{"id":"https://openalex.org/W2409054174","doi":"https://doi.org/10.1145/2925426.2926295","title":"Mini-Ckpts","display_name":"Mini-Ckpts","publication_year":2016,"publication_date":"2016-06-01","ids":{"openalex":"https://openalex.org/W2409054174","doi":"https://doi.org/10.1145/2925426.2926295","mag":"2409054174"},"language":"en","primary_location":{"id":"doi:10.1145/2925426.2926295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2925426.2926295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1530502","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091176753","display_name":"David Fiala","orcid":"https://orcid.org/0000-0001-5497-1468"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Fiala","raw_affiliation_strings":["North Carolina State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031749427","display_name":"Frank Mueller","orcid":"https://orcid.org/0000-0002-0258-0294"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank Mueller","raw_affiliation_strings":["North Carolina State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020783484","display_name":"Kurt Brian Ferreira","orcid":"https://orcid.org/0000-0001-5607-5691"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kurt Ferreira","raw_affiliation_strings":["Sandia National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratory","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019453159","display_name":"Christian Engelmann","orcid":"https://orcid.org/0000-0003-4365-6416"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christian Engelmann","raw_affiliation_strings":["Oak Ridge National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9972000122070312,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.996399998664856,"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/computer-science","display_name":"Computer science","score":0.7938249111175537},{"id":"https://openalex.org/keywords/reboot","display_name":"Reboot","score":0.7903900146484375},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7862921953201294},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5696422457695007},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5667750239372253},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5352910757064819},{"id":"https://openalex.org/keywords/software-fault-tolerance","display_name":"Software fault tolerance","score":0.4770457148551941},{"id":"https://openalex.org/keywords/mean-time-between-failures","display_name":"Mean time between failures","score":0.4643201231956482},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4486548602581024},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.4457891583442688},{"id":"https://openalex.org/keywords/crash","display_name":"Crash","score":0.44172123074531555},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4391351640224457},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3746691346168518},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36077624559402466},{"id":"https://openalex.org/keywords/failure-rate","display_name":"Failure rate","score":0.24400058388710022},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0953456461429596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7938249111175537},{"id":"https://openalex.org/C120524526","wikidata":"https://www.wikidata.org/wiki/Q1709148","display_name":"Reboot","level":2,"score":0.7903900146484375},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7862921953201294},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5696422457695007},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5667750239372253},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5352910757064819},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.4770457148551941},{"id":"https://openalex.org/C44154001","wikidata":"https://www.wikidata.org/wiki/Q754940","display_name":"Mean time between failures","level":3,"score":0.4643201231956482},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4486548602581024},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.4457891583442688},{"id":"https://openalex.org/C183469790","wikidata":"https://www.wikidata.org/wiki/Q333501","display_name":"Crash","level":2,"score":0.44172123074531555},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4391351640224457},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3746691346168518},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36077624559402466},{"id":"https://openalex.org/C163164238","wikidata":"https://www.wikidata.org/wiki/Q2737027","display_name":"Failure