{"id":"https://openalex.org/W3008498625","doi":"https://doi.org/10.1145/3332466.3374518","title":"Identifying scalability bottlenecks for large-scale parallel programs with graph analysis","display_name":"Identifying scalability bottlenecks for large-scale parallel programs with graph analysis","publication_year":2020,"publication_date":"2020-02-19","ids":{"openalex":"https://openalex.org/W3008498625","doi":"https://doi.org/10.1145/3332466.3374518","mag":"3008498625"},"language":"en","primary_location":{"id":"doi:10.1145/3332466.3374518","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3332466.3374518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","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/A5063581276","display_name":"Yuyang Jin","orcid":"https://orcid.org/0000-0003-2358-3395"},"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":"Yuyang Jin","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100735476","display_name":"Haojie Wang","orcid":"https://orcid.org/0000-0003-4605-148X"},"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":"Haojie Wang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"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":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026990786","display_name":"Torsten Hoefler","orcid":"https://orcid.org/0000-0002-1333-9797"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Torsten Hoefler","raw_affiliation_strings":["ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331713","display_name":"Xu Liu","orcid":"https://orcid.org/0000-0002-8984-5485"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu Liu","raw_affiliation_strings":["College of William and Mary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of William and Mary","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"last","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":false,"raw_author_name":"Jidong Zhai","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.236,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.45471193,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"409","last_page":"410"},"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":0.9961000084877014,"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":0.994700014591217,"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":0.8636516332626343},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7622039318084717},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6985001564025879},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6941941380500793},{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.624293327331543},{"id":"https://openalex.org/keywords/serialization","display_name":"Serialization","score":0.6073784828186035},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.600502073764801},{"id":"https://openalex.org/keywords/call-graph","display_name":"Call graph","score":0.5114995241165161},{"id":"https://openalex.org/keywords/root-cause","display_name":"Root cause","score":0.4940636456012726},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.48806607723236084},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.46717458963394165},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.46396198868751526},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4459708333015442},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4418613910675049},{"id":"https://openalex.org/keywords/root-cause-analysis","display_name":"Root cause analysis","score":0.4411194920539856},{"id":"https://openalex.org/keywords/static-analysis","display_name":"Static analysis","score":0.42490851879119873},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.26388663053512573},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22988149523735046},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22605150938034058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8636516332626343},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7622039318084717},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6985001564025879},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6941941380500793},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.624293327331543},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.6073784828186035},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.600502073764801},{"id":"https://openalex.org/C102379954","wikidata":"https://www.wikidata.org/wiki/Q2589940","display_name":"Call graph","level":2,"score":0.5114995241165161},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.4940636456012726},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.48806607723236084},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.46717458963394165},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46396198868751526},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4459708333015442},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4418613910675049},{"id":"https://openalex.org/C130963320","wikidata":"https://www.wikidata.org/wiki/Q1401207","display_name":"Root cause analysis","level":2,"score":0.4411194920539856},{"id":"https://openalex.org/C97686452","wikidata":"https://www.wikidata.org/wiki/Q7604153","display_name":"Static analysis","level":2,"score":0.42490851879119873},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26388663053512573},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22988149523735046},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22605150938034058},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C77595967","wikidata":"https://www.wikidata.org/wiki/Q3151013","display_name":"Forensic 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:10.1145/3332466.3374518","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3332466.3374518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2108177987","https://openalex.org/W2111693532","https://openalex.org/W2144038733"],"related_works":["https://openalex.org/W2030594396","https://openalex.org/W2754538212","https://openalex.org/W2490884653","https://openalex.org/W4200610016","https://openalex.org/W2183996497","https://openalex.org/W129587375","https://openalex.org/W2110363179","https://openalex.org/W2056250485","https://openalex.org/W2535098331","https://openalex.org/W4255366506"],"abstract_inverted_index":{"Scaling":[0],"a":[1,77],"parallel":[2],"program":[3],"to":[4,10,64,80,89,98,144],"modern":[5],"supercomputers":[6],"is":[7],"challenging":[8],"due":[9],"inter-process":[11],"communication,":[12],"code":[13],"serialization,":[14],"and":[15,85,93,133],"resource":[16],"contention.":[17],"Performance":[18],"analysis":[19,62,96],"tools":[20],"for":[21,43,130,142],"finding":[22],"such":[23],"scaling":[24,104],"bottlenecks":[25,129],"either":[26],"base":[27],"on":[28,112,140],"profiling":[29],"or":[30],"tracing.":[31],"Profiling":[32],"incurs":[33],"lower":[34],"overheads":[35],"but":[36],"does":[37],"not":[38],"capture":[39],"detailed":[40],"dependencies":[41],"needed":[42],"root-cause":[44],"analyses.":[45],"Tracing":[46],"collects":[47],"all":[48],"information":[49],"at":[50,76],"prohibitive":[51],"overheads.":[52],"In":[53],"this":[54],"work,":[55],"we":[56],"develop":[57],"ScalAna":[58,108],"that":[59,118],"uses":[60],"static":[61],"techniques":[63,88],"achieve":[65],"the":[66,72,100,113,124],"best":[67],"of":[68,74,103,127],"both":[69],"worlds---it":[70],"enables":[71],"analyzability":[73],"traces":[75],"cost":[78],"similar":[79],"profiling.":[81],"We":[82,106],"leverage":[83],"compiler":[84],"runtime":[86],"lightweight":[87],"generate":[90],"performance":[91],"graph":[92,95],"perform":[94],"algorithm":[97],"detect":[99],"root":[101,125],"cause":[102,126],"issues.":[105],"evaluate":[107],"with":[109],"real":[110,131],"applications":[111,132],"Tianhe-2":[114],"supercomputer.":[115],"Results":[116],"show":[117],"our":[119],"approach":[120],"can":[121],"effectively":[122],"locate":[123],"scalability":[128],"incur":[134],"less":[135],"than":[136],"6.38%":[137],"overhead":[138],"(1.89%":[139],"average)":[141],"up":[143],"2,048":[145],"processes.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
