{"id":"https://openalex.org/W2791029364","doi":"https://doi.org/10.1109/igcc.2017.8323598","title":"Optimizing checkpoint intervals for reduced energy use in exascale systems","display_name":"Optimizing checkpoint intervals for reduced energy use in exascale systems","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2791029364","doi":"https://doi.org/10.1109/igcc.2017.8323598","mag":"2791029364"},"language":"en","primary_location":{"id":"doi:10.1109/igcc.2017.8323598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igcc.2017.8323598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Eighth International Green and Sustainable Computing Conference (IGSC)","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/A5043706893","display_name":"Daniel Dauwe","orcid":"https://orcid.org/0000-0002-6858-8221"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Dauwe","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Colorado State University, Fort Collins, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Colorado State University, Fort Collins, CO, USA","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036331541","display_name":"Rohan Jhaveri","orcid":null},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohan Jhaveri","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Colorado State University, Fort Collins, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Colorado State University, Fort Collins, CO, USA","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018382547","display_name":"Sudeep Pasricha","orcid":"https://orcid.org/0000-0002-0846-0066"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudeep Pasricha","raw_affiliation_strings":["Department of Computer Science, Colorado State University, Fort Collins, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Colorado State University, Fort Collins, CO, USA","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014854157","display_name":"Anthony A. Maciejewski","orcid":"https://orcid.org/0000-0002-1376-5825"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony A. Maciejewski","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Colorado State University, Fort Collins, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Colorado State University, Fort Collins, CO, USA","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071577167","display_name":"Howard Jay Siegel","orcid":"https://orcid.org/0000-0001-6025-4916"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Howard Jay Siegel","raw_affiliation_strings":["Department of Computer Science, Colorado State University, Fort Collins, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Colorado State University, Fort Collins, CO, USA","institution_ids":["https://openalex.org/I92446798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0384,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.93440803,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"3","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9994999766349792,"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":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.8098556995391846},{"id":"https://openalex.org/keywords/mean-time-between-failures","display_name":"Mean time between failures","score":0.7716708183288574},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.6396802067756653},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6309336423873901},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5402431488037109},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5328218340873718},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.5105389356613159},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.48849499225616455},{"id":"https://openalex.org/keywords/interval","display_name":"Interval (graph theory)","score":0.4834071695804596},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4593870937824249},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.45133477449417114},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4369049668312073},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4051669239997864},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.35116004943847656},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17923980951309204},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08142095804214478},{"id":"https://openalex.org/keywords/failure-rate","display_name":"Failure rate","score":0.07347586750984192}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8098556995391846},{"id":"https://openalex.org/C44154001","wikidata":"https://www.wikidata.org/wiki/Q754940","display_name":"Mean time between failures","level":3,"score":0.7716708183288574},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.6396802067756653},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6309336423873901},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5402431488037109},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5328218340873718},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.5105389356613159},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.48849499225616455},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.4834071695804596},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4593870937824249},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45133477449417114},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4369049668312073},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4051669239997864},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35116004943847656},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17923980951309204},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08142095804214478},{"id":"https://openalex.org/C163164238","wikidata":"https://www.wikidata.org/wiki/Q2737027","display_name":"Failure rate","level":2,"score":0.07347586750984192},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/igcc.2017.8323598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igcc.2017.8323598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Eighth International Green and Sustainable Computing Conference (IGSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W63848143","https://openalex.org/W1553890549","https://openalex.org/W1679222828","https://openalex.org/W1733470504","https://openalex.org/W1984564341","https://openalex.org/W1991872262","https://openalex.org/W1997274513","https://openalex.org/W2001495258","https://openalex.org/W2008668366","https://openalex.org/W2018430781","https://openalex.org/W2025024269","https://openalex.org/W2033656974","https://openalex.org/W2035492130","https://openalex.org/W2037730929","https://openalex.org/W2039345646","https://openalex.org/W2056863651","https://openalex.org/W2058135584","https://openalex.org/W2060573894","https://openalex.org/W2133046454","https://openalex.org/W2320681231","https://openalex.org/W2466475476","https://openalex.org/W2475126267","https://openalex.org/W2498809433","https://openalex.org/W2510919118","https://openalex.org/W2567534547","https://openalex.org/W2602474119","https://openalex.org/W2728335099","https://openalex.org/W2893613126","https://openalex.org/W2966565333"],"related_works":["https://openalex.org/W1983353130","https://openalex.org/W168429299","https://openalex.org/W1513192318","https://openalex.org/W2064185557","https://openalex.org/W2384867379","https://openalex.org/W2081804767","https://openalex.org/W2114661492","https://openalex.org/W2059606485","https://openalex.org/W4251879367","https://openalex.org/W2564310820"],"abstract_inverted_index":{"In":[0],"today's":[1],"high":[2],"performance":[3,148,175],"computing":[4],"(HPC)":[5],"systems,":[6],"the":[7,17,20,84,89,112,127,138,192,196],"probability":[8],"of":[9,22,41,70,115,129,168,198],"applications":[10],"experiencing":[11],"failures":[12,39],"has":[13,103],"increased":[14],"significantly":[15],"with":[16,35,92],"increase":[18],"in":[19,51,61,79,153,203],"number":[21],"system":[23,63,136,205],"nodes.":[24],"It":[25],"is":[26],"expected":[27],"that":[28,64,106,133,144,181],"exascale-sized":[29],"systems":[30,82,116],"are":[31],"likely":[32],"to":[33,108,140,162,171,201],"operate":[34],"mean":[36],"time":[37],"between":[38,142],"(MTBF)":[40],"as":[42,44,54,56,88],"little":[43],"a":[45,62,123,135,155,166],"few":[46],"minutes,":[47],"causing":[48],"frequent":[49],"interrupts":[50],"application":[52,147,208],"execution":[53],"well":[55],"substantially":[57],"greater":[58],"energy":[59,85,99,113,151,178],"costs":[60],"will":[65],"already":[66],"consume":[67],"large":[68],"amounts":[69],"energy.":[71],"State-of-the-art":[72],"HPC":[73],"resilience":[74,118],"techniques":[75,95],"proposed":[76],"for":[77,146,173,187],"use":[78,114,152],"these":[80,94],"future":[81],"complicate":[83],"problem":[86],"further":[87,97],"overhead":[90],"associated":[91],"utilizing":[93,117],"also":[96],"increases":[98],"use.":[100],"While":[101],"work":[102,121],"been":[104],"done":[105],"attempts":[107],"analyze":[109],"and":[110,158,194,207],"improve":[111],"techniques,":[119],"our":[120],"offers":[122],"new":[124],"approach":[125,161],"through":[126],"optimization":[128],"checkpoint":[130,157,160],"interval":[131],"lengths":[132],"allows":[134],"designer":[137],"freedom":[139],"choose":[141],"intervals":[143,183],"optimize":[145,172],"efficiency":[149,176],"or":[150,177,191],"both":[154],"traditional":[156],"multilevel":[159],"resilience.":[163],"We":[164],"create":[165],"set":[167],"equations":[169],"able":[170],"either":[174,188],"use,":[179],"demonstrate":[180],"distinct":[182],"exist":[184],"when":[185],"optimizing":[186],"one":[189],"metric":[190],"other,":[193],"examine":[195],"sensitivity":[197],"this":[199],"phenomena":[200],"changes":[202],"several":[204],"parameters":[206],"characteristics.":[209]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}