{"id":"https://openalex.org/W4240675937","doi":"https://doi.org/10.1109/sc.2012.77","title":"MCREngine: A scalable checkpointing system using data-aware aggregation and compression","display_name":"MCREngine: A scalable checkpointing system using data-aware aggregation and compression","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W4240675937","doi":"https://doi.org/10.1109/sc.2012.77"},"language":"en","primary_location":{"id":"doi:10.1109/sc.2012.77","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sc.2012.77","pdf_url":null,"source":{"id":"https://openalex.org/S4363608557","display_name":"2012 International Conference for High Performance Computing, Networking, Storage and Analysis","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1082422","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002465410","display_name":"Tanzima Islam","orcid":"https://orcid.org/0000-0003-2877-5871"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanzima Zerin Islam","raw_affiliation_strings":["Sch. of Electr. &amp; Comput. Eng., Purdue Univ., West Lafayette, IN, USA","School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sch. of Electr. &amp; Comput. Eng., Purdue Univ., West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","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"]},{"id":"https://openalex.org/I4210138311","display_name":"Lawrence Livermore National Security","ror":"https://ror.org/03z21mf61","country_code":"US","type":"government","lineage":["https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kathryn Mohror","raw_affiliation_strings":["Lawrence Livermore Nat. Lab. (LLNL), Livermore, CA, USA","Lawrence Livermore National Laboratory, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore Nat. Lab. (LLNL), Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441","https://openalex.org/I4210138311"]},{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047310442","display_name":"Saurabh Bagchi","orcid":"https://orcid.org/0000-0002-4239-5632"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurabh Bagchi","raw_affiliation_strings":["Sch. of Electr. &amp; Comput. Eng., Purdue Univ., West Lafayette, IN, USA","School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sch. of Electr. &amp; Comput. Eng., Purdue Univ., West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"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"]},{"id":"https://openalex.org/I4210138311","display_name":"Lawrence Livermore National Security","ror":"https://ror.org/03z21mf61","country_code":"US","type":"government","lineage":["https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Moody","raw_affiliation_strings":["Lawrence Livermore Nat. Lab. (LLNL), Livermore, CA, USA","Lawrence Livermore National Laboratory, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore Nat. Lab. (LLNL), Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441","https://openalex.org/I4210138311"]},{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","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"]},{"id":"https://openalex.org/I4210138311","display_name":"Lawrence Livermore National Security","ror":"https://ror.org/03z21mf61","country_code":"US","type":"government","lineage":["https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bronis R. de Supinski","raw_affiliation_strings":["Lawrence Livermore Nat. Lab. (LLNL), Livermore, CA, USA","Lawrence Livermore National Laboratory, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore Nat. Lab. (LLNL), Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441","https://openalex.org/I4210138311"]},{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045622261","display_name":"Rudolf Eigenmann","orcid":"https://orcid.org/0000-0003-1651-827X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rudolf Eigenmann","raw_affiliation_strings":["Sch. of Electr. &amp; Comput. Eng., Purdue Univ., West Lafayette, IN, USA","School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sch. of Electr. &amp; Comput. Eng., Purdue Univ., West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.5272,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.96648238,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"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":0.9994000196456909,"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":0.85657799243927},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.7532965540885925},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.741515576839447},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5626857876777649},{"id":"https://openalex.org/keywords/file-system","display_name":"File