{"id":"https://openalex.org/W4226368483","doi":"https://doi.org/10.1109/tpds.2022.3158742","title":"Leveraging Code Snippets to Detect Variations in the Performance of HPC Systems","display_name":"Leveraging Code Snippets to Detect Variations in the Performance of HPC Systems","publication_year":2022,"publication_date":"2022-03-15","ids":{"openalex":"https://openalex.org/W4226368483","doi":"https://doi.org/10.1109/tpds.2022.3158742"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2022.3158742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3158742","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/A5071200777","display_name":"Jidong Zhai","orcid":"https://orcid.org/0000-0002-7656-6428"},"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":true,"raw_author_name":"Jidong Zhai","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/A5002743116","display_name":"Liyan Zheng","orcid":"https://orcid.org/0000-0001-7327-748X"},"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":"Liyan Zheng","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/A5045322182","display_name":"Jinghan Sun","orcid":"https://orcid.org/0000-0001-7785-2971"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinghan Sun","raw_affiliation_strings":["Department of Computer Science, University of Illinois Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091139467","display_name":"Feng Zhang","orcid":"https://orcid.org/0000-0003-1983-7321"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zhang","raw_affiliation_strings":["Key Laboratory of Data Engineering and Knowledge Engineering (MOE), School of Information, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Data Engineering and Knowledge Engineering (MOE), School of Information, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011572497","display_name":"Xiongchao Tang","orcid":"https://orcid.org/0000-0002-1692-3964"},"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":"Xiongchao Tang","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/A5047215143","display_name":"Xuehai Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuehai Qian","raw_affiliation_strings":["Ming Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Ming Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039946576","display_name":"Bingsheng He","orcid":"https://orcid.org/0000-0001-8618-4581"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bingsheng He","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091437474","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0001-9740-6581"},"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/A5103141832","display_name":"Wenguang Chen","orcid":"https://orcid.org/0000-0002-4281-1018"},"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":"Wenguang 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":"last","author":{"id":"https://openalex.org/A5108050911","display_name":"Weimin Zheng","orcid":"https://orcid.org/0000-0002-4450-5428"},"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":"Weimin Zheng","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"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5071200777"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.9274,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7118552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"33","issue":"12","first_page":"3558","last_page":"3574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980000257492065,"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/workload","display_name":"Workload","score":0.8846592903137207},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8712778687477112},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5834089517593384},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5573124289512634},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4970758259296417},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.48167574405670166},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.42161858081817627},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42072486877441406},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40768134593963623},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21617987751960754},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1451936960220337},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.10593253374099731}],"concepts":[{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.8846592903137207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8712778687477112},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5834089517593384},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5573124289512634},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4970758259296417},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48167574405670166},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.42161858081817627},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42072486877441406},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40768134593963623},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21617987751960754},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1451936960220337},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