{"id":"https://openalex.org/W2792839583","doi":"https://doi.org/10.1109/tpds.2018.2817524","title":"Asynchronous and Exact Forward Recovery for Detected Errors in Iterative Solvers","display_name":"Asynchronous and Exact Forward Recovery for Detected Errors in Iterative Solvers","publication_year":2018,"publication_date":"2018-03-20","ids":{"openalex":"https://openalex.org/W2792839583","doi":"https://doi.org/10.1109/tpds.2018.2817524","mag":"2792839583"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2817524","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_indexed_in_scopus":true,"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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://upcommons.upc.edu/bitstream/2117/118042/1/08320336.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006432908","display_name":"Luc Jaulmes","orcid":"https://orcid.org/0000-0002-5815-2504"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"funder","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Luc Jaulmes","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya."],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya.","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088729105","display_name":"Miquel Moret\u00f3","orcid":"https://orcid.org/0000-0002-9848-8758"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"funder","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Miquel Moreto","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya."],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya.","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075755125","display_name":"Eduard Ayguad\u00e9","orcid":"https://orcid.org/0000-0002-5146-103X"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"funder","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Eduard Ayguade","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya."],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya.","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035035680","display_name":"Jes\u00fas Labarta","orcid":"https://orcid.org/0000-0002-7489-4727"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"funder","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jesus Labarta","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya."],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya.","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020844763","display_name":"Mateo Valero","orcid":"https://orcid.org/0000-0003-2917-2482"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"funder","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mateo Valero","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya."],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya.","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044183257","display_name":"Marc Casas","orcid":"https://orcid.org/0000-0003-4564-2093"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"funder","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Marc Casas","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya."],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya.","institution_ids":["https://openalex.org/I9617848"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.591,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":9,"citation_normalized_percentile":{"value":0.81942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":84,"max":85},"biblio":{"volume":"29","issue":"9","first_page":"1961","last_page":"1974"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9999,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9999,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9994,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9989,"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/solver","display_name":"Solver","score":0.64298105},{"id":"https://openalex.org/keywords/krylov-subspace","display_name":"Krylov subspace","score":0.51986885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8631933},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.64298105},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5203928},{"id":"https://openalex.org/C147060835","wikidata":"https://www.wikidata.org/wiki/Q1757151","display_name":"Krylov subspace","level":3,"score":0.51986885},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.51696676},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.51602817},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5149632},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.49953675},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4451894},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.4150563},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.38649523},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.3850779},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3233578},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1232481},{"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}],"mesh":[],"locations_count":4,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2817524","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_indexed_in_scopus":true,"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":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/118042","pdf_url":"https://upcommons.upc.edu/bitstream/2117/118042/1/08320336.pdf","source":{"id":"https://openalex.org/S4306400551","display_name":"UPCommons (Polytechnic University of Catalonia)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":["Universitat Polit\u00e8cnica de Catalunya"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/e0828d52-19a1-428a-8b3c-2fb9882e36f8","pdf_url":"https://www.research.ed.ac.uk/files/253697926/Asynchronous_and_Exact_JAULMES_DOA08032018_AFV.pdf","source":{"id":"https://openalex.org/S4306400320","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":["University of Edinburgh"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false},{"is_oa":true,"landing_page_url":"https://www.pure.ed.ac.uk/ws/files/253697926/Asynchronous_and_Exact_JAULMES_DOA08032018_AFV.pdf","pdf_url":"https://www.pure.ed.ac.uk/ws/files/253697926/Asynchronous_and_Exact_JAULMES_DOA08032018_AFV.pdf","source":{"id":"https://openalex.org/S4306400320","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":["University of Edinburgh"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/118042","pdf_url":"https://upcommons.upc.edu/bitstream/2117/118042/1/08320336.pdf","source":{"id":"https://openalex.org/S4306400551","display_name":"UPCommons (Polytechnic University