{"id":"https://openalex.org/W4226510426","doi":"https://doi.org/10.1109/tpds.2022.3157690","title":"Jdebug: A Fast, Non-Intrusive and Scalable Fault Locating Tool for Ten-Million-Scale Parallel Applications","display_name":"Jdebug: A Fast, Non-Intrusive and Scalable Fault Locating Tool for Ten-Million-Scale Parallel Applications","publication_year":2022,"publication_date":"2022-03-08","ids":{"openalex":"https://openalex.org/W4226510426","doi":"https://doi.org/10.1109/tpds.2022.3157690"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2022.3157690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3157690","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/A5087086951","display_name":"Dajia Peng","orcid":"https://orcid.org/0000-0002-6805-975X"},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dajia Peng","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","National Supercomputer Center in Wuxi, Wuxi, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"National Supercomputer Center in Wuxi, Wuxi, China","institution_ids":["https://openalex.org/I4210158984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031416021","display_name":"Yunlong Feng","orcid":"https://orcid.org/0000-0002-1151-5179"},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunlong Feng","raw_affiliation_strings":["National Supercomputer Center in Wuxi, Wuxi, China"],"affiliations":[{"raw_affiliation_string":"National Supercomputer Center in Wuxi, Wuxi, China","institution_ids":["https://openalex.org/I4210158984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101595134","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0003-1754-3039"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["National Research Centre of Parallel Computer Engineering and Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Research Centre of Parallel Computer Engineering and Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352268","display_name":"Xin Liu","orcid":"https://orcid.org/0000-0002-7870-6535"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["National Research Centre of Parallel Computer Engineering and Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Research Centre of Parallel Computer Engineering and Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101523284","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0002-7987-2842"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056860593","display_name":"Dexun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dexun Chen","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011359243","display_name":"Jiawei Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Song","raw_affiliation_strings":["National Supercomputer Center in Wuxi, Wuxi, China"],"affiliations":[{"raw_affiliation_string":"National Supercomputer Center in Wuxi, Wuxi, China","institution_ids":["https://openalex.org/I4210158984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051366939","display_name":"Zuoning Chen","orcid":"https://orcid.org/0000-0003-1975-5414"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuoning Chen","raw_affiliation_strings":["National Research Centre of Parallel Computer Engineering and Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Research Centre of Parallel Computer Engineering and Technology, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5087086951"],"corresponding_institution_ids":["https://openalex.org/I4210158984","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.2839,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55644974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"33","issue":"12","first_page":"3491","last_page":"3504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9987999796867371,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9987999796867371,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9987000226974487,"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":0.9979000091552734,"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/debugging","display_name":"Debugging","score":0.8901993036270142},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8616843223571777},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8122018575668335},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5769067406654358},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.45130643248558044},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.43228432536125183},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.38200926780700684},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3658415675163269}],"concepts":[{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.8901993036270142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8616843223571777},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8122018575668335},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5769067406654358},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45130643