{"id":"https://openalex.org/W2102576651","doi":"https://doi.org/10.1109/ipdps.2008.4536279","title":"An optimal checkpoint/restart model for a large scale high performance computing system","display_name":"An optimal checkpoint/restart model for a large scale high performance computing system","publication_year":2008,"publication_date":"2008-04-01","ids":{"openalex":"https://openalex.org/W2102576651","doi":"https://doi.org/10.1109/ipdps.2008.4536279","mag":"2102576651"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2008.4536279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2008.4536279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Symposium on Parallel and Distributed Processing","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/A5003892229","display_name":"Yudan Liu","orcid":"https://orcid.org/0000-0002-7496-7033"},"institutions":[{"id":"https://openalex.org/I919208787","display_name":"Louisiana Tech University","ror":"https://ror.org/04q9esz89","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I919208787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yudan Liu","raw_affiliation_strings":["College of Engineering & Science, Louisiana Tech University, Ruston, LA, USA","College of Engineering & Science, Louisiana Tech University, Ruston, LA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering & Science, Louisiana Tech University, Ruston, LA, USA","institution_ids":["https://openalex.org/I919208787"]},{"raw_affiliation_string":"College of Engineering & Science, Louisiana Tech University, Ruston, LA","institution_ids":["https://openalex.org/I919208787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114147305","display_name":"R. Nassar","orcid":null},"institutions":[{"id":"https://openalex.org/I919208787","display_name":"Louisiana Tech University","ror":"https://ror.org/04q9esz89","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I919208787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Nassar","raw_affiliation_strings":["College of Engineering & Science, Louisiana Tech University, Ruston, LA, USA","College of Engineering & Science, Louisiana Tech University, Ruston, LA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering & Science, Louisiana Tech University, Ruston, LA, USA","institution_ids":["https://openalex.org/I919208787"]},{"raw_affiliation_string":"College of Engineering & Science, Louisiana Tech University, Ruston, LA","institution_ids":["https://openalex.org/I919208787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110446405","display_name":"C. Leangsuksun","orcid":null},"institutions":[{"id":"https://openalex.org/I919208787","display_name":"Louisiana Tech University","ror":"https://ror.org/04q9esz89","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I919208787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Leangsuksun","raw_affiliation_strings":["College of Engineering & Science, Louisiana Tech University, Ruston, LA, USA","College of Engineering & Science, Louisiana Tech University, Ruston, LA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering & Science, Louisiana Tech University, Ruston, LA, USA","institution_ids":["https://openalex.org/I919208787"]},{"raw_affiliation_string":"College of Engineering & Science, Louisiana Tech University, Ruston, LA","institution_ids":["https://openalex.org/I919208787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029063905","display_name":"Nichamon Naksinehaboon","orcid":null},"institutions":[{"id":"https://openalex.org/I919208787","display_name":"Louisiana Tech University","ror":"https://ror.org/04q9esz89","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I919208787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N. Naksinehaboon","raw_affiliation_strings":["College of Engineering & Science, Louisiana Tech University, Ruston, LA, USA","College of Engineering & Science, Louisiana Tech University, Ruston, LA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering & Science, Louisiana Tech University, Ruston, LA, USA","institution_ids":["https://openalex.org/I919208787"]},{"raw_affiliation_string":"College of Engineering & Science, Louisiana Tech University, Ruston, LA","institution_ids":["https://openalex.org/I919208787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005550984","display_name":"Mihaela P\u0103un","orcid":"https://orcid.org/0000-0002-3342-9140"},"institutions":[{"id":"https://openalex.org/I919208787","display_name":"Louisiana Tech University","ror":"https://ror.org/04q9esz89","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I919208787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Paun","raw_affiliation_strings":["College of Engineering & Science, Louisiana Tech University, Ruston, LA, USA","College of Engineering & Science, Louisiana Tech University, Ruston, LA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering & Science, Louisiana Tech University, Ruston, LA, USA","institution_ids":["https://openalex.org/I919208787"]},{"raw_affiliation_string":"College of Engineering & Science, Louisiana Tech University, Ruston, LA","institution_ids":["https://openalex.org/I919208787"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109843869","display_name":"Stephen L. Scott","orcid":null},"institutions":[{"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"]},{"id":"https://openalex.org/I919208787","display_name":"Louisiana Tech University","ror":"https://ror.org/04q9esz89","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I919208787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S.L. Scott","raw_affiliation_strings":["Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","College