{"id":"https://openalex.org/W3007867561","doi":"https://doi.org/10.1109/access.2020.2975832","title":"FT-PBLAS: PBLAS-Based Fault-Tolerant Linear Algebra Computation on High-performance Computing Systems","display_name":"FT-PBLAS: PBLAS-Based Fault-Tolerant Linear Algebra Computation on High-performance Computing Systems","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3007867561","doi":"https://doi.org/10.1109/access.2020.2975832","mag":"3007867561"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.2975832","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2975832","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09007454.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09007454.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101559515","display_name":"Yanchao Zhu","orcid":"https://orcid.org/0000-0002-4598-1063"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanchao Zhu","raw_affiliation_strings":["Beijing Key Laboratory of Network Technology, Beihang University, Beijing, China","School of Computer Science and Engineering, Sino-German Joint Software Institute, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4598-1063","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network Technology, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sino-German Joint Software Institute, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330538","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0002-4911-1161"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Beijing Key Laboratory of Network Technology, Beihang University, Beijing, China","School of Computer Science and Engineering, Sino-German Joint Software Institute, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4911-1161","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network Technology, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sino-German Joint Software Institute, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027457097","display_name":"Guozhen Zhang","orcid":"https://orcid.org/0000-0002-9956-8119"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guozhen Zhang","raw_affiliation_strings":["Beijing Key Laboratory of Network Technology, Beihang University, Beijing, China","School of Computer Science and Engineering, Sino-German Joint Software Institute, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9956-8119","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network Technology, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sino-German Joint Software Institute, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.6182,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.69752019,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"8","issue":null,"first_page":"42674","last_page":"42688"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9980000257492065,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9975000023841858,"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/checksum","display_name":"Checksum","score":0.9549466967582703},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8429672718048096},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7410402297973633},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6622369289398193},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5148352980613708},{"id":"https://openalex.org/keywords/software-fault-tolerance","display_name":"Software fault tolerance","score":0.47924402356147766},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4594164490699768},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4255865812301636},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4146949052810669},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.34646227955818176},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12377914786338806}],"concepts":[{"id":"https://openalex.org/C162372511","wikidata":"https://www.wikidata.org/wiki/Q218341","display_name":"Checksum","level":2,"score":0.9549466967582703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8429672718048096},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7410402297973633},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6622369289398193},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5148352980613708},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.47924402356147766},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4594164490699768},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4255865812301636},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4146949052810669},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.34646227955818176},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12377914786338806},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.2975832","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2975832","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09007454.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1de3ad745bfe4d1da58a67c561e9e3fd","is_oa":true,"landing_page_url":"https://doaj.org/article/1de3ad745bfe4d1da58a67c561e9e3fd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 42674-42688 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.2975832","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2975832","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09007454.