{"id":"https://openalex.org/W1974772932","doi":"https://doi.org/10.1142/s0129626413400112","title":"A SURVEY OF CHECKPOINT/RESTART TECHNIQUES ON DISTRIBUTED MEMORY SYSTEMS","display_name":"A SURVEY OF CHECKPOINT/RESTART TECHNIQUES ON DISTRIBUTED MEMORY SYSTEMS","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W1974772932","doi":"https://doi.org/10.1142/s0129626413400112","mag":"1974772932"},"language":"en","primary_location":{"id":"doi:10.1142/s0129626413400112","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0129626413400112","pdf_url":null,"source":{"id":"https://openalex.org/S18360026","display_name":"Parallel Processing Letters","issn_l":"0129-6264","issn":["0129-6264","1793-642X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Parallel Processing Letters","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/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, University of Erlangen-Nuremberg, 91058 Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen-Nuremberg, 91058 Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003949750","display_name":"Markus Wittmann","orcid":"https://orcid.org/0000-0002-4812-9052"},"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":"MARKUS WITTMANN","raw_affiliation_strings":["Erlangen Regional Computing Center, University of Erlangen-Nuremberg, 91058 Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen-Nuremberg, 91058 Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"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, University of Erlangen-Nuremberg, 91058 Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen-Nuremberg, 91058 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, University of Erlangen-Nuremberg, 91058 Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen-Nuremberg, 91058 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, University of Erlangen-Nuremberg, 91058 Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen-Nuremberg, 91058 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, University of Erlangen-Nuremberg, 91058 Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen-Nuremberg, 91058 Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":2.0581,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.85079727,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"23","issue":"04","first_page":"1340011","last_page":"1340011"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9943000078201294,"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":0.9879999756813049,"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":0.854643702507019},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5983781814575195},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5786853432655334},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5500213503837585},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5485010743141174},{"id":"https://openalex.org/keywords/exascale-computing","display_name":"Exascale computing","score":0.547146737575531},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5259718298912048},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4657725989818573},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4113856554031372},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.38805487751960754},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.37623676657676697},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1951078176498413},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10999950766563416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.854643702507019},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5983781814575195},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5786853432655334},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5500213503837585},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5485010743141174},{"id":"https://openalex.org/C2778837361","wikidata":"https://www.wikidata.org/wiki/Q2450880","display_name":"Exascale computing","level":3,"score":0.547146737575531},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5259718298912048},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4657725989818573},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4113856554031372},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.38805487751960754},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.37623676657676697},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1951078176498413},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10999950766563416},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0129626413400112","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0129626413400112","pdf_url":null,"source":{"id":"https://openalex.org/S18360026","display_name":"Parallel Processing Letters","issn_l":"0129-6264","issn":["0129-6264","1793-642X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Parallel Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1971876223","https://openalex.org/W1992303919","https://openalex.org/W1992773065","https://openalex.org/W2105524676","https://openalex.org/W2115312455"],"related_works":["https://openalex.org/W4318068934","https://openalex.org/W2290952066","https://openalex.org/W4320480730","https://openalex.org/W2056528600","https://openalex.org/W1862835629","https://openalex.org/W2099111379","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W4297752063","https://openalex.org/W3128098196"],"abstract_inverted_index":{"The":[0,43],"road":[1],"to":[2,73,87,103,120,128],"exascale":[3,19],"computing":[4],"poses":[5],"many":[6],"challenges":[7],"for":[8,141,172,199],"the":[9,18,23,32,55,59,70,77,97,121,130,167,173,184,187,203,229],"High":[10],"Performance":[11],"Computing":[12],"(HPC)":[13],"community.":[14],"Each":[15],"step":[16],"on":[17,91,147,157],"path":[20],"is":[21,84,96,202],"mainly":[22],"result":[24],"of":[25,29,31,45,47,61,69,76,109,151,175],"a":[26,67,217],"higher":[27],"level":[28],"parallelism":[30],"basic":[33,49],"building":[34],"blocks":[35],"(i.e.,":[36],"CPUs,":[37],"memory":[38],"units,":[39],"networking":[40],"components,":[41],"etc.).":[42],"reliability":[44],"each":[46],"these":[48],"components":[50],"does":[51],"not":[52],"increase":[53],"at":[54],"same":[56],"rate":[57,60],"as":[58,223],"hardware":[62],"parallelism.":[63],"This":[64],"results":[65],"in":[66,226],"reduction":[68],"mean":[71],"time":[72],"failure":[74,105],"(MTTF)":[75],"whole":[78],"system.":[79],"A":[80,210],"fault":[81],"tolerance":[82],"environment":[83],"thus":[85],"indispensable":[86],"run":[88],"large":[89],"applications":[90,225],"such":[92],"clusters.":[93],"Checkpoint/Restart":[94,169],"(C/R)":[95],"classic":[98],"and":[99,162,191,216],"most":[100],"popular":[101],"method":[102],"minimize":[104],"damage.":[106],"Its":[107],"ease":[108],"implementation":[110],"makes":[111],"it":[112,116],"useful,":[113],"but":[114],"typically":[115],"introduces":[117],"significant":[118],"overhead":[119,200],"application.":[122],"Several":[123],"efforts":[124],"have":[125],"been":[126],"made":[127],"reduce":[129],"C/R":[131,139],"overhead.":[132],"In":[133],"this":[134],"paper":[135],"we":[136,182],"compare":[137],"various":[138],"techniques":[140,230],"their":[142],"overheads":[143],"by":[144],"implementing":[145],"them":[146],"two":[148],"different":[149],"categories":[150],"applications.":[152],"These":[153],"approaches":[154],"are":[155,221],"based":[156],"parallel-file-system":[158],"(PFS)-level":[159],"checkpoints":[160],"(synchronous/asynchronous)":[161],"node-level":[163,176],"checkpoints.":[164,177],"We":[165],"utilize":[166],"Scalable":[168],"(SCR)":[170],"library":[171],"comparison":[174,201],"For":[178],"asynchronous":[179,189],"PFS-level":[180,207],"checkpoints,":[181],"use":[183],"Damaris":[185],"library,":[186],"SCR":[188],"feature,":[190],"application-based":[192,205],"checkpointing":[193,208],"via":[194],"dedicated":[195],"threads.":[196],"Our":[197],"baseline":[198],"na\u00efve":[204],"synchronous":[206],"method.":[209],"3D":[211],"lattice-Boltzmann":[212],"(LBM)":[213],"flow":[214],"solver":[215,220],"Lanczos":[218],"eigenvalue":[219],"used":[222],"prototypical":[224],"which":[227],"all":[228],"considered":[231],"here":[232],"may":[233],"be":[234],"applied.":[235]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
