{"id":"https://openalex.org/W2067021722","doi":"https://doi.org/10.1145/1131322.1131340","title":"Performance evaluation of automatic checkpoint-based fault tolerance for AMPI and Charm++","display_name":"Performance evaluation of automatic checkpoint-based fault tolerance for AMPI and Charm++","publication_year":2006,"publication_date":"2006-04-01","ids":{"openalex":"https://openalex.org/W2067021722","doi":"https://doi.org/10.1145/1131322.1131340","mag":"2067021722"},"language":"en","primary_location":{"id":"doi:10.1145/1131322.1131340","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1131322.1131340","pdf_url":null,"source":{"id":"https://openalex.org/S50071195","display_name":"ACM SIGOPS Operating Systems Review","issn_l":"0163-5980","issn":["0163-5980","1943-586X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGOPS Operating Systems Review","raw_type":"journal-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":["University of Illinois at Urbana-Champaign","University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101630875","display_name":"Chao Huang","orcid":"https://orcid.org/0000-0002-0887-1316"},"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":"Chao Huang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana Champaign","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. Kal\u00e9","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana Champaign","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":2.1125,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.88346883,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"40","issue":"2","first_page":"90","last_page":"99"},"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":0.9926000237464905,"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":0.9829999804496765,"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":0.9069422483444214},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7600985765457153},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6608462333679199},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6525498032569885},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6147378087043762},{"id":"https://openalex.org/keywords/charm","display_name":"Charm (quantum number)","score":0.48797982931137085},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4583001732826233},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.45776230096817017},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32790765166282654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.0835096538066864},{"id":"https://openalex.org/keywords/particle-physics","display_name":"Particle physics","score":0.06311765313148499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9069422483444214},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7600985765457153},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6608462333679199},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6525498032569885},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6147378087043762},{"id":"https://openalex.org/C2781339351","wikidata":"https://www.wikidata.org/wiki/Q2639620","display_name":"Charm (quantum number)","level":2,"score":0.48797982931137085},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4583001732826233},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.45776230096817017},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32790765166282654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0835096538066864},{"id":"https://openalex.org/C109214941","wikidata":"https://www.wikidata.org/wiki/Q18334","display_name":"Particle physics","level":1,"score":0.06311765313148499},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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:10.1145/1131322.1131340","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1131322.1131340","pdf_url":null,"source":{"id":"https://openalex.org/S50071195","display_name":"ACM SIGOPS Operating Systems Review","issn_l":"0163-5980","issn":["0163-5980","1943-586X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGOPS Operating Systems Review","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4000000059604645}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320312143","display_name":"National Centre for Supercomputing Applications","ror":"https://ror.org/03r10zj06"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W34870269","https://openalex.org/W161943517","https://openalex.org/W1513913200","https://openalex.org/W1537929875","https://openalex.org/W1539436949","https://openalex.org/W1551467297","https://openalex.org/W1633989273","https://openalex.org/W1923741182","https://openalex.org/W1971952282","https://openalex.org/W2046309377","https://openalex.org/W2081413727","https://openalex.org/W2099938240","https://openalex.org/W2109942844","https://openalex.org/W2114035455","https://openalex.org/W2131053137","https://openalex.org/W2133201251","https://openalex.org/W2133287150","https://openalex.org/W2155204206","https://openalex.org/W2171453084","https://openalex.org/W3149999634","https://openalex.org/W4206313509","https://openalex.org/W4237816542","https://openalex.org/W6606635309","https://openalex.org/W6679612526","https://openalex.org/W6818786110"],"related_works":["https://openalex.org/W2358129534","https://openalex.org/W3023233353","https://openalex.org/W2351104570","https://openalex.org/W3102190134","https://openalex.org/W2377029499","https://openalex.org/W2391638466","https://openalex.org/W2808286815","https://openalex.org/W4254547616","https://openalex.org/W2064720525","https://openalex.org/W2111125783"],"abstract_inverted_index":{"As":[0],"the":[1,8,36,39,52,61,87,97,118,143,146],"size":[2],"of":[3,10,38,89,106,133,145],"high":[4],"performance":[5],"clusters":[6],"multiplies,":[7],"probability":[9],"system":[11],"failure":[12],"grows":[13],"substantially,":[14],"posing":[15],"an":[16],"increasingly":[17],"significant":[18,68],"challenge":[19],"for":[20,71],"scalability.":[21],"Checkpoint-based":[22],"fault":[23,50,82],"tolerance":[24,83],"methods":[25],"are":[26,110],"effective":[27],"approaches":[28],"at":[29],"dealing":[30],"with":[31],"faults.":[32],"With":[33],"these":[34],"methods,":[35],"state":[37],"entire":[40],"parallel":[41],"application":[42,53,62],"is":[43,54,64],"checkpointed":[44],"to":[45,66,99,129],"reliable":[46],"storage.":[47],"When":[48],"a":[49,57,103,130],"occurs,":[51],"restarted":[55,101],"from":[56],"recent":[58],"checkpoint.":[59],"However,":[60],"developer":[63],"required":[65],"write":[67],"additional":[69],"code":[70],"checkpointing":[72,81,90],"and":[73,79,91,122,125,148],"restarting.":[74,92],"This":[75],"paper":[76],"describes":[77],"disk-based":[78],"memory-based":[80],"schemes":[84,94,109],"that":[85],"automate":[86],"task":[88],"The":[93],"also":[95],"allow":[96],"program":[98],"be":[100,127],"on":[102,112],"different":[104],"number":[105],"processors.":[107],"These":[108],"based":[111],"self-checkpointable,":[113],"migratable":[114],"objects":[115],"supported":[116],"by":[117],"Adaptive":[119],"MPI":[120,137],"(AMPI)":[121],"Charm++":[123],"run-time":[124],"can":[126],"applied":[128],"wide":[131],"class":[132],"applications":[134],"written":[135],"using":[136],"or":[138],"message-driven":[139],"languages.":[140],"We":[141],"demonstrate":[142],"effectiveness":[144],"strategies":[147],"evaluate":[149],"their":[150],"performance.":[151]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
