{"id":"https://openalex.org/W2105032049","doi":"https://doi.org/10.1145/1006209.1006250","title":"Detailed cache coherence characterization for OpenMP benchmarks","display_name":"Detailed cache coherence characterization for OpenMP benchmarks","publication_year":2004,"publication_date":"2004-06-26","ids":{"openalex":"https://openalex.org/W2105032049","doi":"https://doi.org/10.1145/1006209.1006250","mag":"2105032049"},"language":"en","primary_location":{"id":"doi:10.1145/1006209.1006250","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1006209.1006250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th annual international conference on Supercomputing","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/A5050458084","display_name":"Jaydeep Marathe","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jaydeep Marathe","raw_affiliation_strings":["North Carolina State University, Raleigh, NC","North Carolina State University, Raleigh, NC;"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"North Carolina State University, Raleigh, NC;","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078679646","display_name":"Anita Nagarajan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146682","display_name":"Intel (India)","ror":"https://ror.org/04f2n1245","country_code":"IN","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210146682"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anita Nagarajan","raw_affiliation_strings":["Intel Technology India Pvt. Ltd., Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Intel Technology India Pvt. Ltd., Bangalore, India","institution_ids":["https://openalex.org/I4210146682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107279953","display_name":"Frank Mueller","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank Mueller","raw_affiliation_strings":["North Carolina State University, Raleigh, NC","North Carolina State University, Raleigh, NC;"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"North Carolina State University, Raleigh, NC;","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050458084"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":1.8486,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84642596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"287","last_page":"297"},"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":0.9998000264167786,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8510814905166626},{"id":"https://openalex.org/keywords/cache-coherence","display_name":"Cache coherence","score":0.7904033660888672},{"id":"https://openalex.org/keywords/spmd","display_name":"SPMD","score":0.6678901314735413},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6047675609588623},{"id":"https://openalex.org/keywords/interleaving","display_name":"Interleaving","score":0.47296637296676636},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4706662893295288},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.46761783957481384},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4585667848587036},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.3953053951263428},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.37361109256744385},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2196490466594696}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8510814905166626},{"id":"https://openalex.org/C141917322","wikidata":"https://www.wikidata.org/wiki/Q1025017","display_name":"Cache coherence","level":5,"score":0.7904033660888672},{"id":"https://openalex.org/C7042729","wikidata":"https://www.wikidata.org/wiki/Q2289219","display_name":"SPMD","level":2,"score":0.6678901314735413},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6047675609588623},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.47296637296676636},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4706662893295288},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.46761783957481384},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4585667848587036},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.3953053951263428},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.37361109256744385},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2196490466594696},{"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":3,"locations":[{"id":"doi:10.1145/1006209.1006250","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1006209.1006250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th annual international conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.lib.ncsu.edu:1840.4/909","is_oa":false,"landing_page_url":"http://www.lib.ncsu.edu/resolver/1840.4/909","pdf_url":null,"source":{"id":"https://openalex.org/S4306402468","display_name":"NCSU Libraries Repository (North Carolina State University Libraries)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I137902535","host_organization_name":"North Carolina State University","host_organization_lineage":["https://openalex.org/I137902535"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Technical report"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.10.2142","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.2142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://moss.csc.ncsu.edu/~mueller/ftp/pub/mueller/papers/ics04.