rate","level":2,"score":0.24400058388710022},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0953456461429596},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2925426.2926295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2925426.2926295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1530502","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1530502","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1530502","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1530502","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W8329419","https://openalex.org/W39601649","https://openalex.org/W185651294","https://openalex.org/W308775487","https://openalex.org/W1978082708","https://openalex.org/W1988023100","https://openalex.org/W1993660990","https://openalex.org/W1997021720","https://openalex.org/W2000739449","https://openalex.org/W2011754166","https://openalex.org/W2020115430","https://openalex.org/W2034101145","https://openalex.org/W2036473597","https://openalex.org/W2044920626","https://openalex.org/W2065426242","https://openalex.org/W2083613288","https://openalex.org/W2089536264","https://openalex.org/W2109192777","https://openalex.org/W2111464525","https://openalex.org/W2112121929","https://openalex.org/W2112160949","https://openalex.org/W2113809909","https://openalex.org/W2119018856","https://openalex.org/W2120591095","https://openalex.org/W2122249806","https://openalex.org/W2126523385","https://openalex.org/W2130934773","https://openalex.org/W2132213430","https://openalex.org/W2140991542","https://openalex.org/W2148109481","https://openalex.org/W2154817671","https://openalex.org/W2164590718","https://openalex.org/W2165022815","https://openalex.org/W2294406256","https://openalex.org/W2998208529","https://openalex.org/W3003432522","https://openalex.org/W6679516117"],"related_works":["https://openalex.org/W2769385735","https://openalex.org/W2318035278","https://openalex.org/W2316993527","https://openalex.org/W2971479921","https://openalex.org/W3145923041","https://openalex.org/W2946906624","https://openalex.org/W841176518","https://openalex.org/W1978919910","https://openalex.org/W2157727563","https://openalex.org/W2101077206"],"abstract_inverted_index":{"Concern":[0],"is":[1,48,139,153,177,224],"growing":[2],"in":[3,39,88,100,141,218],"the":[4,10,25,30,58,64,91,117,133,146,149,151,160,166,211,219,234,245],"high-performance":[5],"computing":[6],"(HPC)":[7],"community":[8],"on":[9,20],"reliability":[11],"of":[12,57,67,79,97,119,191,197,221,231,254],"future":[13],"extreme-scale":[14],"systems.":[15],"Current":[16],"efforts":[17],"have":[18,35],"focused":[19],"application":[21,81,114,161],"fault-tolerance":[22,205,232],"rather":[23],"than":[24,233],"operating":[26,212],"system":[27],"(OS),":[28],"despite":[29,116],"fact":[31],"that":[32,37,132,210],"recent":[33],"studies":[34],"suggested":[36],"failures":[38,99],"OS":[40,47,92,122,152],"memory":[41,143],"may":[42],"be":[43,95],"more":[44],"likely.":[45],"The":[46,171],"critical":[49,134],"to":[50,82,85,145,179,183,203,247],"a":[51,101,110,120,137,156,188,195,225],"system's":[52],"correct":[53],"and":[54,60,159,168,174,186,213,228,251],"efficient":[55],"operation":[56],"node":[59,73],"processes":[61,78],"it":[62],"governs---and":[63],"parallel":[65],"nature":[66],"HPC":[68,199],"applications":[69],"means":[70],"any":[71],"single":[72],"failure":[74,123,167],"generally":[75],"forces":[76],"all":[77],"this":[80,105,128,207,242],"terminate":[83],"due":[84],"tight":[86],"communication":[87],"HPC.":[89],"Therefore,":[90],"itself":[93],"must":[94],"capable":[96],"tolerating":[98],"robust":[102],"system.":[103],"In":[104,201],"work,":[106],"we":[107],"introduce":[108],"mini-ckpts,":[109],"framework":[111],"which":[112],"enables":[113,252],"survival":[115],"occurrence":[118],"fatal":[121],"or":[124],"crash.":[125],"mini-ckpts":[126,172],"achieves":[127],"tolerance":[129],"by":[130],"ensuring":[131],"data":[135],"describing":[136],"process":[138,176],"preserved":[140],"persistent":[142],"prior":[144],"failure.":[147],"Following":[148],"failure,":[150],"rejuvenated":[154],"via":[155],"warm":[157],"reboot":[158],"continues":[162],"execution":[163],"effectively":[164],"making":[165],"restart":[169],"transparent.":[170],"rejuvenation":[173],"recovery":[175],"measured":[178],"take":[180],"between":[181,192],"three":[182],"six":[184],"seconds":[185],"has":[187,244],"failure-free":[189],"overhead":[190],"3-5%":[193],"for":[194],"number":[196],"key":[198],"workloads.":[200],"contrast":[202],"current":[204,235],"methods,":[206],"work":[208],"ensures":[209],"runtime":[214],"systems":[215],"can":[216],"continue":[217],"presence":[220],"faults.":[222,256],"This":[223],"much":[226],"finer-grained":[227],"dynamic":[229],"method":[230],"coarse-grained":[236],"application-centric":[237],"methods.":[238],"Handling":[239],"faults":[240],"at":[241],"level":[243],"potential":[246],"greatly":[248],"reduce":[249],"overheads":[250],"mitigation":[253],"additional":[255]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-06-24T00:00:00"}
