{"id":"https://openalex.org/W1991726467","doi":"https://doi.org/10.1109/ipdpsw.2010.5470810","title":"Highly scalable checkpointing for exascale computing","display_name":"Highly scalable checkpointing for exascale computing","publication_year":2010,"publication_date":"2010-04-01","ids":{"openalex":"https://openalex.org/W1991726467","doi":"https://doi.org/10.1109/ipdpsw.2010.5470810","mag":"1991726467"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw.2010.5470810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2010.5470810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel &amp; Distributed Processing, Workshops and Phd Forum (IPDPSW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5041034518","display_name":"Christer Karlsson","orcid":"https://orcid.org/0000-0001-7353-5303"},"institutions":[{"id":"https://openalex.org/I167576493","display_name":"Colorado School of Mines","ror":"https://ror.org/04raf6v53","country_code":"US","type":"education","lineage":["https://openalex.org/I167576493"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christer Karlsson","raw_affiliation_strings":["Colorado Schml of Mines, Golden, CO, USA","Colorado School of Mines, Golden, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Colorado Schml of Mines, Golden, CO, USA","institution_ids":["https://openalex.org/I167576493"]},{"raw_affiliation_string":"Colorado School of Mines, Golden, USA","institution_ids":["https://openalex.org/I167576493"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061737717","display_name":"Zizhong Chen","orcid":"https://orcid.org/0000-0003-2578-4940"},"institutions":[{"id":"https://openalex.org/I167576493","display_name":"Colorado School of Mines","ror":"https://ror.org/04raf6v53","country_code":"US","type":"education","lineage":["https://openalex.org/I167576493"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zizhong Chen","raw_affiliation_strings":["Colorado Schml of Mines, Golden, CO, USA","Colorado School of Mines, Golden, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Colorado Schml of Mines, Golden, CO, USA","institution_ids":["https://openalex.org/I167576493"]},{"raw_affiliation_string":"Colorado School of Mines, Golden, USA","institution_ids":["https://openalex.org/I167576493"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I167576493"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4757","issue":null,"first_page":"1","last_page":"4"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994000196456909,"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":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8942753672599792},{"id":"https://openalex.org/keywords/mean-time-between-failures","display_name":"Mean time between failures","score":0.8585696220397949},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.818820595741272},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.7173797488212585},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.6819425225257874},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.4782544672489166},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.46940672397613525},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4435213506221771},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4093969762325287},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24699175357818604},{"id":"https://openalex.org/keywords/failure-rate","display_name":"Failure rate","score":0.17199262976646423},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.1465117633342743}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8942753672599792},{"id":"https://openalex.org/C44154001","wikidata":"https://www.wikidata.org/wiki/Q754940","display_name":"Mean time between failures","level":3,"score":0.8585696220397949},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.818820595741272},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.7173797488212585},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6819425225257874},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.4782544672489166},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.46940672397613525},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4435213506221771},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4093969762325287},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24699175357818604},{"id":"https://openalex.org/C163164238","wikidata":"https://www.wikidata.org/wiki/Q2737027","display_name":"Failure rate","level":2,"score":0.17199262976646423},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.1465117633342743},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdpsw.2010.5470810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2010.5470810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel &amp; Distributed Processing, Workshops and Phd Forum (IPDPSW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W64728161","https://openalex.org/W1559261530","https://openalex.org/W1697546184","https://openalex.org/W1974401809","https://openalex.org/W2102844000","https://openalex.org/W2128648139","https://openalex.org/W6678728210"],"related_works":["https://openalex.org/W1983353130","https://openalex.org/W168429299","https://openalex.org/W1513192318","https://openalex.org/W2064185557","https://openalex.org/W2781863720","https://openalex.org/W164281019","https://openalex.org/W2908016214","https://openalex.org/W2104929755","https://openalex.org/W2258317757","https://openalex.org/W4290043243"],"abstract_inverted_index":{"A":[0],"consequence":[1],"of":[2,8,68,83,122,136],"the":[3,6,21,42,69,99,111,120,130,134,139,157],"fact":[4],"that":[5,132],"number":[7,135],"processors":[9],"in":[10,63,129],"High":[11],"Performance":[12],"Computers":[13],"(HPC)":[14],"continues":[15],"to":[16,56,77,87,91,97,103,118,141],"increase":[17],"is":[18,38,53,86,127],"demonstrated":[19],"by":[20],"correlation":[22],"between":[23],"Mean-Time-To-Failure(T":[24],"<sub":[25,35],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[26,36],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">MTTF</sub>":[27,37],")":[28],"and":[29,166],"application":[30],"execution":[31,44],"time.":[32],"The":[33,81,125],"T":[34],"becoming":[39],"shorter":[40],"than":[41],"expected":[43],"time":[45],"for":[46],"many":[47,67],"next":[48,100],"generation":[49,101],"HPC":[50],"applications.":[51],"There":[52],"an":[54,89],"ability":[55,76],"handle":[57,142],"failure":[58,108],"without":[59,109],"a":[60,74,93],"system-wide":[61],"breakdown":[62],"most":[64],"architecture,":[65],"but":[66],"applications":[70,102],"do":[71],"not":[72],"have":[73],"built-in":[75],"survive":[78,104],"node":[79,105],"failures.":[80],"purpose":[82],"this":[84],"paper":[85],"present":[88,156],"approach":[90],"develop":[92,115],"highly":[94],"scalable":[95,128],"technique":[96,126],"allow":[98],"and/or":[106],"link":[107],"aborting":[110],"computation.":[112],"We":[113,154],"will":[114,155],"several":[116],"strategies":[117],"improve":[119],"scalability":[121],"diskless":[123],"checkpointing.":[124],"sense":[131],"when":[133],"processes":[137,147],"increases,":[138],"overhead":[140],"k":[143],"failures":[144],"on":[145],"p":[146],"should":[148],"remain":[149],"as":[150,152],"constant":[151],"possible.":[153],"proposed":[158],"technique,":[159],"initial":[160],"results":[161],"together":[162],"with":[163],"remaining":[164],"objectives":[165],"challenges.":[167]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}