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W106099067","https://openalex.org/W574151725","https://openalex.org/W1510263988","https://openalex.org/W1560342753","https://openalex.org/W1560751310","https://openalex.org/W1569032152","https://openalex.org/W1804921254","https://openalex.org/W1977263182","https://openalex.org/W1980257390","https://openalex.org/W1997291344","https://openalex.org/W2011271680","https://openalex.org/W2019747336","https://openalex.org/W2023029176","https://openalex.org/W2035330754","https://openalex.org/W2040183246","https://openalex.org/W2041330544","https://openalex.org/W2080329299","https://openalex.org/W2086890464","https://openalex.org/W2100928955","https://openalex.org/W2104480547","https://openalex.org/W2104916267","https://openalex.org/W2106961628","https://openalex.org/W2125955291","https://openalex.org/W2140384194","https://openalex.org/W2141342364","https://openalex.org/W2150881394","https://openalex.org/W2160468841","https://openalex.org/W2544403503","https://openalex.org/W2585550685","https://openalex.org/W2677178705","https://openalex.org/W3041276148","https://openalex.org/W4242456090","https://openalex.org/W4250702372"],"related_works":["https://openalex.org/W2290179447","https://openalex.org/W2389264397","https://openalex.org/W2098134458","https://openalex.org/W2145592252","https://openalex.org/W2118508246","https://openalex.org/W2407815036","https://openalex.org/W4255008187","https://openalex.org/W2123859627","https://openalex.org/W4250205214","https://openalex.org/W2036306661"],"abstract_inverted_index":{"Past":[0],"work":[1,82],"on":[2,12,107],"studying":[3,13],"cache":[4,183],"coherence":[5,60,147,151,184,208,263],"in":[6,35,40,62,118,142,168,215,259,271],"shared-memory":[7],"symmetric":[8],"multiprocessors":[9],"(SMPs)":[10],"concentrates":[11],"aggregate":[14],"events,":[15],"often":[16],"from":[17,122,232],"an":[18],"architecture":[19],"point":[20],"of":[21,33,50,64,80,103,116,139,176,213,240,267],"view.":[22],"However,":[23],"this":[24,81],"approach":[25],"provides":[26],"insufficient":[27],"information":[28,209],"about":[29],"the":[30,48,65,114,123,128,169,174,199,211,216],"exact":[31],"sources":[32],"inefficiencies":[34],"parallel":[36],"applications.":[37],"For":[38],"SMPs":[39],"contemporary":[41],"clusters,":[42],"application":[43,66,217],"performance":[44,135,202],"is":[45,186],"impacted":[46],"by":[47,94,131],"pattern":[49],"shared":[51],"memory":[52,91],"usage,":[53],"and":[54,74,126,163,222,225,247,265],"it":[55],"becomes":[56],"essential":[57],"to":[58,145,160,164,245,269],"understand":[59],"behavior":[61],"terms":[63],"program":[67,251],"constructs":[68],"--":[69,149,159],"such":[70],"as":[71,84,153,155,193],"data":[72,95,120,161,223],"structures":[73,162,224],"source":[75,170,220],"code":[76],"lines.The":[77],"technical":[78],"contributions":[79],"are":[83],"follows.":[85],"We":[86,112],"introduce":[87],"ccSIM,":[88,241],"a":[89,108],"cache-coherent":[90],"simulator":[92],"fed":[93],"traces":[96,121],"obtained":[97],"through":[98],"on-the-fly":[99],"dynamic":[100],"binary":[101],"rewriting":[102],"OpenMP":[104,256],"benchmarks":[105],"executing":[106],"Power3":[109],"SMP":[110],"node.":[111],"explore":[113],"degrees":[115],"freedom":[117],"interleaving":[119],"different":[124],"processors":[125],"assess":[127],"simulation":[129],"accuracy":[130],"comparing":[132],"with":[133,255],"hardware":[134,201],"counters.":[136],"The":[137],"novelty":[138],"ccSIM":[140],"lies":[141],"its":[143,194],"ability":[144],"relate":[146],"traffic":[148,185,196],"specifically":[150],"misses":[152,264],"well":[154],"their":[156,165],"progenitor":[157],"invalidations":[158,214],"reference":[166],"locations":[167],"program,":[171],"thereby":[172],"facilitating":[173],"detection":[175],"inefficiencies.":[177],"Our":[178],"experiments":[179],"demonstrate":[180],"that":[181],"(a)":[182],"simulated":[187],"accurately":[188],"for":[189,230,250,275],"SPMD":[190],"programming":[191],"styles":[192],"invalidation":[195],"closely":[197],"matches":[198],"corresponding":[200],"counters,":[203],"(b)":[204],"we":[205,227,242],"derive":[206],"detailed":[207],"indicating":[210],"location":[212],"code,":[218],"i.e,":[219],"line":[221],"(c)":[226],"illustrate":[228],"opportunities":[229,249],"optimizations":[231],"these":[233,237],"details.":[234],"By":[235],"exploiting":[236],"unique":[238],"features":[239],"were":[243],"able":[244],"identify":[246],"locate":[248],"transformations,":[252],"including":[253],"interactions":[254],"constructs,":[257],"resulting":[258],"both":[260],"significantly":[261],"decreased":[262],"savings":[266],"up":[268],"73%":[270],"wall-clock":[272],"execution":[273],"time":[274],"several":[276],"real-world":[277],"benchmarks.":[278]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}