248558044},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.43228432536125183},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.38200926780700684},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3658415675163269},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2022.3157690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3157690","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":53,"referenced_works":["https://openalex.org/W94105952","https://openalex.org/W148387851","https://openalex.org/W787130922","https://openalex.org/W1511806592","https://openalex.org/W1520271518","https://openalex.org/W1565978235","https://openalex.org/W1568471959","https://openalex.org/W1584432367","https://openalex.org/W1964800194","https://openalex.org/W1994941228","https://openalex.org/W2009927602","https://openalex.org/W2024166759","https://openalex.org/W2036641664","https://openalex.org/W2049381173","https://openalex.org/W2060545895","https://openalex.org/W2062581644","https://openalex.org/W2073949144","https://openalex.org/W2106913893","https://openalex.org/W2121082877","https://openalex.org/W2123728588","https://openalex.org/W2132148774","https://openalex.org/W2133940115","https://openalex.org/W2137270184","https://openalex.org/W2139712615","https://openalex.org/W2145377152","https://openalex.org/W2149897682","https://openalex.org/W2160097679","https://openalex.org/W2160611910","https://openalex.org/W2161694060","https://openalex.org/W2303756261","https://openalex.org/W2327265941","https://openalex.org/W2475126267","https://openalex.org/W2550807907","https://openalex.org/W2610148524","https://openalex.org/W2747036920","https://openalex.org/W2767472765","https://openalex.org/W2900798440","https://openalex.org/W3008047568","https://openalex.org/W3106729728","https://openalex.org/W4231029117","https://openalex.org/W4232616607","https://openalex.org/W4244567449","https://openalex.org/W4250558257","https://openalex.org/W4255079701","https://openalex.org/W6603817057","https://openalex.org/W6606167324","https://openalex.org/W6630768022","https://openalex.org/W6633885192","https://openalex.org/W6634800407","https://openalex.org/W6678286823","https://openalex.org/W6679911381","https://openalex.org/W6681208820","https://openalex.org/W6729494362"],"related_works":["https://openalex.org/W2360437063","https://openalex.org/W2623111183","https://openalex.org/W4317733979","https://openalex.org/W83946232","https://openalex.org/W2051038782","https://openalex.org/W2380581122","https://openalex.org/W3120511008","https://openalex.org/W2355334917","https://openalex.org/W2150111101","https://openalex.org/W2357638286"],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"Jdebug,":[3],"a":[4,54],"fast,":[5],"non-intrusive":[6],"and":[7,28,62,69,82,90,122,147,153,163,172],"scalable":[8],"fault":[9],"locating":[10],"tool":[11],"for":[12],"extreme-scale":[13],"parallel":[14],"applications.":[15,29],"Large-scale":[16],"debugging":[17,41,63],"has":[18],"drawn":[19],"more":[20],"attention":[21],"with":[22,131],"the":[23,46,115,125,137],"increasing":[24],"scale":[25],"of":[26,78,109,134,140],"supercomputers":[27],"To":[30],"eliminate":[31,71],"program":[32,72],"intrusion":[33],"caused":[34,95],"by":[35,96],"traditional":[36],"instrumentation":[37],"or":[38,99],"interception":[39],"during":[40,74],"information":[42,56],"acquisition,":[43],"we":[44],"introduce":[45],"out-of-band":[47],"management":[48],"into":[49],"large-scale":[50],"debugging.":[51],"We":[52],"propose":[53],"rapid":[55],"gathering":[57],"scheme":[58],"that":[59,105],"separates":[60],"user":[61],"traffic":[64],"to":[65,70,158],"solve":[66],"scalability":[67,161],"problem":[68],"interference":[73],"merging":[75],"data.":[76],"Observations":[77],"Program":[79],"Counters":[80],"(PC)":[81],"performance":[83],"characteristics":[84],"in":[85,128],"suspended":[86],"applications":[87],"find":[88,160],"abnormalities":[89],"help":[91,159],"locate":[92,124],"abnormal":[93,126,156],"threads":[94,127,157],"software":[97],"errors":[98,162],"hardware":[100,164],"failures":[101,165],"effectively.":[102],"Evaluation":[103],"shows":[104],"Jdebug":[106,151],"collects":[107],"PCs":[108],"over":[110],"20":[111],"million":[112],"cores":[113],"on":[114],"new":[116],"Sunway":[117],"supercomputer":[118],"within":[119],"1.97":[120],"seconds,":[121],"can":[123],"1.4":[129],"seconds":[130],"an":[132],"accuracy":[133],"92.5%.":[135],"In":[136],"running":[138],"test":[139],"three":[141],"fundamental":[142],"benchmarks":[143],"(HPL,":[144],"HPCG,":[145],"Graph500)":[146],"seventeen":[148],"real-world":[149],"applications,":[150],"quickly":[152],"accurately":[154],"locates":[155],"including":[166],"memory":[167],"access":[168],"failures,":[169,171,175],"communication":[170],"execution":[173],"component":[174],"which":[176],"validates":[177],"its":[178],"effectiveness.":[179]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}