{"id":"https://openalex.org/W2917667657","doi":"https://doi.org/10.1109/padsw.2018.8644528","title":"CoLoR: Co-Located Rescuers for Fault Tolerance in HPC Systems","display_name":"CoLoR: Co-Located Rescuers for Fault Tolerance in HPC Systems","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2917667657","doi":"https://doi.org/10.1109/padsw.2018.8644528","mag":"2917667657"},"language":"en","primary_location":{"id":"doi:10.1109/padsw.2018.8644528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/padsw.2018.8644528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-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/A5018115688","display_name":"Zaeem Hussain","orcid":null},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zaeem Hussain","raw_affiliation_strings":["Department of Computer Science, University of Pittsburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101857582","display_name":"Xiaolong Cui","orcid":"https://orcid.org/0000-0003-4498-9028"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaolong Cui","raw_affiliation_strings":["Department of Computer Science, University of Pittsburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051806341","display_name":"Taieb Znati","orcid":"https://orcid.org/0000-0002-9389-3033"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taieb Znati","raw_affiliation_strings":["Department of Computer Science, University of Pittsburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038997010","display_name":"Rami Melhem","orcid":"https://orcid.org/0000-0001-6403-5446"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rami Melhem","raw_affiliation_strings":["Department of Computer Science, University of Pittsburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3953,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68877095,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"15","issue":null,"first_page":"569","last_page":"576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":1.0,"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":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9937999844551086,"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":0.9912999868392944,"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/fault-tolerance","display_name":"Fault tolerance","score":0.8289275169372559},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8165751695632935},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.7198106050491333},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6423088908195496},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.6330636143684387},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5394381880760193},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.45629075169563293},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4552047550678253},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.4497872292995453},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4230617880821228},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4076152443885803},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.39274823665618896},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.3440626263618469},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.32834330201148987},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23480787873268127},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0740104615688324}],"concepts":[{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.8289275169372559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8165751695632935},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.7198106050491333},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6423088908195496},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.6330636143684387},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5394381880760193},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.45629075169563293},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4552047550678253},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.4497872292995453},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4230617880821228},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4076152443885803},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.39274823665618896},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3440626263618469},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32834330201148987},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23480787873268127},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0740104615688324},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C165205528","wikidata":"https://www.wikidata.org/wiki/Q83371","display_name":"Seismology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/padsw.2018.8644528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/padsw.2018.8644528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W23377417","https://openalex.org/W63848143","https://openalex.org/W1506585574","https://openalex.org/W1984564341","https://openalex.org/W1985713815","https://openalex.org/W2001219263","https://openalex.org/W2014413779","https://openalex.org/W2031260715","https://openalex.org/W2035492130","https://openalex.org/W2052915895","https://openalex.org/W2063924830","https://openalex.org/W2077546582","https://openalex.org/W2088552220","https://openalex.org/W2098675182","https://openalex.org/W2100970777","https://openalex.org/W2114035455","https://openalex.org/W2116011221","https://openalex.org/W2125776594","https://openalex.org/W2133046454","https://openalex.org/W2138544153","https://openalex.org/W2155204206","https://openalex.org/W2169164058","https://openalex.org/W2189441933","https://openalex.org/W2521708680","https://openalex.org/W2571820657","https://openalex.org/W2787618317","https://openalex.org/W3022806736","https://openalex.org/W4234514454","https://openalex.org/W6630039267","https://openalex.org/W6687178930"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W3191490922","https://openalex.org/W2794038527","https://openalex.org/W2327638088","https://openalex.org/W2151092287"],"abstract_inverted_index":{"With":[0],"the":[1,8,24,55,66,121],"increase":[2],"in":[3,81,95],"scale":[4],"of":[5,10,20,35,69,138],"HPC":[6,112],"systems,":[7],"frequency":[9],"system":[11,139],"wide":[12],"failures":[13],"is":[14],"expected":[15,83],"to":[16,43,58],"increase.":[17],"The":[18],"performance":[19,109],"Coordinated":[21],"Checkpoint/Restart":[22],"(C/R),":[23],"traditional":[25,130],"fault":[26,49],"tolerance":[27,50],"technique,":[28],"degrades":[29],"under":[30],"high":[31],"failure":[32],"rates":[33],"because":[34],"frequent":[36],"global":[37],"rollbacks,":[38],"which":[39],"themselves":[40],"are":[41],"susceptible":[42],"failures.":[44,71],"We":[45,89],"propose":[46],"CoLoR,":[47],"a":[48,78,92,135],"scheme":[51,79],"that":[52,76,125],"i)requires":[53],"only":[54],"failing":[56],"process":[57],"recover,":[59],"ii)overlaps":[60],"reexecution":[61],"with":[62,118],"restart,":[63],"and":[64,102,106,132],"iii)avoids":[65],"cumulative":[67],"effect":[68],"successive":[70],"Our":[72,114],"theoretical":[73,122],"analysis":[74],"reveals":[75],"such":[77],"results":[80],"lower":[82],"completion":[84],"time":[85],"than":[86],"coordinated":[87],"C/R.":[88],"also":[90],"provide":[91],"proof-of-concept":[93],"implementation":[94],"MPI":[96],"using":[97,142],"receiver":[98],"based":[99],"message":[100],"logging":[101],"colocated":[103],"rescuer":[104],"(CoLoR)processes,":[105],"evaluate":[107],"its":[108],"on":[110],"several":[111],"benchmarks.":[113],"experimental":[115],"results,":[116],"combined":[117],"observations":[119],"from":[120],"analysis,":[123],"show":[124],"CoLoR":[126],"can":[127],"outperform":[128],"both":[129],"C/R":[131],"replication":[133],"over":[134],"large":[136],"range":[137],"sizes,":[140],"without":[141],"extra":[143],"logger":[144],"nodes.":[145]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