system","score":0.46439510583877563},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4562467634677887},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.43771740794181824},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4205777645111084},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.41758063435554504},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4122496247291565},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.40241503715515137},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19996917247772217},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.133204847574234},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10414350032806396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.85657799243927},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.7532965540885925},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.741515576839447},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5626857876777649},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.46439510583877563},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4562467634677887},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.43771740794181824},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4205777645111084},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.41758063435554504},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4122496247291565},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40241503715515137},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19996917247772217},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.133204847574234},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10414350032806396},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/sc.2012.77","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sc.2012.77","pdf_url":null,"source":{"id":"https://openalex.org/S4363608557","display_name":"2012 International Conference for High Performance Computing, Networking, Storage and Analysis","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1082422","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1082422","pdf_url":null,"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:1082422","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1082422","pdf_url":null,"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":[],"funders":[{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W39601649","https://openalex.org/W1492406391","https://openalex.org/W1497470190","https://openalex.org/W1498674203","https://openalex.org/W1506891209","https://openalex.org/W1912206988","https://openalex.org/W1981432246","https://openalex.org/W1984564341","https://openalex.org/W2003421875","https://openalex.org/W2023779315","https://openalex.org/W2043522772","https://openalex.org/W2082498963","https://openalex.org/W2089536264","https://openalex.org/W2100970777","https://openalex.org/W2109485293","https://openalex.org/W2110455446","https://openalex.org/W2113824616","https://openalex.org/W2116011221","https://openalex.org/W2119018856","https://openalex.org/W2125269836","https://openalex.org/W2139244298","https://openalex.org/W2140746402","https://openalex.org/W2142265837","https://openalex.org/W2145594092","https://openalex.org/W2147667563","https://openalex.org/W2159161022","https://openalex.org/W2160225915","https://openalex.org/W2163295644","https://openalex.org/W2165022815","https://openalex.org/W2167563208","https://openalex.org/W2181301067","https://openalex.org/W2998129307","https://openalex.org/W3150262005","https://openalex.org/W4241823868","https://openalex.org/W6629876402"],"related_works":["https://openalex.org/W2375742443","https://openalex.org/W2149381099","https://openalex.org/W1483190388","https://openalex.org/W4200520489","https://openalex.org/W2061536531","https://openalex.org/W193873054","https://openalex.org/W2952348651","https://openalex.org/W1967080779","https://openalex.org/W2612632602","https://openalex.org/W2321805087"],"abstract_inverted_index":{"High":[0],"performance":[1],"computing":[2],"(HPC)":[3],"systems":[4],"use":[5],"checkpoint-restart":[6,27],"to":[7,32,43,102,123,130],"tolerate":[8],"failures.":[9],"Typically,":[10],"applications":[11,24,42],"store":[12],"their":[13],"states":[14],"in":[15,54],"checkpoints":[16,71,100,114],"on":[17],"a":[18,64,133],"parallel":[19],"file":[20],"system":[21],"(PFS).":[22],"As":[23],"scale":[25],"up,":[26],"incurs":[28],"high":[29,38],"overheads":[30,39],"due":[31],"contention":[33],"for":[34],"PFS":[35],"resources.":[36],"The":[37],"force":[40],"large-scale":[41,112],"reduce":[44],"checkpoint":[45],"frequency,":[46],"which":[47],"means":[48],"more":[49],"compute":[50],"time":[51],"is":[52],"lost":[53],"the":[55,79],"event":[56],"of":[57,78,99],"failure.":[58],"We":[59],"alleviate":[60],"this":[61],"problem":[62],"through":[63,83],"scalable":[65],"checkpointrestart":[66],"system,":[67],"MCRENGINE.":[68],"MCRENGINE":[69,117],"aggregates":[70],"from":[72],"multiple":[73],"application":[74,113],"processes":[75],"with":[76,111,135],"knowledge":[77],"data":[80],"semantics":[81],"available":[82],"widely-used":[84],"I/O":[85],"libraries,":[86],"e.g.,":[87],"HDF5":[88],"and":[89,91,107,125],"netCDF,":[90],"compresses":[92],"them.":[93],"Our":[94,109],"novel":[95],"scheme":[96],"improves":[97],"compressibility":[98],"up":[101,122,129],"115%":[103],"over":[104,132],"simple":[105],"concatenation":[106],"compression.":[108,139],"evaluation":[110],"show":[115],"that":[116],"reduces":[118],"checkpointing":[119],"overhead":[120,127],"by":[121,128],"87%":[124],"restart":[126],"62%":[131],"baseline":[134],"no":[136],"aggregation":[137],"or":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
