{"id":"https://openalex.org/W3178420079","doi":"https://doi.org/10.1109/tpds.2021.3096055","title":"Near-Zero Downtime Recovery From Transient-Error-Induced Crashes","display_name":"Near-Zero Downtime Recovery From Transient-Error-Induced Crashes","publication_year":2021,"publication_date":"2021-07-09","ids":{"openalex":"https://openalex.org/W3178420079","doi":"https://doi.org/10.1109/tpds.2021.3096055","mag":"3178420079"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2021.3096055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3096055","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":["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/A5100408398","display_name":"Chao Chen","orcid":"https://orcid.org/0000-0003-1960-4042"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Chen","raw_affiliation_strings":["Amazon Science, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1960-4042","affiliations":[{"raw_affiliation_string":"Amazon Science, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064465394","display_name":"Greg Eisenhauer","orcid":"https://orcid.org/0000-0002-2070-043X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Greg Eisenhauer","raw_affiliation_strings":["School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2070-043X","affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061235810","display_name":"Santosh Pande","orcid":"https://orcid.org/0000-0001-6723-8062"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Santosh Pande","raw_affiliation_strings":["School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1608,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.44092084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"33","issue":"4","first_page":"765","last_page":"778"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9998000264167786,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9986000061035156,"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":0.9976999759674072,"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":0.7248654961585999},{"id":"https://openalex.org/keywords/downtime","display_name":"Downtime","score":0.7182371020317078},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.628600001335144},{"id":"https://openalex.org/keywords/transient","display_name":"Transient (computer programming)","score":0.5561171174049377},{"id":"https://openalex.org/keywords/crash","display_name":"Crash","score":0.5500350594520569},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5163847208023071},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46824562549591064},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46413418650627136},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.34966588020324707},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.22846147418022156},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14158546924591064},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11790555715560913}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7248654961585999},{"id":"https://openalex.org/C180591934","wikidata":"https://www.wikidata.org/wiki/Q1253369","display_name":"Downtime","level":2,"score":0.7182371020317078},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.628600001335144},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.5561171174049377},{"id":"https://openalex.org/C183469790","wikidata":"https://www.wikidata.org/wiki/Q333501","display_name":"Crash","level":2,"score":0.5500350594520569},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5163847208023071},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46824562549591064},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46413418650627136},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.34966588020324707},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.22846147418022156},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14158546924591064},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11790555715560913}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2021.3096055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3096055","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1978082708","https://openalex.org/W1978347128","https://openalex.org/W1988070283","https://openalex.org/W1997843200","https://openalex.org/W2021337678","https://openalex.org/W2021595237","https://openalex.org/W2036641664","https://openalex.org/W2037523067","https://openalex.org/W2043422726","https://openalex.org/W2080640552","https://openalex.org/W2088552220","https://openalex.org/W2105524676","https://openalex.org/W2110137598","https://openalex.org/W2128511938","https://openalex.org/W2134320686","https://openalex.org/W2336984031","https://openalex.org/W2346318102","https://openalex.org/W2486202470","https://openalex.org/W2563678330","https://openalex.org/W2565180819","https://openalex.org/W2565481669","https://