{"id":"https://openalex.org/W2604753019","doi":"https://doi.org/10.1109/igcc.2016.7892626","title":"Monitoring strategies for scalable dynamic checkpointing","display_name":"Monitoring strategies for scalable dynamic checkpointing","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2604753019","doi":"https://doi.org/10.1109/igcc.2016.7892626","mag":"2604753019"},"language":"en","primary_location":{"id":"doi:10.1109/igcc.2016.7892626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igcc.2016.7892626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Seventh International Green and Sustainable Computing Conference (IGSC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2117/103468","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106622856","display_name":"Swann Perarnau","orcid":"https://orcid.org/0000-0002-1029-0684"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Swann Perarnau","raw_affiliation_strings":["Argonne National Laboratory"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013543252","display_name":"Leonardo Bautista-Gomez","orcid":"https://orcid.org/0000-0002-0814-5779"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]},{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Leonardo Bautista-Gomez","raw_affiliation_strings":["Barcelona Supercomputing Center (BSC)"],"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC)","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5106622856"],"corresponding_institution_ids":["https://openalex.org/I1282105669"],"apc_list":null,"apc_paid":null,"fwci":0.2966,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69147026,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9995999932289124,"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":0.9995999932289124,"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":0.998199999332428,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8405193090438843},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8191641569137573},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.8019841313362122},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.7613694071769714},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6951707601547241},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5505648851394653},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5066936612129211},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.46002545952796936},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3208354413509369},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.28798678517341614},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11605378985404968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8405193090438843},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8191641569137573},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.8019841313362122},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.7613694071769714},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6951707601547241},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5505648851394653},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5066936612129211},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.46002545952796936},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3208354413509369},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.28798678517341614},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11605378985404968},{"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/igcc.2016.7892626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igcc.2016.7892626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Seventh International Green and Sustainable Computing Conference (IGSC)","raw_type":"proceedings-article"},{"id":"pmh:oai:recercat.cat:2072/283338","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/103468","pdf_url":null,"source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/submittedVersion"}],"best_oa_location":{"id":"pmh:oai:recercat.cat:2072/283338","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/103468","pdf_url":null,"source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/submittedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W384167648","https://openalex.org/W1578105119","https://openalex.org/W1581005283","https://openalex.org/W1965626898","https://openalex.org/W1966243865","https://openalex.org/W1981432246","https://openalex.org/W1999900893","https://openalex.org/W2025024269","https://openalex.org/W2032858539","https://openalex.org/W2033656974","https://openalex.org/W2038155581","https://openalex.org/W2039631162","https://openalex.org/W2081235423","https://openalex.org/W2089536264","https://openalex.org/W2115711419","https://openalex.org/W2120591095","https://openalex.org/W2125169487","https://openalex.org/W2133046454","https://openalex.org/W2137512117","https://openalex.org/W2142812297","https://openalex.org/W2160100693","https://openalex.org/W2169246841","https://openalex.org/W2170500888","https://openalex.org/W2263480027","https://openalex.org/W2318507312","https://openalex.org/W2491102031","https://openalex.org/W3006036681","https://openalex.org/W6613162932","https://openalex.org/W6633553838","https://openalex.org/W6658828644","https://openalex.org/W6692882405"],"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/W2064720525","https://openalex.org/W2111125783"],"abstract_inverted_index":{"Resilience":[0],"is":[1,46],"an":[2],"important":[3,47,75],"challenge":[4],"for":[5,117],"extreme-scale":[6],"supercomputers.":[7],"Failures":[8],"in":[9,18,26,33,48],"current":[10],"supercomputers":[11],"are":[12,30],"assumed":[13],"to":[14,50,54,67,77,86,103,113,129,144],"be":[15],"uniformly":[16],"distributed":[17],"time.":[19],"However,":[20],"recent":[21],"studies":[22],"show":[23],"that":[24,65],"failures":[25],"high-performance":[27],"computing":[28,71],"systems":[29],"partially":[31],"correlated":[32],"time,":[34],"generating":[35],"periods":[36,45],"of":[37,43,97,126,134],"higher":[38],"failure":[39],"density.":[40],"The":[41],"detection":[42],"those":[44,87],"order":[49],"adjust":[51],"the":[52,78,124,145],"system":[53,64,128],"new":[55],"conditions.":[56],"In":[57,120],"this":[58,98],"paper":[59],"we":[60,122],"present":[61],"a":[62],"monitoring":[63],"listens":[66],"hardware":[68],"events":[69,76,135],"across":[70],"nodes":[72],"and":[73,141],"forwards":[74],"fault":[79],"tolerance":[80],"runtime":[81],"so":[82],"it":[83],"can":[84],"react":[85],"regime":[88],"changes.":[89],"Our":[90],"evaluation":[91],"at":[92],"scale":[93],"shows":[94],"several":[95],"aspects":[96],"dynamic":[99],"checkpointing":[100],"scheme,":[101],"critical":[102],"understanding":[104],"its":[105],"applicability":[106],"on":[107],"production":[108],"systems,":[109],"as":[110,112,131,136],"well":[111],"identifying":[114],"possible":[115],"avenues":[116],"future":[118],"improvements.":[119],"particular,":[121],"evaluate":[123],"ability":[125],"our":[127],"monitor":[130],"many":[132],"types":[133],"possible,":[137],"measure":[138],"their":[139],"importance,":[140],"forward":[142],"them":[143],"resilience":[146],"runtime.":[147]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
