{"id":"https://openalex.org/W3005478802","doi":"https://doi.org/10.1177/1094342020901885","title":"Overhead of using spare nodes","display_name":"Overhead of using spare nodes","publication_year":2020,"publication_date":"2020-02-04","ids":{"openalex":"https://openalex.org/W3005478802","doi":"https://doi.org/10.1177/1094342020901885","mag":"3005478802"},"language":"en","primary_location":{"id":"doi:10.1177/1094342020901885","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342020901885","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","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/A5102836031","display_name":"Atsushi Hori","orcid":"https://orcid.org/0000-0002-7010-8098"},"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":true,"raw_author_name":"Atsushi Hori","raw_affiliation_strings":["RIKEN Center for Computational Science, Kobe, Hyogo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Hyogo, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035283499","display_name":"Kazumi Yoshinaga","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146980","display_name":"Meguro Parasitological Museum","ror":"https://ror.org/050bkqc56","country_code":"JP","type":"archive","lineage":["https://openalex.org/I4210146980"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazumi Yoshinaga","raw_affiliation_strings":["Meguro-ku, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meguro-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I4210146980"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008117654","display_name":"Thomas H\u00e9rault","orcid":"https://orcid.org/0000-0001-6756-6189"},"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":"Thomas Herault","raw_affiliation_strings":["Innovative Computing Laboratory, The University of Tennessee, Knoxville, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, The University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054873210","display_name":"Aur\u00e9lien Bouteiller","orcid":"https://orcid.org/0000-0001-5108-509X"},"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":"Aur\u00e9lien Bouteiller","raw_affiliation_strings":["Innovative Computing Laboratory, The University of Tennessee, Knoxville, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, The University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010055736","display_name":"George Bosilca","orcid":"https://orcid.org/0000-0003-2411-8495"},"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":"George Bosilca","raw_affiliation_strings":["Innovative Computing Laboratory, The University of Tennessee, Knoxville, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, The University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053784620","display_name":"Yutaka Ishikawa","orcid":"https://orcid.org/0000-0003-2286-9770"},"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":"Yutaka Ishikawa","raw_affiliation_strings":["RIKEN Center for Computational Science, Kobe, Hyogo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Hyogo, Japan","institution_ids":["https://openalex.org/I4210129730"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102836031"],"corresponding_institution_ids":["https://openalex.org/I4210129730"],"apc_list":null,"apc_paid":null,"fwci":0.4024,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65618434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"34","issue":"2","first_page":"208","last_page":"226"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9997000098228455,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.998199999332428,"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/spare-part","display_name":"Spare part","score":0.8539576530456543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7571144104003906},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.7106478810310364},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6790032386779785},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6227089762687683},{"id":"https://openalex.org/keywords/substitution","display_name":"Substitution (logic)","score":0.569968581199646},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5264742374420166},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.47905290126800537},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4132290184497833},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.38330695033073425},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2041187286376953},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1180925965309143},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09980118274688721}],"concepts":[{"id":"https://openalex.org/C194648553","wikidata":"https://www.wikidata.org/wiki/Q1364774","display_name":"Spare part","level":2,"score":0.8539576530456543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7571144104003906},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.7106478810310364},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6790032386779785},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6227089762687683},{"id":"https://openalex.org/C2778220771","wikidata":"https://www.wikidata.org/wiki/Q1522579","display_name":"Substitution (logic)","level":2,"score":0.569968581199646},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5264742374420166},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.47905290126800537},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4132290184497833},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.38330695033073425},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2041187286376953},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1180925965309143},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09980118274688721},{"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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"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":1,"locations":[{"id":"doi:10.1177/1094342020901885","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342020901885","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1977520786","https://openalex.org/W1979572629","https://openalex.org/W2001219263","https://openalex.org/W2009852231","https://openalex.org/W2017060126","https://openalex.org/W2021234574","https://openalex.org/W2025024269","https://openalex.org/W2049644498","https://openalex.org/W2063924830","https://openalex.org/W2081413727","https://openalex.org/W2087094132","https://openalex.org/W2088112706","https://openalex.org/W2096504919","https://openalex.org/W2116886065","https://openalex.org/W2128577831","https://openalex.org/W2151984682","https://openalex.org/W2157237396","https://openalex.org/W2229245554","https://openalex.org/W2234212075","https://openalex.org/W2240709090","https://openalex.org/W2247921729","https://openalex.org/W2250057853","https://openalex.org/W2336358014","https://openalex.org/W4244600229","https://openalex.org/W4245507143","https://openalex.org/W4248073216"],"related_works":["https://openalex.org/W2376859990","https://openalex.org/W2912704652","https://openalex.org/W2381161177","https://openalex.org/W2319226115","https://openalex.org/W1862835629","https://openalex.org/W2099111379","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991","https://openalex.org/W2781863720"],"abstract_inverted_index":{"With":[0],"the":[1,8,87,106,120,123,162,180,209,234,251,256,268,277,330,340],"increasing":[2],"fault":[3,11],"rate":[4],"on":[5,147,255,267,276,312,345],"high-end":[6],"supercomputers,":[7],"topic":[9],"of":[10,89,122,182,205,270,294],"tolerance":[12],"has":[13,160,320],"been":[14],"gathering":[15],"attention.":[16],"To":[17],"cope":[18],"with":[19,47,52,325],"this":[20,186],"situation,":[21],"various":[22],"fault-tolerance":[23,32],"techniques":[24,33],"are":[25,70,73,215,222],"under":[26],"investigation;":[27],"these":[28,48,170],"include":[29],"user-level,":[30],"algorithm-based":[31],"and":[34,103,192,201,230,240,258,333],"parallel":[35],"execution":[36],"environments":[37],"that":[38,178,247,302],"enable":[39],"jobs":[40],"to":[41,97],"continue":[42],"following":[43,208],"node":[44,127,190,194,271],"failure.":[45],"Even":[46,66],"techniques,":[49],"some":[50],"programs":[51],"static":[53],"load":[54],"balancing,":[55],"such":[56,112,305],"as":[57],"stencil":[58,137,252],"computation,":[59,138],"may":[60,166],"underperform":[61],"after":[62],"a":[63,113,136,144,148,158,176,292,326],"failure":[64],"recovery.":[65],"when":[67,248],"spare":[68,91,189],"nodes":[69,79,92],"present,":[71],"they":[72],"not":[74],"always":[75],"substituted":[76],"for":[77,100],"failed":[78,193],"in":[80,143,175,203,282],"an":[81,321],"effective":[82],"way.":[83],"This":[84,315],"article":[85],"considers":[86],"questions":[88,171],"how":[90,96,104],"should":[93],"be":[94,167,173,198,245,261,280,289,300,310],"allocated,":[95],"substitute":[98],"them":[99],"faulty":[101],"nodes,":[102],"much":[105],"communication":[107,183,206,253,306,341],"performance":[108,207,254,275,287,307,342],"is":[109,141,316],"affected":[110],"by":[111,126,224,232,291],"substitution.":[114,210],"The":[115,211,219,273],"third":[116],"question":[117],"stems":[118],"from":[119],"modification":[121],"rank":[124,139],"mapping":[125,140,165],"substitutions,":[128],"which":[129],"can":[130,260,279,288,309],"incur":[131],"additional":[132],"message":[133,154],"collisions.":[134,155],"In":[135,185],"done":[142],"straightforward":[145],"way":[146,177],"Cartesian":[149,337],"network":[150,323,346],"without":[151],"incurring":[152],"any":[153],"However,":[156],"once":[157],"substitution":[159,195,213],"occurred,":[161],"optimal":[163],"node-rank":[164],"destroyed.":[168],"Therefore,":[169],"must":[172],"answered":[174],"minimizes":[179],"degradation":[181,308,343],"performance.":[184],"article,":[187],"several":[188],"allocation":[191],"methods":[196,214,221],"will":[197,244,298],"proposed,":[199],"analyzed,":[200],"compared":[202],"terms":[204],"proposed":[212],"named":[216],"sliding":[217,220],"methods.":[218],"analyzed":[223],"using":[225,233],"our":[226],"developed":[227],"simulation":[228],"program":[229],"evaluated":[231],"K":[235,257,278,331],"computer,":[236],"Blue":[237],"Gene/Q":[238],"(BG/Q),":[239],"TSUBAME":[241,313,318],"2.5.":[242,314],"It":[243],"shown":[246,301],"failures":[249],"occur,":[250],"BG/Q":[259,334],"slowed":[262,290],"around":[263],"10":[264],"times":[265],"depending":[266],"number":[269],"failures.":[272],"barrier":[274,286],"cut":[281],"half.":[283],"On":[284],"BG/Q,":[285],"factor":[293],"10.":[295],"Further,":[296],"it":[297],"also":[299],"almost":[303],"no":[304],"seen":[311],"because":[317],"2.5":[319],"Infiniband":[322],"connected":[324],"FatTree":[327],"topology,":[328],"while":[329],"computer":[332],"have":[335],"dedicated":[336],"networks.":[338],"Thus,":[339],"depends":[344],"characteristics.":[347]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
