{"id":"https://openalex.org/W2744576085","doi":"https://doi.org/10.1109/tpds.2018.2866794","title":"CRAFT: A Library for Easier Application-Level Checkpoint/Restart and Automatic Fault Tolerance","display_name":"CRAFT: A Library for Easier Application-Level Checkpoint/Restart and Automatic Fault Tolerance","publication_year":2018,"publication_date":"2018-08-23","ids":{"openalex":"https://openalex.org/W2744576085","doi":"https://doi.org/10.1109/tpds.2018.2866794","mag":"2744576085"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2018.2866794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2866794","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1708.02030","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102889958","display_name":"Faisal Shahzad","orcid":"https://orcid.org/0000-0002-6766-7622"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Faisal Shahzad","raw_affiliation_strings":["Erlangen Regional Computing Center (RRZE), University of Erlangen-Nuremberg, Martensstrasse 1, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6766-7622","affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center (RRZE), University of Erlangen-Nuremberg, Martensstrasse 1, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010377968","display_name":"Jonas Thies","orcid":"https://orcid.org/0000-0001-9231-9999"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonas Thies","raw_affiliation_strings":["German Aerospace Center (DLR), Simulation and Software Technology, Linder H\u00f6he, Cologne, Germany","[German Aerospace Center (DLR), Simulation and Software Technology, Linder H\u00f6he, Cologne, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Aerospace Center (DLR), Simulation and Software Technology, Linder H\u00f6he, Cologne, Germany","institution_ids":["https://openalex.org/I2898391981"]},{"raw_affiliation_string":"[German Aerospace Center (DLR), Simulation and Software Technology, Linder H\u00f6he, Cologne, Germany]","institution_ids":["https://openalex.org/I2898391981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038048025","display_name":"Moritz Kreutzer","orcid":"https://orcid.org/0000-0002-7822-9468"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Moritz Kreutzer","raw_affiliation_strings":["Erlangen Regional Computing Center (RRZE), University of Erlangen-Nuremberg, Martensstrasse 1, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center (RRZE), University of Erlangen-Nuremberg, Martensstrasse 1, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112049374","display_name":"Thomas Zeiser","orcid":"https://orcid.org/0009-0002-2916-911X"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Zeiser","raw_affiliation_strings":["Erlangen Regional Computing Center (RRZE), University of Erlangen-Nuremberg, Martensstrasse 1, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center (RRZE), University of Erlangen-Nuremberg, Martensstrasse 1, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082552227","display_name":"Georg Hager","orcid":"https://orcid.org/0000-0002-8723-2781"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georg Hager","raw_affiliation_strings":["Erlangen Regional Computing Center (RRZE), University of Erlangen-Nuremberg, Martensstrasse 1, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center (RRZE), University of Erlangen-Nuremberg, Martensstrasse 1, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070209050","display_name":"Gerhard Wellein","orcid":"https://orcid.org/0000-0001-7371-3026"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Wellein","raw_affiliation_strings":["Erlangen Regional Computing Center (RRZE), University of Erlangen-Nuremberg, Martensstrasse 1, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center (RRZE), University of Erlangen-Nuremberg, Martensstrasse 1, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8567,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77335025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"30","issue":"3","first_page":"501","last_page":"514"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998000264167786,"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":0.9998000264167786,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9934999942779541,"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":0.86618971824646},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6971526145935059},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6740519404411316},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5346879959106445},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4843524694442749},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46707063913345337},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4624389111995697},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.45165008306503296},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.414266973733902},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3693295121192932},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.14899221062660217}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.86618971824646},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6971526145935059},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6740519404411316},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5346879959106445},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4843524694442749},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46707063913345337},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4624389111995697},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.45165008306503296},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.414266973733902},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3693295121192932},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.14899221062660217},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tpds.2018.2866794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2866794","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:elib.dlr.de:114762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/TPDS.2018.2866794>.","pdf_url":null,"source":{"id":"https://openalex.org/S4377196266","display_name":"elib (German Aerospace Center)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2898391981","host_organization_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","host_organization_lineage":["https://openalex.org/I2898391981"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Zeitschriftenbeitrag"},{"id":"pmh:oai:arXiv.org:1708.02030","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.02030","pdf_url":"https://arxiv.org/pdf/1708.02030","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"mag:2744576085","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1708.02030.