{"id":"https://openalex.org/W2887779342","doi":"https://doi.org/10.1145/3225058.3225142","title":"Unveiling Thread Communication Bottlenecks Using Hardware-Independent Metrics","display_name":"Unveiling Thread Communication Bottlenecks Using Hardware-Independent Metrics","publication_year":2018,"publication_date":"2018-08-08","ids":{"openalex":"https://openalex.org/W2887779342","doi":"https://doi.org/10.1145/3225058.3225142","mag":"2887779342"},"language":"en","primary_location":{"id":"doi:10.1145/3225058.3225142","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3225058.3225142","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3225058.3225142","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3225058.3225142","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028887858","display_name":"Arya Mazaheri","orcid":"https://orcid.org/0000-0002-5671-4710"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Arya Mazaheri","raw_affiliation_strings":["Technische Universit\u00e4t Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018089961","display_name":"Felix Wolf","orcid":"https://orcid.org/0000-0001-6595-3599"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Wolf","raw_affiliation_strings":["Technische Universit\u00e4t Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079359777","display_name":"Ali Jannesari","orcid":"https://orcid.org/0000-0001-8672-5317"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Jannesari","raw_affiliation_strings":["Iowa State University, Ames, IA, USA"],"affiliations":[{"raw_affiliation_string":"Iowa State University, Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028887858"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.5255,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6330487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9991999864578247,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8837075233459473},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.7668715715408325},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7256345748901367},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6199473142623901},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6036432385444641},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5861036777496338},{"id":"https://openalex.org/keywords/cache-coherence","display_name":"Cache coherence","score":0.5340413451194763},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4993557929992676},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4659351706504822},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4247826933860779},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.42196419835090637},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.41132423281669617},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.3452714681625366},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.2408122718334198},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21248593926429749},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1441117823123932}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8837075233459473},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.7668715715408325},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7256345748901367},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6199473142623901},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6036432385444641},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5861036777496338},{"id":"https://openalex.org/C141917322","wikidata":"https://www.wikidata.org/wiki/Q1025017","display_name":"Cache coherence","level":5,"score":0.5340413451194763},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4993557929992676},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4659351706504822},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4247826933860779},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.42196419835090637},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.41132423281669617},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.3452714681625366},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.2408122718334198},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21248593926429749},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1441117823123932},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3225058.3225142","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3225058.3225142","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3225058.3225142","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:108665","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/108665/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"}],"best_oa_location":{"id":"doi:10.1145/3225058.3225142","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3225058.3225142","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3225058.3225142","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1326792750","display_name":null,"funder_award_id":"01IH16008","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G352791218","display_name":null,"funder_award_id":"(BMBF)","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G4135887580","display_name":null,"funder_award_id":"01IH16008D","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G562809674","display_name":null,"funder_award_id":"DE-SC0015524","funder_id":"https://openalex.org/F4320337674","funder_display_name":"Wind