{"id":"https://openalex.org/W2023779315","doi":"https://doi.org/10.1145/1183401.1183405","title":"Experimental evaluation of application-level checkpointing for OpenMP programs","display_name":"Experimental evaluation of application-level checkpointing for OpenMP programs","publication_year":2006,"publication_date":"2006-06-28","ids":{"openalex":"https://openalex.org/W2023779315","doi":"https://doi.org/10.1145/1183401.1183405","mag":"2023779315"},"language":"en","primary_location":{"id":"doi:10.1145/1183401.1183405","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183401.1183405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th annual international conference on Supercomputing","raw_type":"proceedings-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/A5111681485","display_name":"Greg Bronevetsky","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Greg Bronevetsky","raw_affiliation_strings":["Cornell University, Ithaca, NY","Cornell University (Ithaca, NY);"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Cornell University (Ithaca, NY);","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013181067","display_name":"Keshav Pingali","orcid":"https://orcid.org/0000-0002-0484-4636"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keshav Pingali","raw_affiliation_strings":["Cornell University, Ithaca, NY","Cornell University (Ithaca, NY);"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Cornell University (Ithaca, NY);","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086230556","display_name":"Paul Stodghill","orcid":"https://orcid.org/0000-0003-3875-8450"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Stodghill","raw_affiliation_strings":["Cornell University, Ithaca, NY","Cornell University (Ithaca, NY);"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Cornell University (Ithaca, NY);","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111681485"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":1.2071,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.80945887,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9965000152587891,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9921000003814697,"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":0.887586236000061},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.8091917037963867},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7283754348754883},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6117252111434937},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5620622038841248},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.5248945951461792},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5056731700897217},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4570356607437134},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44717124104499817},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.43839094042778015},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4262653887271881},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.37931665778160095},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3665507733821869},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20554086565971375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.887586236000061},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.8091917037963867},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7283754348754883},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6117252111434937},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5620622038841248},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5248945951461792},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5056731700897217},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4570356607437134},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44717124104499817},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.43839094042778015},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4262653887271881},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.37931665778160095},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3665507733821869},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20554086565971375},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1183401.1183405","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183401.1183405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th annual international conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1510894298","https://openalex.org/W1846255488","https://openalex.org/W1898787029","https://openalex.org/W1993383198","https://openalex.org/W1997021720","https://openalex.org/W2028133900","https://openalex.org/W2047117506","https://openalex.org/W2048784665","https://openalex.org/W2068810256","https://openalex.org/W2093956690","https://openalex.org/W2096049668","https://openalex.org/W2100970777","https://openalex.org/W2114035455","https://openalex.org/W2131053137","https://openalex.org/W2152085994","https://openalex.org/W2156204788","https://openalex.org/W2162351670","https://openalex.org/W2171453084","https://openalex.org/W4239437589","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2379153735","https://openalex.org/W2046172023","https://openalex.org/W2972896947","https://openalex.org/W2170146914","https://openalex.org/W2355105570","https://openalex.org/W2083974823","https://openalex.org/W1862835629","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991"],"abstract_inverted_index":{"It":[0],"is":[1,17,26,35,73,89],"becoming":[2],"important":[3,240],"for":[4,79,142,194,207],"long-running":[5],"scientific":[6],"applications":[7,125,196],"to":[8,29,59,62,100,114,117,121,154,161,177],"tolerate":[9,122],"hardware":[10],"faults.":[11],"The":[12,42],"most":[13,162],"commonly":[14],"used":[15],"approach":[16,72,141,173,201],"checkpoint":[18],"and":[19,55,130,197,221,236,238],"restart":[20],"(CPR)":[21],"-":[22],"the":[23,33,38,52,56,64,67,94,109,119,148,169,187,216,222,243],"computation's":[24],"state":[25,65],"saved":[27,40],"periodically":[28],"disk.":[30],"Upon":[31],"failure":[32],"computation":[34],"restarted":[36],"from":[37],"last":[39],"state.":[41],"common":[43,160],"CPR":[44],"mechanism,":[45],"called":[46],"System-level":[47],"Checkpointing":[48,87],"(SLC),":[49],"requires":[50],"modifying":[51],"Operating":[53],"System":[54],"communication":[57],"libraries":[58],"enable":[60,101],"them":[61,128],"save":[63],"of":[66,111,171,210,246],"entire":[68],"parallel":[69],"application.":[70],"This":[71],"not":[74],"portable":[75,91],"since":[76],"a":[77,90,103,139,156,178],"checkpointer":[78],"one":[80],"system":[81],"rarely":[82],"works":[83],"on":[84,132,230],"another.":[85],"Application-level":[86],"(ALC)":[88],"alternative":[92],"where":[93],"programmer":[95],"manually":[96],"modifies":[97],"their":[98],"program":[99],"CPR,":[102],"very":[104],"labor-intensive":[105],"task.We":[106],"are":[107],"investigating":[108],"use":[110],"compiler":[112],"technology":[113],"instrument":[115],"codes":[116],"embed":[118],"ability":[120],"faults":[123],"into":[124],"themselves,":[126],"making":[127],"self-checkpointing":[129],"self-restarting":[131],"any":[133],"platform.":[134],"In":[135],"[9]":[136,152],"we":[137],"described":[138],"general":[140],"checkpointing":[143],"shared":[144,163,181],"memory":[145,164,182],"APIs":[146],"at":[147],"application":[149],"level.":[150],"Since":[151],"applied":[153],"only":[155],"toy":[157],"feature":[158],"set":[159],"APIs,":[165],"this":[166,172,200,211,247],"paper":[167],"shows":[168],"practicality":[170],"by":[174,202],"extending":[175],"it":[176],"specific":[179],"popular":[180],"API:":[183],"OpenMP.":[184],"We":[185],"describe":[186],"challenges":[188],"involved":[189],"in":[190],"providing":[191],"automated":[192],"ALC":[193],"OpenMP":[195,218],"experimentally":[198],"validate":[199],"showing":[203],"detailed":[204],"performance":[205,244],"results":[206],"our":[208],"implementation":[209],"technique.":[212],"Our":[213],"experiments":[214],"with":[215],"NAS":[217],"benchmarks":[219],"[1]":[220],"EPCC":[223],"microbench-marks":[224],"[21]":[225],"show":[226],"generally":[227],"low":[228],"overhead":[229],"three":[231],"different":[232],"architectures:":[233],"Linux/IA64,":[234],"Tru64/Alpha":[235],"Solaris/Sparc":[237],"highlight":[239],"lessons":[241],"about":[242],"characteristics":[245],"aproach.":[248]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
