{"id":"https://openalex.org/W3176827258","doi":"https://doi.org/10.1109/tpds.2021.3090757","title":"Accelerating Restarted GMRES With Mixed Precision Arithmetic","display_name":"Accelerating Restarted GMRES With Mixed Precision Arithmetic","publication_year":2021,"publication_date":"2021-06-22","ids":{"openalex":"https://openalex.org/W3176827258","doi":"https://doi.org/10.1109/tpds.2021.3090757","mag":"3176827258"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2021.3090757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3090757","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","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/A5044449337","display_name":"Neil Lindquist","orcid":"https://orcid.org/0000-0001-9404-3121"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Neil Lindquist","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA"],"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073990539","display_name":"Piotr \u0141uszczek","orcid":"https://orcid.org/0000-0002-0089-6965"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr Luszczek","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA"],"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]},{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","Oak Ridge National Laboratory, Oak Ridge, TN, USA","University of Manchester, Manchester, U.K"],"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"University of Manchester, Manchester, U.K","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044449337"],"corresponding_institution_ids":["https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":2.5155,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.90623995,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"33","issue":"4","first_page":"1027","last_page":"1037"},"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":0.9961000084877014,"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":0.9847999811172485,"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":0.9508098363876343},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.7063599824905396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7005339860916138},{"id":"https://openalex.org/keywords/preconditioner","display_name":"Preconditioner","score":0.6910912990570068},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.6384278535842896},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5146547555923462},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4891557991504669},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.4832109212875366},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46365341544151306},{"id":"https://openalex.org/keywords/incomplete-lu-factorization","display_name":"Incomplete LU factorization","score":0.45596784353256226},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4364740252494812},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4348962604999542},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.42869558930397034},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.38197100162506104},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33363550901412964},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.32644250988960266},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30897751450538635},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.23831814527511597},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.08258756995201111},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.06873154640197754}],"concepts":[{"id":"https://openalex.org/C155332342","wikidata":"https://www.wikidata.org/wiki/Q1432976","display_name":"Generalized minimal residual method","level":3,"score":0.9508098363876343},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.7063599824905396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7005339860916138},{"id":"https://openalex.org/C167431342","wikidata":"https://www.wikidata.org/wiki/Q1754327","display_name":"Preconditioner","level":3,"score":0.6910912990570068},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.6384278535842896},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5146547555923462},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4891557991504669},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.4832109212875366},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46365341544151306},{"id":"https://openalex.org/C134978465","wikidata":"https://www.wikidata.org/wiki/Q1654069","display_name":"Incomplete LU