147060835","wikidata":"https://www.wikidata.org/wiki/Q1757151","display_name":"Krylov subspace","level":3,"score":0.635718822479248},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6299226880073547},{"id":"https://openalex.org/C136625980","wikidata":"https://www.wikidata.org/wiki/Q663208","display_name":"Rounding","level":2,"score":0.6045644283294678},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5354848504066467},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.5269913077354431},{"id":"https://openalex.org/C32900221","wikidata":"https://www.wikidata.org/wiki/Q181365","display_name":"Dot product","level":2,"score":0.5224891304969788},{"id":"https://openalex.org/C155332342","wikidata":"https://www.wikidata.org/wiki/Q1432976","display_name":"Generalized minimal residual method","level":3,"score":0.49072563648223877},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47921258211135864},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.4383629858493805},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4269601106643677},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.27291572093963623},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16546732187271118},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/3432261.3432270","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3432261.3432270","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3432261.3432270","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Conference on High Performance Computing in Asia-Pacific Region","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-02986873v1","is_oa":true,"landing_page_url":"https://hal.science/hal-02986873","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":"2020","raw_type":"info:eu-repo/semantics/preprint"},{"id":"pmh:oai:fraunhofer.de:N-621205","is_oa":true,"landing_page_url":"http://publica.fraunhofer.de/documents/N-621205.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"Fraunhofer ITWM","raw_type":"report"},{"id":"pmh:oai:fraunhofer.de:N-637583","is_oa":true,"landing_page_url":"http://publica.fraunhofer.de/documents/N-637583.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"Fraunhofer ITWM","raw_type":"Conference Paper"},{"id":"pmh:oai:null:publica/411749","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/411749","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/300713","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/300713","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"report"}],"best_oa_location":{"id":"doi:10.1145/3432261.3432270","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3432261.3432270","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3432261.3432270","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Conference on High Performance Computing in Asia-Pacific Region","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4009883370","display_name":"Development of accurate and reproducible matrix computation library for massively parallel environments","funder_award_id":"19K20286","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G495187929","display_name":null,"funder_award_id":"EU\u2010H2020","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G5136527164","display_name":null,"funder_award_id":"842528","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320323954","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3120677723.pdf","grobid_xml":"https://content.openalex.org/works/W3120677723.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1451071356","https://openalex.org/W1953299766","https://openalex.org/W1969213662","https://openalex.org/W1975602595","https://openalex.org/W2002064155","https://openalex.org/W2006705329","https://openalex.org/W2035080386","https://openalex.org/W2073327480","https://openalex.org/W2079232854","https://openalex.org/W2103657170","https://openalex.org/W2104281151","https://openalex.org/W2283035009","https://openalex.org/W2288982856","https://openalex.org/W2959261637","https://openalex.org/W2997514602","https://openalex.org/W3012028217","https://openalex.org/W3034986667","https://openalex.org/W3036888600","https://openalex.org/W3098056654","https://openalex.org/W3152567310"],"related_works":["https://openalex.org/W2042846224","https://openalex.org/W2942315554","https://openalex.org/W2358905935","https://openalex.org/W2102729529","https://openalex.org/W2009694692","https://openalex.org/W2124576060","https://openalex.org/W1544024826","https://openalex.org/W4281636333","https://openalex.org/W4297795876","https://openalex.org/W3090071302"],"abstract_inverted_index":{"On":[0],"Krylov":[1],"subspace":[2],"methods":[3],"such":[4],"as":[5,119,121],"the":[6,11,21,34,38,41,48,51,54,65,79,109,115,136,154,157,179,194],"Conjugate":[7],"Gradient":[8],"(CG)":[9],"method,":[10,91],"number":[12],"of":[13,23,40,53,78,140,159,164,181],"iterations":[14],"until":[15],"convergence":[16,55],"may":[17,56],"increase":[18],"due":[19],"to":[20],"loss":[22],"computational":[24,61,126],"accuracy":[25,165],"caused":[26],"by":[27],"rounding":[28],"errors":[29],"in":[30,59,143,162],"floating-point":[31],"computations.":[32],"At":[33],"same":[35,66],"time,":[36],"because":[37],"order":[39],"computation":[42,118],"is":[43],"nondeterministic":[44],"on":[45,83,97,171,193,201],"parallel":[46],"computation,":[47],"result":[49],"and":[50,75,86,149,156,166,168,174,188],"behavior":[52],"be":[57],"nonidentical":[58,144],"different":[60,125,147],"environments,":[62],"even":[63],"for":[64],"input.":[67],"In":[68,89,128],"this":[69,129],"study,":[70],"we":[71,131,177],"present":[72],"an":[73,185],"accurate":[74,187],"reproducible":[76,189],"implementation":[77,139,191],"unpreconditioned":[80],"CG":[81,141,190],"method":[82,183],"x86":[84],"CPUs":[85,148,173],"NVIDIA":[87],"GPUs.":[88,150,175],"our":[90,160,182],"while":[92],"all":[93,99],"variables":[94],"are":[95,106],"stored":[96],"FP64,":[98],"inner":[100],"product":[101],"operations":[102],"(including":[103],"matrix-vector":[104],"multiplications)":[105],"performed":[107],"using":[108],"Ozaki":[110],"scheme.":[111],"The":[112],"scheme":[113],"delivers":[114],"correctly":[116],"rounded":[117],"well":[120],"bit-level":[122],"reproducibility":[123,167],"among":[124],"environments.":[127],"paper,":[130],"show":[132],"some":[133],"examples":[134],"where":[135],"standard":[137],"FP64":[138],"results":[142,145],"across":[146],"We":[151],"then":[152],"demonstrate":[153],"applicability":[155],"effectiveness":[158],"approach":[161],"terms":[163],"their":[169],"performance":[170,180],"both":[172],"Furthermore,":[176],"compare":[178],"against":[184],"existing":[186],"based":[192],"Exact":[195],"Basic":[196],"Linear":[197],"Algebra":[198],"Subprograms":[199],"(ExBLAS)":[200],"CPUs.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}