{"id":"https://openalex.org/W2031260715","doi":"https://doi.org/10.1109/dsnw.2012.6264677","title":"A scalable double in-memory checkpoint and restart scheme towards exascale","display_name":"A scalable double in-memory checkpoint and restart scheme towards exascale","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2031260715","doi":"https://doi.org/10.1109/dsnw.2012.6264677","mag":"2031260715"},"language":"en","primary_location":{"id":"doi:10.1109/dsnw.2012.6264677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsnw.2012.6264677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN 2012)","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/A5109069612","display_name":"Gengbin Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gengbin Zheng","raw_affiliation_strings":["Department of Computer Science, University of Illinois, Urbana-Champaign, Urbana, IL, USA","Department of Computer Science, University of Illinois at Urbana-Champaign, 61801, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois, Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign, 61801, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086688855","display_name":"Xiang Ni","orcid":"https://orcid.org/0000-0002-2601-7367"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Ni","raw_affiliation_strings":["Department of Computer Science, University of Illinois, Urbana-Champaign, Urbana, IL, USA","Department of Computer Science, University of Illinois at Urbana-Champaign, 61801, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois, Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign, 61801, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051465480","display_name":"Laxmikant V. Kal\u00e9","orcid":"https://orcid.org/0000-0001-9673-8445"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laxmikant V. Kale","raw_affiliation_strings":["Department of Computer Science, University of Illinois, Urbana-Champaign, Urbana, IL, USA","Department of Computer Science, University of Illinois at Urbana-Champaign, 61801, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois, Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign, 61801, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5109069612"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":15.9784,"has_fulltext":false,"cited_by_count":99,"citation_normalized_percentile":{"value":0.99270561,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9940000176429749,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9916999936103821,"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":0.8490146398544312},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8117968440055847},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7012221813201904},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6510262489318848},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.6263567805290222},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.5472204685211182},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4102446436882019},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.36701124906539917},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.32619744539260864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8490146398544312},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8117968440055847},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7012221813201904},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6510262489318848},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.6263567805290222},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.5472204685211182},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4102446436882019},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.36701124906539917},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.32619744539260864},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/dsnw.2012.6264677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsnw.2012.6264677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN 2012)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.498.3510","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.498.3510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://charm.cs.illinois.edu/newPapers/12-12/paper.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W34870269","https://openalex.org/W1603470798","https://openalex.org/W1981432246","https://openalex.org/W1984564341","https://openalex.org/W2001495258","https://openalex.org/W2033656974","https://openalex.org/W2046309377","https://openalex.org/W2067021722","https://openalex.org/W2109942844","https://openalex.org/W2116115793","https://openalex.org/W2133046454","https://openalex.org/W2133201251","https://openalex.org/W2155204206","https://openalex.org/W2159027807","https://openalex.org/W2160779498","https://openalex.org/W2171938442","https://openalex.org/W2610607207","https://openalex.org/W3143778233","https://openalex.org/W3150262005","https://openalex.org/W6601359364","https://openalex.org/W6676276647","https://openalex.org/W6682581173","https://openalex.org/W6683531572","https://openalex.org/W6684853765","https://openalex.org/W6818786110"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W4235240664","https://openalex.org/W2965083567","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W2889616422","https://openalex.org/W2089704382","https://openalex.org/W2064720525","https://openalex.org/W2111125783","https://openalex.org/W1906576859"],"abstract_inverted_index":{"As":[0],"the":[1,6,44,47,60,97,109,121,148],"size":[2],"of":[3,8,46,144],"supercomputers":[4],"increases,":[5],"probability":[7],"system":[9],"failure":[10,58],"grows":[11],"substantially,":[12],"posing":[13],"an":[14,74],"increasingly":[15],"significant":[16],"challenge":[17],"for":[18,26,89],"scalability.":[19],"It":[20],"is":[21,51,62],"important":[22],"to":[23,53,113,141,159],"provide":[24],"resilience":[25],"long":[27],"running":[28,131],"applications.":[29],"Checkpoint-based":[30],"fault":[31,81],"tolerance":[32,82],"methods":[33],"are":[34],"effective":[35],"approaches":[36],"at":[37],"dealing":[38],"with":[39],"faults.":[40],"With":[41],"these":[42],"methods,":[43],"state":[45],"entire":[48],"parallel":[49,87],"application":[50,61],"checkpointed":[52],"reliable":[54],"storage.":[55],"When":[56],"a":[57,65,132,145],"occurs,":[59],"restarted":[63],"from":[64],"recent":[66],"checkpoint.":[67],"In":[68,91],"previous":[69],"work,":[70],"we":[71,94],"have":[72],"demonstrated":[73],"efficient":[75],"double":[76],"in-memory":[77,110],"checkpoint":[78,149],"and":[79,119],"restart":[80,155],"scheme,":[83],"which":[84],"leverages":[85],"Charm++'s":[86],"objects":[88],"checkpointing.":[90],"this":[92],"paper,":[93],"further":[95],"optimize":[96],"scheme":[98,112],"by":[99,104],"eliminating":[100],"several":[101],"bottlenecks":[102],"caused":[103],"serialized":[105],"communication.":[106],"We":[107],"extend":[108],"checkpointing":[111],"work":[114],"on":[115,123,139,165],"MPI":[116],"communication":[117],"layer,":[118],"demonstrate":[120],"performance":[122],"very":[124],"large":[125],"scale":[126],"supercomputers.":[127],"For":[128],"example,":[129],"when":[130],"one":[133],"million":[134],"atom":[135],"molecular":[136],"dynamics":[137],"simulation":[138],"up":[140],"64K":[142,166],"cores":[143],"BlueGene/P":[146],"machine,":[147],"time":[150,156],"was":[151,157],"in":[152],"milliseconds.":[153],"The":[154],"measured":[158],"be":[160],"less":[161],"than":[162],"0.15":[163],"seconds":[164],"cores.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":16},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
