{"id":"https://openalex.org/W2021234574","doi":"https://doi.org/10.1145/2642769.2642774","title":"Toward Local Failure Local Recovery Resilience Model using MPI-ULFM","display_name":"Toward Local Failure Local Recovery Resilience Model using MPI-ULFM","publication_year":2014,"publication_date":"2014-08-29","ids":{"openalex":"https://openalex.org/W2021234574","doi":"https://doi.org/10.1145/2642769.2642774","mag":"2021234574"},"language":"en","primary_location":{"id":"doi:10.1145/2642769.2642774","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2642769.2642774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st European MPI Users' Group Meeting","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/1319632","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019745966","display_name":"Keita Teranishi","orcid":"https://orcid.org/0000-0001-6647-2690"},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keita Teranishi","raw_affiliation_strings":["Sandia National Laboratories, P.O. Box 969, MS 9159 Livermore, CA 94551-0969, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, P.O. Box 969, MS 9159 Livermore, CA 94551-0969, U.S.A","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074276326","display_name":"Michael A. Heroux","orcid":"https://orcid.org/0000-0002-5893-0273"},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael A. Heroux","raw_affiliation_strings":["Sandia National Laboratories, P.O. Box 5800, MS 1320 Albuquerque, NM 87185-1320, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, P.O. Box 5800, MS 1320 Albuquerque, NM 87185-1320, U.S.A","institution_ids":["https://openalex.org/I192454743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I192454743"],"apc_list":null,"apc_paid":null,"fwci":10.4477,"has_fulltext":true,"cited_by_count":74,"citation_normalized_percentile":{"value":0.98430092,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"56"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9908000230789185,"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":0.9886000156402588,"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":0.8333711624145508},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7570433616638184},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.710094153881073},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6523830890655518},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6355677247047424},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4257989823818207},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.37115001678466797},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.25510579347610474}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8333711624145508},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7570433616638184},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.710094153881073},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6523830890655518},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6355677247047424},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4257989823818207},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.37115001678466797},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.25510579347610474},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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":2,"locations":[{"id":"doi:10.1145/2642769.2642774","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2642769.2642774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st European MPI Users' Group Meeting","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1319632","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1319632","pdf_url":"https://www.osti.gov/servlets/purl/1319632","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:1319632","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1319632","pdf_url":"https://www.osti.gov/servlets/purl/1319632","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":[{"id":"https://openalex.org/G3017597143","display_name":null,"funder_award_id":"DE-AC04-94AL85000","funder_id":"https://openalex.org/F4320338291","funder_display_name":"Sandia National Laboratories"},{"id":"https://openalex.org/G5827802491","display_name":null,"funder_award_id":"DE-AC04-94AL85000","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G7318852158","display_name":null,"funder_award_id":"AC04-94AL85000","funder_id":"https://openalex.org/F4320338291","funder_display_name":"Sandia National Laboratories"},{"id":"https://openalex.org/G8456466421","display_name":null,"funder_award_id":"AC04-94AL85000","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2021234574.pdf","grobid_xml":"https://content.openalex.org/works/W2021234574.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W170768260","https://openalex.org/W1551972236","https://openalex.org/W1570188389","https://openalex.org/W1779522739","https://openalex.org/W1984564341","https://openalex.org/W1997021720","https://openalex.org/W2022916138","https://openalex.org/W2048894106","https://openalex.org/W2095954861","https://openalex.org/W2105227455","https://openalex.org/W2108095339","https://openalex.org/W2128577831","https://openalex.org/W2133046454","https://openalex.org/W2165989201","https://openalex.org/W2168405877","https://openalex.org/W2296772319","https://openalex.org/W2949958961","https://openalex.org/W4255486661","https://openalex.org/W4295098767","https://openalex.org/W6676342289"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W2965083567","https://openalex.org/W4401278057","https://openalex.org/W1982914007","https://openalex.org/W2159583675","https://openalex.org/W1824242903","https://openalex.org/W1493858311","https://openalex.org/W2155470929","https://openalex.org/W2111125783","https://openalex.org/W2394465510"],"abstract_inverted_index":{"The":[0],"current":[1],"system":[2],"reaction":[3],"to":[4,13,61,81],"the":[5,16,21,24,59,75,83,90],"loss":[6],"of":[7,77,93],"a":[8,69,97],"single":[9],"MPI":[10],"process":[11,70,101],"is":[12,71],"kill":[14],"all":[15],"remaining":[17],"processes":[18],"and":[19,64,88],"restart":[20],"application":[22,56,66],"from":[23,100],"most":[25],"recent":[26],"checkpoint.":[27],"This":[28],"approach":[29],"will":[30],"become":[31],"unfeasible":[32],"for":[33],"future":[34],"extreme":[35],"scale":[36],"systems.":[37],"We":[38,73],"address":[39],"this":[40],"issue":[41],"using":[42,86],"an":[43],"emerging":[44],"resilient":[45,91],"computing":[46],"model":[47,85],"called":[48],"Local":[49,51],"Failure":[50],"Recovery":[52],"(LFLR)":[53],"that":[54,95],"provides":[55],"developers":[57],"with":[58],"ability":[60],"recover":[62],"locally":[63],"continue":[65],"execution":[67],"when":[68],"lost.":[72],"discuss":[74],"design":[76],"our":[78],"software":[79],"framework":[80],"enable":[82],"LFLR":[84],"MPI-ULFM":[87],"demonstrate":[89],"version":[92],"MiniFE":[94],"achieves":[96],"scalable":[98],"recovery":[99],"failures.":[102]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-10T07:45:09.275182","created_date":"2025-10-10T00:00:00"}