{"id":"https://openalex.org/W2072672002","doi":"https://doi.org/10.1109/dsnw.2012.6264668","title":"Asynchronous checkpoint migration with MRNet in the Scalable Checkpoint / Restart Library","display_name":"Asynchronous checkpoint migration with MRNet in the Scalable Checkpoint / Restart Library","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2072672002","doi":"https://doi.org/10.1109/dsnw.2012.6264668","mag":"2072672002"},"language":"en","primary_location":{"id":"doi:10.1109/dsnw.2012.6264668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsnw.2012.6264668","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/1047769","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080122988","display_name":"Kathryn Mohror","orcid":"https://orcid.org/0000-0002-1366-1655"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kathryn Mohror","raw_affiliation_strings":["Lawrence Livemore National Laboratory, USA","Lawrence Livermore National Laboratory USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livemore National Laboratory, USA","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence Livermore National Laboratory USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068423553","display_name":"Adam Moody","orcid":null},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Moody","raw_affiliation_strings":["Lawrence Livemore National Laboratory, USA","Lawrence Livermore National Laboratory USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livemore National Laboratory, USA","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence Livermore National Laboratory USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058719424","display_name":"Bronis R. de Supinski","orcid":"https://orcid.org/0000-0002-0339-1006"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bronis R. de Supinski","raw_affiliation_strings":["Lawrence Livemore National Laboratory, USA","Lawrence Livermore National Laboratory USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livemore National Laboratory, USA","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence Livermore National Laboratory USA","institution_ids":["https://openalex.org/I1282311441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1282311441"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11181","display_name":"Advanced Data Storage Technologies","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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9977999925613403,"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":0.8430644869804382},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7910481691360474},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6298991441726685},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5653971433639526},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5109878778457642},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.4523018002510071},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4305090308189392},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4227273464202881},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4161544442176819},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3037731647491455}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8430644869804382},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7910481691360474},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6298991441726685},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5653971433639526},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5109878778457642},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.4523018002510071},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4305090308189392},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4227273464202881},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4161544442176819},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3037731647491455},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/dsnw.2012.6264668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsnw.2012.6264668","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:osti.gov:1047769","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1047769","pdf_url":"https://www.osti.gov/servlets/purl/1047769","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},{"id":"pmh:info:ark/67531/metadc829263","is_oa":false,"landing_page_url":"https://digital.library.unt.edu/ark:/67531/metadc829263/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400792","display_name":"University of North Texas Digital Library (University of North Texas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123534392","host_organization_name":"University of North Texas","host_organization_lineage":["https://openalex.org/I123534392"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Presented at: Workshop on Fault-Tolerance for HPC at Extreme Scale (FTXS 2012), Boston, MA, United States, Jun 25 - Jun 28, 2012","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:osti.gov:1047769","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1047769","pdf_url":"https://www.osti.gov/servlets/purl/1047769","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":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G5522089832","display_name":null,"funder_award_id":"DE-AC52-07NA27344","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"},{"id":"https://openalex.org/G8374966015","display_name":null,"funder_award_id":"AC52-07NA27344","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G991281326","display_name":null,"funder_award_id":"AC52-07NA27344","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2072672002.pdf","grobid_xml":"https://content.openalex.org/works/W2072672002.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1558516248","https://openalex.org/W1792708371","https://openalex.org/W1981432246","https://openalex.org/W1984564341","https://openalex.org/W2006743077","https://openalex.org/W2043522772","https://openalex.org/W2087275952","https://openalex.org/W2089536264","https://openalex.org/W2104129492","https://openalex.org/W2106913893","https://openalex.org/W2116768598","https://openalex.org/W2118582701","https://openalex.org/W2128854702","https://openalex.org/W2142471151","https://openalex.org/W2150697658","https://openalex.org/W2163295644","https://openalex.org/W2167563208","https://openalex.org/W2171371822","https://openalex.org/W2296772319","https://openalex.org/W2983146677","https://openalex.org/W3150262005","https://openalex.org/W6638443947","https://openalex.org/W6672627820","https://openalex.org/W6679232093","https://openalex.org/W6769711090"],"related_works":["https://openalex.org/W595346907","https://openalex.org/W153296825","https://openalex.org/W598989511","https://openalex.org/W2375779923","https://openalex.org/W2041986468","https://openalex.org/W1967800214","https://openalex.org/W2055675609","https://openalex.org/W4388001050","https://openalex.org/W2245277136","https://openalex.org/W3013668398"],"abstract_inverted_index":{"Applications":[0],"running":[1],"on":[2,15],"today's":[3],"supercomputers":[4],"tolerate":[5],"failures":[6],"by":[7,86,121],"periodically":[8],"saving":[9],"their":[10],"state":[11],"in":[12,118],"checkpoint":[13],"files":[14],"stable":[16],"storage,":[17],"such":[18],"as":[19,122,124],"a":[20,63],"parallel":[21,77,101],"file":[22,78,102],"system.":[23,103],"Although":[24],"this":[25,43],"approach":[26],"is":[27],"simple,":[28],"the":[29,33,72,76,88,100,107,115,139,142],"overhead":[30],"of":[31,49,109,141],"writing":[32],"checkpoints":[34,70,96],"can":[35,113],"be":[36],"prohibitive,":[37],"especially":[38],"for":[39,90],"large-scale":[40],"jobs.":[41],"In":[42],"paper,":[44],"we":[45],"present":[46],"initial":[47,135],"results":[48],"an":[50,91],"enhancement":[51,82],"to":[52,68,75,93,99,148],"our":[53,127,134,146],"Scalable":[54],"Checkpoint":[55],"/":[56],"Restart":[57],"Library":[58],"(SCR).":[59],"We":[60,104,137],"employ":[61],"MRNet,":[62],"tree-based":[64],"overlay":[65],"network":[66],"library,":[67],"transfer":[69],"from":[71],"compute":[73],"nodes":[74],"system":[79],"asynchronously.":[80],"This":[81],"increases":[83],"application":[84,92],"efficiency":[85],"removing":[87],"need":[89],"block":[94],"while":[95],"are":[97],"transferred":[98],"show":[105],"that":[106],"integration":[108],"SCR":[110],"with":[111,133],"MRNet":[112],"reduce":[114],"time":[116],"spent":[117],"I/O":[119],"operations":[120],"much":[123],"15\u00d7.":[125],"However,":[126],"experiments":[128],"exposed":[129],"new":[130],"scalability":[131,143],"issues":[132],"implementation.":[136],"discuss":[138],"sources":[140],"problems":[144],"and":[145],"plans":[147],"address":[149],"them.":[150]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2025-10-10T00:00:00"}