{"id":"https://openalex.org/W4301442552","doi":"https://doi.org/10.3233/spr-130371","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":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W4301442552","doi":"https://doi.org/10.3233/spr-130371"},"language":"en","primary_location":{"id":"pmh:oai:doaj.org/article:2318fa4ebd1243f993f8e60876faa545","is_oa":true,"landing_page_url":"https://doaj.org/article/2318fa4ebd1243f993f8e60876faa545","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scientific Programming, Vol 21, Iss 3-4, Pp 149-163 (2013)","raw_type":"article"},"type":"article","indexed_in":["doaj"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doaj.org/article/2318fa4ebd1243f993f8e60876faa545","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":["School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kathryn Mohror","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"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":["School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Moody","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bronis R. de Supinski","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"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":["School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47697107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9976000189781189,"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":0.9976000189781189,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9854000210762024,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9847999811172485,"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":0.7790939807891846},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.771561861038208},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.6213836073875427},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.48644495010375977},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40022891759872437},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.39976152777671814},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.27575021982192993},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13643673062324524},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.048006534576416016},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.04073271155357361}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7790939807891846},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.771561861038208},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.6213836073875427},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.48644495010375977},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40022891759872437},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39976152777671814},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27575021982192993},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13643673062324524},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.048006534576416016},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.04073271155357361}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:doaj.org/article:2318fa4ebd1243f993f8e60876faa545","is_oa":true,"landing_page_url":"https://doaj.org/article/2318fa4ebd1243f993f8e60876faa545","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scientific Programming, Vol 21, Iss 3-4, Pp 149-163 (2013)","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:doaj.org/article:2318fa4ebd1243f993f8e60876faa545","is_oa":true,"landing_page_url":"https://doaj.org/article/2318fa4ebd1243f993f8e60876faa545","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scientific Programming, Vol 21, Iss 3-4, Pp 149-163 (2013)","raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2364921833","https://openalex.org/W1604898313","https://openalex.org/W2385146268","https://openalex.org/W1986253068","https://openalex.org/W1596201972","https://openalex.org/W1967954938","https://openalex.org/W1516830477","https://openalex.org/W1788737569","https://openalex.org/W2503642292","https://openalex.org/W1767718647"],"abstract_inverted_index":{"High":[0],"performance":[1],"computing":[2],"(HPC)":[3],"systems":[4],"use":[5],"checkpoint-restart":[6,27,66],"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],"system,":[67],"mcrEngine.":[68],"McrEngine":[69],"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],"mcrEngine":[117],"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":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}