openalex.org/W2631994569","https://openalex.org/W2647773517","https://openalex.org/W2767321582","https://openalex.org/W2767966988","https://openalex.org/W2808246216","https://openalex.org/W2903494439","https://openalex.org/W2986347693","https://openalex.org/W3014653994","https://openalex.org/W3034155241","https://openalex.org/W4229822017","https://openalex.org/W4232172996","https://openalex.org/W4233556486","https://openalex.org/W4246684434","https://openalex.org/W4254699165","https://openalex.org/W6649817641","https://openalex.org/W6680487673"],"related_works":["https://openalex.org/W2046276983","https://openalex.org/W2954002293","https://openalex.org/W2078264086","https://openalex.org/W2892741875","https://openalex.org/W2164372000","https://openalex.org/W1862835629","https://openalex.org/W2099111379","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991"],"abstract_inverted_index":{"Due":[0],"to":[1,36,50,57,69,94,107,134,147,176,191],"the":[2,21,82,117,136,193,207,253,301,307],"system":[3],"scaling,transient":[4],"errorscaused":[5],"by":[6,162,258],"external":[7],"noise,":[8],"e.g.,":[9],"heat":[10],"fluxes":[11],"and":[12,23,87,109,173,217,248,290,303],"particle":[13],"strikes,":[14],"have":[15],"become":[16],"a":[17,102,121,218,282],"growing":[18],"concern":[19],"for":[20,75,126,196,270],"current":[22],"upcoming":[24],"exa-scale":[25,312],"high-performance-computing":[26],"(HPC)":[27],"systems.":[28,313],"Applications":[29],"running":[30,244],"on":[31,170,224,245],"these":[32],"systems":[33,77],"are":[34,63,132,189],"expected":[35],"experience":[37],"transient":[38],"errors":[39,62,231,257],"more":[40],"frequently":[41],"than":[42],"ever":[43],"before,":[44],"which":[45,272],"will":[46],"either":[47],"lead":[48],"them":[49,56],"generate":[51],"incorrect":[52],"outputs":[53],"or":[54],"cause":[55],"crash.":[58],"However,":[59],"since":[60],"such":[61,294],"still":[64],"quite":[65],"rare":[66],"as":[67,204,206],"compared":[68],"no-fault":[70,85],"cases,":[71],"desirable":[72],"solutions":[73],"call":[74],"low/no-overhead":[76],"that":[78],"do":[79],"not":[80],"compromise":[81],"performance":[83],"under":[84],"conditions":[86],"also":[88,240],"allow":[89],"very":[90,283],"fast":[91],"fault":[92],"recovery":[93,124,130,157,179,297],"minimize":[95],"downtime.":[96,238],"In":[97],"this":[98,182],"article,":[99],"we":[100,264],"presentIterPro,":[101],"light-weight":[103],"compiler-assisted":[104],"resilience":[105,197,308],"technique":[106],"quickly":[108],"accurately":[110],"recover":[111,223],"processes":[112],"from":[113],"transient-error-induced":[114],"crashes.":[115],"During":[116,211],"compilation":[118],"of":[119,123,143,152,229,234,255,276,287,306],"applications,IterProconstructs":[120],"set":[122],"kernels":[125,131],"crash-prone":[127],"instructions.":[128],"These":[129],"executed":[133],"repair":[135],"corrupted":[137],"process":[138],"states":[139],"on-the-fly":[140],"upon":[141],"occurrences":[142],"errors,":[144],"enabling":[145],"applications":[146],"continue":[148],"their":[149,212],"executions":[150],"instead":[151],"being":[153],"terminated.":[154],"When":[155],"constructing":[156],"kernels,IterProexploits":[158],"side":[159,194],"effects":[160,195],"introduced":[161,190],"induction":[163],"variable":[164],"based":[165,169],"code":[166,186],"optimization":[167],"techniques":[168],"loop":[171],"unrolling":[172],"strength":[174],"reduction":[175],"improve":[177],"its":[178],"capability.":[180],"To":[181],"end,":[183],"two":[184],"new":[185],"transformation":[187],"passes":[188],"expose":[192],"purposes.":[198],"We":[199,239],"evaluatedIterProwith":[200,241],"4":[201],"scientific":[202],"workloads":[203],"well":[205],"NPB":[208],"benchmarks":[209],"suite.":[210],"normal":[213],"execution,IterProincurs":[214],"almostzeroruntime":[215],"overhead":[216],"small,":[219],"fixed27MBmemory":[220],"overhead.":[221],"Meanwhile,IterProcan":[222],"an":[225,295],"average":[226],"83.55":[227],"percent":[228,289],"crash-causing":[230,256],"within":[232],"dozens":[233],"milliseconds":[235],"with":[236,281],"negligible":[237,291],"parallel":[242],"jobs":[243],"3072":[246],"cores":[247],"showed":[249],"thatIterProcan":[250],"successfully":[251],"mask":[252],"impact":[254],"providing":[259],"almost":[260],"uninterrupted":[261],"execution.":[262],"Finally,":[263],"present":[265],"our":[266],"preliminary":[267],"evaluation":[268],"result":[269],"BLAS,":[271],"shows":[273],"thatIterProis":[274],"capable":[275],"recovering":[277],"failures":[278],"in":[279,310],"libraries":[280],"high":[284],"coverage":[285],"rate":[286],"83":[288],"overheads.":[292],"With":[293],"effective":[296],"mechanism,IterProcould":[298],"tremendously":[299],"mitigate":[300],"overheads":[302],"resource":[304],"requirements":[305],"subsystem":[309],"future":[311]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}