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1708.02030","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1708.02030","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1708.02030","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.02030","pdf_url":"https://arxiv.org/pdf/1708.02030","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W141129880","https://openalex.org/W191492107","https://openalex.org/W1041528403","https://openalex.org/W1537929875","https://openalex.org/W1576341769","https://openalex.org/W1583736387","https://openalex.org/W1984564341","https://openalex.org/W1986905947","https://openalex.org/W1998221613","https://openalex.org/W2000870360","https://openalex.org/W2013639878","https://openalex.org/W2017060126","https://openalex.org/W2021234574","https://openalex.org/W2044681268","https://openalex.org/W2045879521","https://openalex.org/W2054129151","https://openalex.org/W2086160340","https://openalex.org/W2095487435","https://openalex.org/W2096049668","https://openalex.org/W2105039796","https://openalex.org/W2128577831","https://openalex.org/W2145071552","https://openalex.org/W2152085994","https://openalex.org/W2152419477","https://openalex.org/W2152844070","https://openalex.org/W2152893862","https://openalex.org/W2175670603","https://openalex.org/W2246786759","https://openalex.org/W2285867394","https://openalex.org/W2526559026","https://openalex.org/W2540977105","https://openalex.org/W3101951032","https://openalex.org/W3141239549","https://openalex.org/W3158458472","https://openalex.org/W4239022315","https://openalex.org/W4252273460","https://openalex.org/W6607731702","https://openalex.org/W6630659090","https://openalex.org/W6631987640","https://openalex.org/W6655627441","https://openalex.org/W6684440641","https://openalex.org/W6727979456","https://openalex.org/W6740868767","https://openalex.org/W7046307239"],"related_works":["https://openalex.org/W2963258975","https://openalex.org/W2587630802","https://openalex.org/W1974772932","https://openalex.org/W1546275500","https://openalex.org/W2130768881","https://openalex.org/W39601649","https://openalex.org/W3094386879","https://openalex.org/W2756453082","https://openalex.org/W191503951","https://openalex.org/W2411107954","https://openalex.org/W2047196223","https://openalex.org/W2078349455","https://openalex.org/W3158095115","https://openalex.org/W2761821601","https://openalex.org/W3193156221","https://openalex.org/W2766302805","https://openalex.org/W2149719295","https://openalex.org/W3145876489","https://openalex.org/W2033435686","https://openalex.org/W2755218711"],"abstract_inverted_index":{"In":[0],"order":[1],"to":[2,41,129],"efficiently":[3],"use":[4],"the":[5,18,23,36,49,70,96,121,138,149,176,211,215],"future":[6],"generations":[7],"of":[8,17,56,64,72,98,112,120,135,180],"supercomputers,":[9],"fault":[10],"tolerance":[11],"and":[12,33,79,104,114,146,178,183,197,219],"power":[13],"consumption":[14],"are":[15,109,225],"two":[16,85],"prime":[19],"challenges":[20,212],"anticipated":[21],"by":[22,214],"High":[24],"Performance":[25],"Computing":[26],"(HPC)":[27],"community.":[28],"Checkpoint/Restart":[29,151],"(CR)":[30],"has":[31],"been":[32],"still":[34],"is":[35,48],"most":[37,50,102],"widely":[38],"used":[39,106,118],"technique":[40,53],"deal":[42],"with":[43,203],"hard":[44],"failures.":[45],"Application-level":[46],"CR":[47,52],"effective":[51],"in":[54],"terms":[55],"overhead":[57,136],"efficiency":[58],"but":[59],"it":[60,88],"takes":[61],"a":[62,141],"lot":[63],"implementation":[65,71,97],"effort.":[66,207],"This":[67,208],"work":[68,209],"presents":[69,210],"our":[73],"C++":[74],"based":[75,169],"library":[76,92,124,139,153],"CRAFT":[77,113,159],"(Checkpoint-Restart":[78],"Automatic":[80],"Fault":[81],"Tolerance),":[82],"which":[83,173],"serves":[84],"purposes.":[86],"First,":[87],"provides":[89,160],"an":[90,161],"extendable":[91],"that":[93],"significantly":[94,174],"eases":[95],"application-level":[99,195],"checkpointing.":[100,157],"The":[101,123,222],"basic":[103],"frequently":[105],"checkpoint":[107],"data-types":[108],"already":[110],"part":[111],"can":[115,125,193],"be":[116,126],"directly":[117],"out":[119],"box.":[122],"easily":[127],"extended":[128],"add":[130],"more":[131],"data-types.":[132],"As":[133],"means":[134],"reduction,":[137],"offers":[140],"built-in":[142],"asynchronous":[143],"checkpointing":[144],"mechanism":[145],"also":[147],"supports":[148],"Scalable":[150],"(SCR)":[152],"for":[154,164],"node":[155],"level":[156],"Second,":[158],"easier":[162],"interface":[163],"User-Level":[165],"Failure":[166],"Mitigation":[167],"(ULFM)":[168],"dynamic":[170],"process":[171,201],"recovery,":[172],"reduces":[175],"complexity":[177],"effort":[179],"failure":[181],"detection":[182],"communication":[184],"recovery":[185],"mechanism.":[186],"By":[187],"utilizing":[188],"both":[189],"functionalities":[190],"together,":[191],"applications":[192],"write":[194],"checkpoints":[196],"recover":[198],"dynamically":[199],"from":[200],"failures":[202],"very":[204],"limited":[205],"programming":[206],"addressed":[213],"library,":[216],"its":[217,220],"design,":[218],"use.":[221],"associated":[223],"overheads":[224],"analyzed":[226],"using":[227],"benchmarks.":[228]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}