of Catalonia)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":["Universitat Polit\u00e8cnica de Catalunya"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n","award_id":"TIN2015-65316-P"}],"datasets":[],"versions":[],"referenced_works_count":42,"referenced_works":["https://openalex.org/W1554281179","https://openalex.org/W1568101540","https://openalex.org/W1575701986","https://openalex.org/W1601007342","https://openalex.org/W1833656387","https://openalex.org/W1981493666","https://openalex.org/W1984564341","https://openalex.org/W2022916138","https://openalex.org/W2035080386","https://openalex.org/W2036641664","https://openalex.org/W2037523067","https://openalex.org/W2063924830","https://openalex.org/W2064388050","https://openalex.org/W2065171379","https://openalex.org/W2071051794","https://openalex.org/W2074626480","https://openalex.org/W2083613288","https://openalex.org/W2086247510","https://openalex.org/W2098675182","https://openalex.org/W2098841537","https://openalex.org/W2114462749","https://openalex.org/W2118231788","https://openalex.org/W2121417875","https://openalex.org/W2122249806","https://openalex.org/W2128511938","https://openalex.org/W2138660187","https://openalex.org/W2142677441","https://openalex.org/W2144512449","https://openalex.org/W2162351670","https://openalex.org/W2165485434","https://openalex.org/W2168159483","https://openalex.org/W2170310381","https://openalex.org/W2471965769","https://openalex.org/W2504412359","https://openalex.org/W2587647010","https://openalex.org/W2767694495","https://openalex.org/W3000330907","https://openalex.org/W4213043702","https://openalex.org/W4245880889","https://openalex.org/W4246310005","https://openalex.org/W4249144718","https://openalex.org/W4295109456"],"related_works":["https://openalex.org/W4389168214","https://openalex.org/W4366457933","https://openalex.org/W3161880765","https://openalex.org/W2942315554","https://openalex.org/W2798286561","https://openalex.org/W2575167716","https://openalex.org/W2394408226","https://openalex.org/W2119553411","https://openalex.org/W2116573255","https://openalex.org/W2106635645"],"abstract_inverted_index":{"Current":[0],"trends":[1],"and":[2,17,42,129,209,211,220,246,260,275,301,316,348],"projections":[3],"show":[4,293],"that":[5,39,192,357],"faults":[6,310],"in":[7,54,63,168,267],"computer":[8],"systems":[9],"become":[10],"increasingly":[11,361],"common.Such":[12],"errors":[13,242],"may":[14],"be":[15,30],"detected,":[16],"possibly":[18],"corrected":[19],"transparently,":[20],"e.g.":[21],"by":[22,134,151,184],"Error":[23],"Correcting":[24],"Codes":[25],"(ECC).For":[26],"a":[27,55,72,83,113,228],"program":[28,80,103],"to":[29,34,82,123,165,178,196,256,273,276,286,327],"fault-tolerant,":[31],"it":[32,65],"needs":[33],"also":[35,67,355],"handle":[36],"the":[37,69,79,126,130,136,140,156,169,188,225,233,248,252,261,277,306,312,330,338,364],"Errors":[38],"are":[40,175,360],"Detected":[41],"Uncorrected":[43],"(DUE),":[44],"such":[45,98],"as":[46,99,109,363],"an":[47,58,61,101],"ECC":[48],"encountering":[49],"too":[50],"many":[51],"bit":[52],"flips":[53],"codeword.While":[56],"correcting":[57],"error":[59,115,153],"has":[60],"overhead":[62,150],"itself,":[64],"can":[66],"affect":[68],"progress":[70,90,127],"of":[71,142,171,200,227,250,264,329],"program.The":[73],"most":[74],"generic":[75],"technique,":[76,281],"rolling":[77],"back":[78,88],"state":[81,138],"previously":[84],"taken":[85],"checkpoint,":[86],"sets":[87],"any":[89,198],"done":[91],"since":[92],"then.Alternately,":[93],"application":[94],"specific":[95],"techniques":[96,359],"exist,":[97],"restarting":[100],"iterative":[102,119],"with":[104,155,341],"its":[105],"latest":[106],"iteration's":[107],"values":[108],"initial":[110],"guess.We":[111],"introduce":[112],"novel":[114],"correction":[116,154],"technique":[117,160,217],"for":[118,218],"linear":[120],"solvers,":[121],"designed":[122],"preserve":[124],"both":[125],"made":[128],"solver's":[131,157],"future":[132],"convergence":[133],"recovering":[135],"program's":[137],"exactly.Leveraging":[139],"asynchrony":[141],"task-based":[143],"programming":[144],"models,":[145],"we":[146],"mask":[147],"our":[148,216,291,299,358],"technique's":[149],"overlapping":[152,319],"normal":[158],"workload.Our":[159],"relies":[161],"on":[162,243,282,305,344,351],"analysing":[163],"solvers":[164],"find":[166],"redundancy":[167],"form":[170],"relations":[172],"between":[173,298],"data.We":[174],"then":[176],"able":[177],"restore":[179],"discarded":[180],"or":[181,186],"corrupted":[182],"data":[183,223],"recomputing":[185],"inverting":[187],"appropriate":[189],"relations.We":[190],"demonstrate":[191],"this":[193],"approach":[194],"allows":[195],"recover":[197,221],"part":[199],"three":[201],"widely":[202],"used":[203],"Krylov":[204],"subspace":[205],"methods:":[206],"CG,":[207],"GMRES":[208],"BiCGStab,":[210],"their":[212,322],"pre-conditioned":[213],"versions.We":[214],"implement":[215],"CG":[219],"lost":[222],"at":[224,235,308],"scale":[226,288],"memory":[229,241,253],"page,":[230],"which":[231,236,309],"is":[232],"granularity":[234],"Operating":[237],"Systems":[238],"(OS)":[239],"report":[240],"commodity":[244],"hardware,":[245],"study":[247],"effect":[249],"varying":[251],"page":[254,317,346],"size":[255,366],"address":[257],"non-standard":[258],"sizes":[259],"possible":[262],"use":[263],"huge":[265],"pages":[266],"High":[268],"Performance":[269],"Computing":[270],"(HPC).When":[271],"compared":[272],"checkpointing":[274],"state-of-the-art":[278,339],"algorithmic":[279],"restart":[280],"small":[283],"(8":[284],"cores)":[285],"large":[287],"(1024":[289],"cores),":[290],"methods":[292,335],"less":[294],"overhead.A":[295],"trade-off":[296],"arises":[297],"straightforward":[300],"asynchronous":[302],"approaches,":[303],"based":[304],"rate":[307,315],"happen.At":[311],"lowest":[313],"considered":[314],"size,":[318],"recoveries":[320],"decreases":[321],"average":[323],"cost":[324],"from":[325],"5.40%":[326],"2.24%":[328],"ideal":[331],"faultless":[332],"execution":[333],"time.Our":[334],"generally":[336],"outperform":[337],"even":[340],"increased":[342],"overheads":[343],"big":[345],"sizes,":[347],"perform":[349],"similarly":[350],"edge":[352],"cases.These":[353],"results":[354],"indicate":[356],"efficient":[362],"matrix":[365],"increases.":[367]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2792839583","counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-04-24T05:14:00.710728","created_date":"2018-03-29"}