{"id":"https://openalex.org/W2045879521","doi":"https://doi.org/10.1177/1094342005056139","title":"The Lam/Mpi Checkpoint/Restart Framework: System-Initiated Checkpointing","display_name":"The Lam/Mpi Checkpoint/Restart Framework: System-Initiated Checkpointing","publication_year":2005,"publication_date":"2005-11-01","ids":{"openalex":"https://openalex.org/W2045879521","doi":"https://doi.org/10.1177/1094342005056139","mag":"2045879521"},"language":"en","primary_location":{"id":"doi:10.1177/1094342005056139","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342005056139","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","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/A5049396814","display_name":"Sriram Sankaran","orcid":"https://orcid.org/0000-0002-7395-9242"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sriram Sankaran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112376463","display_name":"Jeffrey M. Squyres","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeffrey M. Squyres","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072932958","display_name":"Brian Barrett","orcid":"https://orcid.org/0000-0002-4380-4020"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Barrett","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066645529","display_name":"Vishal Sahay","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vishal Sahay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074260102","display_name":"Andrew Lumsdaine","orcid":"https://orcid.org/0000-0002-9153-6622"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew Lumsdaine","raw_affiliation_strings":["OPEN SYSTEMS LABORATORY, INDIANA UNIVERSITY BLOOMINGTON, IN 47404, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPEN SYSTEMS LABORATORY, INDIANA UNIVERSITY BLOOMINGTON, IN 47404, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090151651","display_name":"Jason Duell","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jason Duell","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010244689","display_name":"Paul Hargrove","orcid":"https://orcid.org/0000-0001-6691-5287"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Hargrove","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5109844591","display_name":"Eric Roman","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Roman","raw_affiliation_strings":["LAWRENCE BERKELEY NATIONAL LABORATORY BERKELEY, CA 94720, USA","Lawrence Berkeley National Laboratory Berkeley, CA 94720, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LAWRENCE BERKELEY NATIONAL LABORATORY BERKELEY, CA 94720, USA","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Lawrence Berkeley National Laboratory Berkeley, CA 94720, USA","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5074260102"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":33.2586,"has_fulltext":false,"cited_by_count":277,"citation_normalized_percentile":{"value":0.99676989,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"19","issue":"4","first_page":"479","last_page":"493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":1.0,"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":1.0,"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":0.9976000189781189,"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":0.9975000023841858,"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":0.8361239433288574},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.760751485824585},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6716558933258057},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5657268762588501},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5468021631240845},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5411978363990784},{"id":"https://openalex.org/keywords/rollback","display_name":"Rollback","score":0.4975297749042511},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.49738600850105286},{"id":"https://openalex.org/keywords/process-migration","display_name":"Process migration","score":0.49574288725852966},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4617379605770111},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.4216915965080261},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.41448289155960083},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09978246688842773}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8361239433288574},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.760751485824585},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6716558933258057},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5657268762588501},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5468021631240845},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5411978363990784},{"id":"https://openalex.org/C174220543","wikidata":"https://www.wikidata.org/wiki/Q395307","display_name":"Rollback","level":3,"score":0.4975297749042511},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49738600850105286},{"id":"https://openalex.org/C36351404","wikidata":"https://www.wikidata.org/wiki/Q7247295","display_name":"Process migration","level":3,"score":0.49574288725852966},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4617379605770111},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.4216915965080261},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.41448289155960083},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09978246688842773},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1177/1094342005056139","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342005056139","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.110.9068","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.110.9068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lam-mpi.org/papers/lacsi2003/lacsi-2003.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.112.6274","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.112.6274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.osl.iu.edu/~brbarret/doc/hpca2005-lam-cr.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320317220","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14"},{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"},{"id":"https://openalex.org/F4320338292","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W34870269","https://openalex.org/W104327127","https://openalex.org/W134816542","https://openalex.org/W307918303","https://openalex.org/W369273693","https://openalex.org/W1484530169","https://openalex.org/W1494933502","https://openalex.org/W1509811702","https://openalex.org/W1510543252","https://openalex.org/W1510894298","https://openalex.org/W1524357507","https://openalex.org/W1537929875","https://openalex.org/W1571582830","https://openalex.org/W1573548168","https://openalex.org/W1579775238","https://openalex.org/W1583642359","https://openalex.org/W1589918049","https://openalex.org/W1641327695","https://openalex.org/W1701369565","https://openalex.org/W1825216778","https://openalex.org/W1846255488","https://openalex.org/W1862835629","https://openalex.org/W1971952282","https://openalex.org/W1997021720","https://openalex.org/W2004381122","https://openalex.org/W2013639878","https://openalex.org/W2081413727","https://openalex.org/W2081612620","https://openalex.org/W2099343440","https://openalex.org/W2100970777","https://openalex.org/W2108686966","https://openalex.org/W2112121929","https://openalex.org/W2116006827","https://openalex.org/W2131053137","https://openalex.org/W2133201251","https://openalex.org/W2133431504","https://openalex.org/W2133553843","https://openalex.org/W2135890534","https://openalex.org/W2140332639","https://openalex.org/W2171453084","https://openalex.org/W2188835178","https://openalex.org/W2903691225","https://openalex.org/W3035757797","https://openalex.org/W4232322658","https://openalex.org/W4232707757","https://openalex.org/W4244056258","https://openalex.org/W4249690261","https://openalex.org/W4250750404","https://openalex.org/W4285719527","https://openalex.org/W4299544056","https://openalex.org/W4301447929"],"related_works":["https://openalex.org/W2103295733","https://openalex.org/W2525033434","https://openalex.org/W4280533024","https://openalex.org/W4300992253","https://openalex.org/W1942762218","https://openalex.org/W1985270856","https://openalex.org/W2393992006","https://openalex.org/W1833720599","https://openalex.org/W3101274117","https://openalex.org/W1966875563"],"abstract_inverted_index":{"As":[0],"high":[1],"performance":[2,99],"clusters":[3],"continue":[4],"to":[5,73,79,102],"grow":[6],"in":[7],"size":[8],"and":[9,15,32,41,85],"popularity,":[10],"issues":[11],"of":[12,34,63,105],"fault":[13,92],"tolerance":[14],"reliability":[16],"are":[17],"becoming":[18],"limiting":[19],"factors":[20],"on":[21],"application":[22],"scalability.":[23],"To":[24],"address":[25],"these":[26],"issues,":[27],"we":[28],"present":[29],"the":[30,51,60,74,77,103,106],"design":[31],"implementation":[33,62],"a":[35,66],"system":[36,58,78],"for":[37,44,82,91],"providing":[38],"coordinated":[39],"checkpointing":[40],"rollback":[42],"recovery":[43],"MPI-based":[45],"parallel":[46],"applications.":[47],"Our":[48],"approach":[49],"integrates":[50],"Berkeley":[52],"Lab":[53],"BLCR":[54],"kernel-level":[55],"process":[56],"checkpoint":[57,107],"with":[59],"LAM":[61],"MPI":[64],"through":[65],"defined":[67],"checkpoint/restart":[68],"interface.":[69],"Checkpointing":[70],"is":[71],"transparent":[72],"application,":[75],"allowing":[76],"be":[80],"used":[81],"cluster":[83],"maintenance":[84],"scheduling":[86],"reasons":[87],"as":[88,90],"well":[89],"tolerance.":[93],"Experimental":[94],"results":[95],"show":[96],"negligible":[97],"communication":[98],"impact":[100],"due":[101],"incorporation":[104],"support":[108],"capabilities":[109],"into":[110],"LAM/MPI.":[111]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":15}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}