Energy Technologies Office"},{"id":"https://openalex.org/G7354878288","display_name":null,"funder_award_id":"DE-SC0015524","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320320875","display_name":"Deutscher Akademischer Austauschdienst","ror":"https://ror.org/039djdh30"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320324316","display_name":"Klaus Tschira Stiftung","ror":"https://ror.org/052jep661"},{"id":"https://openalex.org/F4320334761","display_name":"German Academic Exchange Service London","ror":"https://ror.org/039djdh30"},{"id":"https://openalex.org/F4320337674","display_name":"Wind Energy Technologies Office","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2887779342.pdf","grobid_xml":"https://content.openalex.org/works/W2887779342.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1207262704","https://openalex.org/W1464406661","https://openalex.org/W1484238698","https://openalex.org/W1574846734","https://openalex.org/W1965100924","https://openalex.org/W1972541532","https://openalex.org/W1976251241","https://openalex.org/W1976514563","https://openalex.org/W1980052993","https://openalex.org/W1999786966","https://openalex.org/W2014538051","https://openalex.org/W2020035025","https://openalex.org/W2024717934","https://openalex.org/W2032616619","https://openalex.org/W2038229768","https://openalex.org/W2056303926","https://openalex.org/W2064541493","https://openalex.org/W2065866286","https://openalex.org/W2078781838","https://openalex.org/W2080592089","https://openalex.org/W2091250014","https://openalex.org/W2111056844","https://openalex.org/W2122452659","https://openalex.org/W2130531463","https://openalex.org/W2133407588","https://openalex.org/W2144433126","https://openalex.org/W2145021036","https://openalex.org/W2160602621","https://openalex.org/W2161867520","https://openalex.org/W2169828639","https://openalex.org/W2169875292","https://openalex.org/W2169987756","https://openalex.org/W2293417476","https://openalex.org/W2302861480","https://openalex.org/W2397454561","https://openalex.org/W3008756550","https://openalex.org/W3030672572","https://openalex.org/W3148339845","https://openalex.org/W4244012835","https://openalex.org/W4256386389"],"related_works":["https://openalex.org/W2145592252","https://openalex.org/W2118508246","https://openalex.org/W2407815036","https://openalex.org/W4255008187","https://openalex.org/W4250205214","https://openalex.org/W2036306661","https://openalex.org/W2162521625","https://openalex.org/W2143087414","https://openalex.org/W2286165368","https://openalex.org/W1797968800"],"abstract_inverted_index":{"A":[0],"critical":[1],"factor":[2],"for":[3,143],"developing":[4],"robust":[5],"shared-memory":[6],"applications":[7],"is":[8],"the":[9,13,16,90,100,157,166,187,192,204,209,216],"efficient":[10],"use":[11],"of":[12,69,92,102,127,168,211,221,227],"cache":[14,217],"and":[15,25,36,50,95,116,124,140,159,219],"communication":[17,33,49,93,103,117,139,173],"between":[18,34,66],"threads.":[19],"Inappropriate":[20],"data":[21,64,80,179],"structures,":[22],"algorithm":[23,183],"design,":[24],"inefficient":[26,178],"thread":[27,48,125,138],"affinity":[28],"may":[29],"result":[30],"in":[31,194,225],"superfluous":[32],"threads/cores":[35],"severe":[37],"performance":[38,115,193],"problems.":[39],"For":[40],"this":[41,106],"reason,":[42],"state-of-the-art":[43],"profiling":[44],"tools":[45,84],"focus":[46,97],"on":[47,98,147,156],"behavior":[51],"to":[52,59,78,113,136,177,199,214],"present":[53],"different":[54],"metrics":[55,135],"that":[56,119],"enable":[57],"programmers":[58],"write":[60],"cache-friendly":[61],"programs.":[62],"The":[63],"shared":[65],"a":[67,75,110,148,222],"pair":[68],"threads":[70],"should":[71],"be":[72],"reused":[73],"with":[74],"reasonable":[76],"distance":[77],"preserve":[79],"locality.":[81],"However,":[82],"existing":[83],"do":[85],"not":[86],"take":[87],"into":[88],"account":[89],"locality":[91,174],"events":[94],"mainly":[96],"analyzing":[99],"amount":[101],"instead.":[104],"In":[105],"paper,":[107],"we":[108,190,207],"introduce":[109],"new":[111,133],"method":[112,213],"analyze":[114],"bottlenecks":[118],"arise":[120],"from":[121],"data-access":[122],"patterns":[123],"interactions":[126],"each":[128],"code":[129,150],"region.":[130,151],"We":[131,152],"propose":[132],"hardware-independent":[134],"characterize":[137],"provide":[141],"suggestions":[142],"applying":[144,186],"appropriate":[145],"optimizations":[146],"specific":[149],"evaluated":[153],"our":[154,169,212],"approach":[155,170],"SPLASH":[158],"Rodinia":[160,195],"benchmark":[161],"suites.":[162],"Experimental":[163],"results":[164],"validate":[165],"effectiveness":[167],"by":[171,197,202],"finding":[172],"issues":[175],"due":[176],"structures":[180],"and/or":[181],"poor":[182],"implementations.":[184],"By":[185],"suggested":[188],"optimizations,":[189],"improved":[191],"benchmarks":[196],"up":[198],"56%.":[200],"Furthermore,":[201],"varying":[203],"input":[205],"size":[206],"demonstrated":[208],"ability":[210],"assess":[215],"usage":[218],"scalability":[220],"given":[223],"application":[224],"terms":[226],"its":[228],"inherent":[229],"communication.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