of Engineering & Science, Louisiana Tech University, Ruston, LA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"College of Engineering & Science, Louisiana Tech University, Ruston, LA","institution_ids":["https://openalex.org/I919208787"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8138,"has_fulltext":false,"cited_by_count":104,"citation_normalized_percentile":{"value":0.93679926,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7964062690734863},{"id":"https://openalex.org/keywords/rollback","display_name":"Rollback","score":0.7815369367599487},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6557992100715637},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.62372225522995},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.6233974695205688},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.47108685970306396},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.45566219091415405},{"id":"https://openalex.org/keywords/interval","display_name":"Interval (graph theory)","score":0.4114985764026642},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3821398913860321},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.33260419964790344},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20968866348266602},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08965829014778137},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.06225380301475525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7964062690734863},{"id":"https://openalex.org/C174220543","wikidata":"https://www.wikidata.org/wiki/Q395307","display_name":"Rollback","level":3,"score":0.7815369367599487},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6557992100715637},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.62372225522995},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6233974695205688},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.47108685970306396},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45566219091415405},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.4114985764026642},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3821398913860321},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.33260419964790344},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20968866348266602},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08965829014778137},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.06225380301475525},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2008.4536279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2008.4536279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Symposium on Parallel and Distributed Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1567880","https://openalex.org/W191492107","https://openalex.org/W1530574078","https://openalex.org/W1538116128","https://openalex.org/W1558516248","https://openalex.org/W1971952282","https://openalex.org/W2033656974","https://openalex.org/W2044565821","https://openalex.org/W2045879521","https://openalex.org/W2048784665","https://openalex.org/W2098259808","https://openalex.org/W2106017997","https://openalex.org/W2119018856","https://openalex.org/W2129935547","https://openalex.org/W2132920089","https://openalex.org/W2133046454","https://openalex.org/W2135917956","https://openalex.org/W2167083307","https://openalex.org/W2799087070","https://openalex.org/W2992707587","https://openalex.org/W4232225775","https://openalex.org/W6607731702","https://openalex.org/W6631753506","https://openalex.org/W6643050054","https://openalex.org/W6678776837"],"related_works":["https://openalex.org/W2075454349","https://openalex.org/W2145855242","https://openalex.org/W2010356481","https://openalex.org/W2016184125","https://openalex.org/W4236084769","https://openalex.org/W2103295733","https://openalex.org/W1862835629","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991"],"abstract_inverted_index":{"The":[0],"increase":[1],"in":[2,58],"the":[3,21,73,108],"physical":[4],"size":[5],"of":[6,35],"High":[7],"Performance":[8],"Computing":[9],"(HPC)":[10],"platform":[11],"makes":[12],"system":[13,75],"reliability":[14],"more":[15],"challenging.":[16],"In":[17,106],"order":[18],"to":[19,29],"minimize":[20],"performance":[22],"loss":[23],"(rollback":[24],"and":[25,87,101,116],"checkpoint":[26,66,79,90,99,114],"overheads)":[27],"due":[28],"unexpected":[30],"failures":[31],"or":[32],"unnecessary":[33],"overhead":[34,115],"fault":[36,54],"tolerant":[37],"mechanisms,":[38],"we":[39],"present":[40],"a":[41,59,88,97,123],"reliability-aware":[42],"method":[43],"for":[44,112],"an":[45],"optimal":[46,65],"checkpoint/restart":[47],"strategy.":[48],"Our":[49,119],"scheme":[50],"aims":[51],"at":[52],"addressing":[53],"tolerance":[55],"challenge,":[56],"especially":[57],"large-scale":[60],"HPC":[61],"system,":[62],"by":[63],"providing":[64],"placement":[67],"techniques":[68],"that":[69],"are":[70],"derived":[71],"from":[72],"actual":[74],"reliability.":[76],"Unlike":[77],"existing":[78,127],"models,":[80],"which":[81],"can":[82,94],"only":[83],"handle":[84],"Poisson":[85],"failure":[86,104],"constant":[89],"interval,":[91],"our":[92],"model":[93],"deal":[95],"with":[96,102],"varying":[98],"interval":[100],"different":[103],"distributions.":[105],"addition,":[107],"approach":[109],"considers":[110],"optimality":[111],"both":[113],"rollback":[117],"time.":[118],"validation":[120],"results":[121],"suggest":[122],"significant":[124],"improvement":[125],"over":[126],"techniques.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