factorization","level":4,"score":0.45596784353256226},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4364740252494812},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4348962604999542},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.42869558930397034},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.38197100162506104},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33363550901412964},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32644250988960266},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30897751450538635},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.23831814527511597},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.08258756995201111},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.06873154640197754},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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":1,"locations":[{"id":"doi:10.1109/tpds.2021.3090757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3090757","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3221691958","display_name":null,"funder_award_id":"4000123266","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"},{"id":"https://openalex.org/G4374624133","display_name":null,"funder_award_id":"MSE E01-1315-038","funder_id":"https://openalex.org/F4320309541","funder_display_name":"University of Tennessee"},{"id":"https://openalex.org/G8557420397","display_name":null,"funder_award_id":"2004541","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309541","display_name":"University of Tennessee","ror":"https://ror.org/00xzqjh13"},{"id":"https://openalex.org/F4320316892","display_name":"UT-Battelle","ror":"https://ror.org/04nza6677"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W101236918","https://openalex.org/W1506342804","https://openalex.org/W1940881156","https://openalex.org/W1966287322","https://openalex.org/W1975818677","https://openalex.org/W1977146902","https://openalex.org/W1984840642","https://openalex.org/W2005498993","https://openalex.org/W2020804487","https://openalex.org/W2035080386","https://openalex.org/W2037785139","https://openalex.org/W2060497191","https://openalex.org/W2078794610","https://openalex.org/W2081741920","https://openalex.org/W2083232784","https://openalex.org/W2087891564","https://openalex.org/W2088415187","https://openalex.org/W2099860858","https://openalex.org/W2108291106","https://openalex.org/W2111593426","https://openalex.org/W2112979995","https://openalex.org/W2140086608","https://openalex.org/W2140153041","https://openalex.org/W2144215687","https://openalex.org/W2155967869","https://openalex.org/W2159937165","https://openalex.org/W2284108769","https://openalex.org/W2294713103","https://openalex.org/W2406344247","https://openalex.org/W2752879223","https://openalex.org/W2801307125","https://openalex.org/W2903589674","https://openalex.org/W2944067258","https://openalex.org/W2962883842","https://openalex.org/W2963078637","https://openalex.org/W3022909171","https://openalex.org/W3024923751","https://openalex.org/W3088997490","https://openalex.org/W3131233784","https://openalex.org/W3138530731","https://openalex.org/W3145286848","https://openalex.org/W3157984709","https://openalex.org/W4287661227","https://openalex.org/W6644572417","https://openalex.org/W6681304122","https://openalex.org/W6766206972","https://openalex.org/W6777992065","https://openalex.org/W6783699156","https://openalex.org/W6784949362","https://openalex.org/W6790507599","https://openalex.org/W6793455254"],"related_works":["https://openalex.org/W3157581606","https://openalex.org/W2113830538","https://openalex.org/W2385105452","https://openalex.org/W2091702533","https://openalex.org/W2137797529","https://openalex.org/W4327753697","https://openalex.org/W2034237012","https://openalex.org/W2118830201","https://openalex.org/W2282105799","https://openalex.org/W3176827258"],"abstract_inverted_index":{"The":[0],"generalized":[1],"minimum":[2],"residual":[3],"method":[4,78],"(GMRES)":[5],"is":[6],"a":[7,88,95],"commonly":[8],"used":[9],"iterative":[10,22],"Krylov":[11],"solver":[12],"for":[13],"sparse,":[14],"non-symmetric":[15],"systems":[16],"of":[17,56,76,90],"linear":[18],"equations.":[19],"Like":[20],"other":[21],"solvers,":[23],"data":[24],"movement":[25],"dominates":[26],"its":[27,67],"run":[28],"time.":[29],"To":[30],"improve":[31],"this":[32,77],"performance,":[33],"we":[34,49,108],"propose":[35],"running":[36],"GMRES":[37,59],"in":[38,45,105],"reduced":[39],"precision":[40,58,69],"with":[41,60,63,87,123],"key":[42],"operations":[43],"remaining":[44],"full":[46],"precision.":[47],"Additionally,":[48],"provide":[50],"theoretical":[51],"results":[52],"linking":[53],"the":[54,74,84,99,124,128],"convergence":[55,75],"finite":[57],"classical":[61],"Gram-Schmidt":[62],"reorthogonalization":[64],"(CGSR)":[65],"and":[66,92],"infinite":[68],"counterpart":[70],"which":[71],"helps":[72],"justify":[73],"to":[79,115,119],"double-precision":[80,121],"accuracy.":[81],"We":[82],"tested":[83],"mixed-precision":[85],"approach":[86],"variety":[89],"matrices":[91],"preconditioners":[93,126],"on":[94],"GPU-accelerated":[96],"node.":[97],"Excluding":[98],"incomplete":[100],"LU":[101],"factorization":[102],"without":[103],"fill":[104],"(ILU(0))":[106],"preconditioner,":[107],"achieved":[109],"average":[110],"speedups":[111],"ranging":[112],"from":[113],"8":[114],"61":[116],"percent":[117],"relative":[118],"comparable":[120],"implementations,":[122],"simpler":[125],"achieving":[127],"higher":[129],"speedups.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}