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1897972234","display_name":null,"funder_award_id":"2016YFB0200100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4048776522","display_name":null,"funder_award_id":"91530324","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3007867561.pdf","grobid_xml":"https://content.openalex.org/works/W3007867561.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1515402129","https://openalex.org/W1567848171","https://openalex.org/W1576341769","https://openalex.org/W1607166357","https://openalex.org/W1770291975","https://openalex.org/W1976859632","https://openalex.org/W2002257715","https://openalex.org/W2021234574","https://openalex.org/W2024166759","https://openalex.org/W2028133900","https://openalex.org/W2039747889","https://openalex.org/W2056109788","https://openalex.org/W2072072075","https://openalex.org/W2083613288","https://openalex.org/W2109017398","https://openalex.org/W2116115793","https://openalex.org/W2118706534","https://openalex.org/W2122295525","https://openalex.org/W2128564847","https://openalex.org/W2139244298","https://openalex.org/W2148143831","https://openalex.org/W2151984682","https://openalex.org/W2159249499","https://openalex.org/W2162989857","https://openalex.org/W2475126267","https://openalex.org/W2508394916","https://openalex.org/W2539230224","https://openalex.org/W2900798440","https://openalex.org/W2913795177","https://openalex.org/W3022909171","https://openalex.org/W3150262005","https://openalex.org/W4232616607","https://openalex.org/W4244477174","https://openalex.org/W4297724452","https://openalex.org/W6636116026","https://openalex.org/W6637902329"],"related_works":["https://openalex.org/W2971479921","https://openalex.org/W2106348006","https://openalex.org/W3145923041","https://openalex.org/W2412349256","https://openalex.org/W2946906624","https://openalex.org/W841176518","https://openalex.org/W1978919910","https://openalex.org/W2024212764","https://openalex.org/W2123437881","https://openalex.org/W2098626762"],"abstract_inverted_index":{"As":[0],"high-performance":[1],"computing":[2],"(HPC)":[3],"systems":[4,52],"have":[5,24,69,109],"scaled":[6],"up,":[7],"resilience":[8],"has":[9],"become":[10,70],"a":[11,91,176,190,204,227,234],"great":[12],"challenge.":[13],"To":[14,168,213],"guarantee":[15],"resilience,":[16],"various":[17],"kinds":[18],"of":[19,43,48,137,141,146,193,206,209,258],"hardware":[20],"and":[21,37,50,76,101,125,139,219,233,246,251],"software":[22,30],"techniques":[23],"been":[25],"proposed.":[26],"However,":[27,105],"among":[28],"popular":[29],"fault-tolerant":[31,180,191,207,244],"techniques,":[32],"both":[33],"the":[34,38,46,79,122,194,215,223,252,256],"checkpoint-restart":[35],"approach":[36,229],"replication":[39],"technique":[40,81],"face":[41],"challenges":[42],"scalability":[44],"in":[45,95,116,164,211,222],"era":[47],"peta-":[49],"exa-scale":[51],"due":[53],"to":[54,87,148],"their":[55],"numerous":[56],"processes.":[57],"In":[58],"this":[59,172],"situation,":[60],"algorithm-based":[61,64],"approaches,":[62],"or":[63,120],"fault":[65,114],"tolerance":[66,115],"(ABFT)":[67],"mechanisms,":[68],"attractive":[71],"because":[72,201],"they":[73,134,152],"are":[74,126,162],"efficient":[75],"lightweight.":[77],"Although":[78],"ABFT":[80,107],"is":[82,85],"algorithm-dependent,":[83],"it":[84,89,103,202],"possible":[86],"implement":[88],"at":[90,112,121],"low":[92],"level":[93,124],"(e.g.,":[94],"libraries":[96],"for":[97,130,179,230,236],"basic":[98,196],"numerical":[99],"algorithms)":[100],"make":[102],"application-independent.":[104],"previous":[106],"approaches":[108],"mainly":[110],"aimed":[111],"achieving":[113],"integrated":[117],"circuits":[118],"(ICs)":[119],"architecture":[123],"therefore":[127],"not":[128],"suitable":[129],"HPC":[131,166,249],"systems;":[132],"e.g.,":[133],"use":[135],"checksums":[136,145],"rows":[138],"columns":[140],"matrices":[142],"rather":[143],"than":[144],"blocks":[147],"detect":[149],"errors.":[150],"Furthermore,":[151],"cannot":[153],"deal":[154],"with":[155],"errors":[156,232],"caused":[157],"by":[158],"node":[159,238],"failure,":[160,239],"which":[161],"common":[163],"current":[165],"systems.":[167],"solve":[169],"these":[170],"problems,":[171],"paper":[173],"proposes":[174],"FT-PBLAS,":[175],"PBLAS-based":[177],"library":[178],"parallel":[181,195],"linear":[182,197],"algebra":[183,198],"computations":[184],"that":[185],"can":[186],"be":[187],"regarded":[188],"as":[189],"version":[192],"subprograms":[199],"(PBLAS),":[200],"provides":[203],"series":[205],"versions":[208],"interfaces":[210],"PBLAS.":[212],"support":[214],"underlying":[216],"error":[217],"detection":[218],"recovery":[220],"mechanisms":[221,245],"library,":[224],"we":[225],"propose":[226],"block-checksum":[228],"non-fatal":[231],"scheme":[235],"addressing":[237],"respectively.":[240],"We":[241],"evaluate":[242],"two":[243],"FT-PBLAS":[247],"on":[248],"systems,":[250],"experimental":[253],"results":[254],"demonstrate":[255],"performance":[257],"our":[259],"library.":[260]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}