.10593253374099731},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2022.3158742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3158742","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":[{"id":"https://openalex.org/G3439014634","display_name":null,"funder_award_id":"4202031","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G7619151073","display_name":null,"funder_award_id":"U20A20226","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7965752731","display_name":null,"funder_award_id":"L192027","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W307918303","https://openalex.org/W842872497","https://openalex.org/W1547956788","https://openalex.org/W1976006326","https://openalex.org/W1982008063","https://openalex.org/W1987450723","https://openalex.org/W2002555321","https://openalex.org/W2022856699","https://openalex.org/W2039789965","https://openalex.org/W2061156357","https://openalex.org/W2062011830","https://openalex.org/W2067263736","https://openalex.org/W2068975988","https://openalex.org/W2074135817","https://openalex.org/W2080128705","https://openalex.org/W2090520191","https://openalex.org/W2100997884","https://openalex.org/W2101778912","https://openalex.org/W2119438786","https://openalex.org/W2121204404","https://openalex.org/W2127245553","https://openalex.org/W2144038733","https://openalex.org/W2144463710","https://openalex.org/W2153773948","https://openalex.org/W2158502911","https://openalex.org/W2163039982","https://openalex.org/W2170902912","https://openalex.org/W2344975850","https://openalex.org/W2461316586","https://openalex.org/W2470920449","https://openalex.org/W2560696237","https://openalex.org/W3175777295","https://openalex.org/W3205994751","https://openalex.org/W4238826819","https://openalex.org/W4246163672","https://openalex.org/W4246166885","https://openalex.org/W4246569695","https://openalex.org/W4250558257","https://openalex.org/W4252521241","https://openalex.org/W4256344501","https://openalex.org/W6623314183","https://openalex.org/W6631615826","https://openalex.org/W6683351356","https://openalex.org/W6704925373"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W3214280620","https://openalex.org/W2329539859","https://openalex.org/W3191490922","https://openalex.org/W2765823764","https://openalex.org/W2227905990","https://openalex.org/W2079244304","https://openalex.org/W2794038527","https://openalex.org/W2151092287","https://openalex.org/W2523801036"],"abstract_inverted_index":{"Variations":[0],"in":[1,58,64,82,154,182],"the":[2,48,83,95,125,162,173,213,216,232],"performance":[3,59,84,103,214,225],"of":[4,15,26,56,85,90,98,122,127,145,169,188,215],"parallel":[5,170],"and":[6,131,148,172],"distributed":[7],"systems":[8],"are":[9,118],"becoming":[10],"increasingly":[11],"challenging.":[12],"The":[13,52,87,185],"runtimes":[14],"different":[16],"executions":[17],"can":[18,100,178],"vary":[19],"greatly":[20],"even":[21],"with":[22,165,203,223],"a":[23,132,166,200],"fixed":[24,119],"number":[25,168],"computing":[27],"nodes.":[28],"Many":[29],"HPC":[30,65,112,240],"applications":[31,113],"on":[32,161],"supercomputers":[33],"exhibit":[34],"such":[35],"variance.":[36],"This":[37,136],"not":[38],"only":[39],"leads":[40],"to":[41,79,140,151],"unpredictable":[42],"execution":[43],"times,":[44],"but":[45],"also":[46,227],"renders":[47],"system\u2019s":[49],"behavior":[50],"unintuitive.":[51],"efficient":[53],"online":[54],"detection":[55],"variations":[57,81,153,181],"is":[60,93,191,226],"an":[61,72,107,128,239],"open":[62],"problem":[63],"research.":[66],"To":[67],"solve":[68],"it,":[69],"we":[70],"propose":[71],"approach,":[73],"called":[74],"<sc":[75,158,208],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[76,159,209],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">vSensor</small>":[77,160,210],",":[78],"detect":[80,152],"systems.":[86],"key":[88],"finding":[89],"this":[91],"study":[92],"that":[94,117,176,211,229],"source":[96],"code":[97,115,147],"programs":[99],"better":[101],"represent":[102],"at":[104],"runtime":[105],"than":[106,193],"external":[108],"detector.":[109],"Specifically,":[110],"many":[111],"contain":[114],"snippets":[116,144],"workload":[120,126],"patterns":[121],"execution,":[123],"e.g.,":[124],"invariant":[129],"quantity":[130],"linearly":[133],"growing":[134],"workload.":[135],"observation":[137],"allows":[138],"us":[139],"automatically":[141],"identify":[142,180,199],"these":[143],"workload-related":[146],"use":[149],"them":[150],"performance.":[155,184],"We":[156,198],"evaluate":[157],"Tianhe-2A":[163,233],"system":[164,183,234],"large":[167],"applications,":[171],"results":[174],"indicate":[175],"it":[177],"efficiently":[179],"average":[186],"overhead":[187],"4,096":[189],"processes":[190],"less":[192],"6%":[194],"for":[195,238],"fixed-workload":[196],"v-sensors.":[197],"problematic":[201],"node":[202],"slow":[204],"memory":[205],"by":[206,218,235],"using":[207],"degrades":[212],"program":[217],"21%.":[219],"A":[220],"serious":[221],"issue":[222],"network":[224],"detected":[228],"slows":[230],"down":[231],"3.37":[236],"times":[237],"kernel.":[241]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}