{"id":"https://openalex.org/W2170241157","doi":"https://doi.org/10.1145/1669112.1669165","title":"Comparing cache architectures and coherency protocols on x86-64 multicore SMP systems","display_name":"Comparing cache architectures and coherency protocols on x86-64 multicore SMP systems","publication_year":2009,"publication_date":"2009-12-12","ids":{"openalex":"https://openalex.org/W2170241157","doi":"https://doi.org/10.1145/1669112.1669165","mag":"2170241157"},"language":"en","primary_location":{"id":"doi:10.1145/1669112.1669165","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1669112.1669165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"type":"conference-paper","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/A5028693652","display_name":"Daniel Hackenberg","orcid":"https://orcid.org/0000-0002-8491-770X"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Hackenberg","raw_affiliation_strings":["Technische Universit\u00e4t Dresden, Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091536912","display_name":"Daniel Molka","orcid":"https://orcid.org/0000-0001-8375-2280"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Molka","raw_affiliation_strings":["Technische Universit\u00e4t Dresden, Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040346332","display_name":"Wolfgang E. Nagel","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang E. Nagel","raw_affiliation_strings":["Technische Universit\u00e4t Dresden, Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78650965"],"apc_list":null,"apc_paid":null,"fwci":4.7554,"has_fulltext":false,"cited_by_count":123,"citation_normalized_percentile":{"value":0.9636685,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"413","last_page":"422"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9988999962806702,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983999729156494,"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/x86","display_name":"x86","score":0.9002339839935303},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8120720386505127},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6866729855537415},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6541136503219604},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6350376605987549},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4667304754257202},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2778337001800537},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.06609341502189636}],"concepts":[{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.9002339839935303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8120720386505127},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6866729855537415},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6541136503219604},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6350376605987549},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4667304754257202},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2778337001800537},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.06609341502189636}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1669112.1669165","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1669112.1669165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.466.3810","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.466.3810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.freebsd.org/~lstewart/articles/cache-performance-x86-2009.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1492601037","https://openalex.org/W1546459231","https://openalex.org/W1555915743","https://openalex.org/W1819012263","https://openalex.org/W2004937484","https://openalex.org/W2033875825","https://openalex.org/W2086202544","https://openalex.org/W2181609752","https://openalex.org/W3113306529","https://openalex.org/W6672045869"],"related_works":["https://openalex.org/W1542410906","https://openalex.org/W2096357811","https://openalex.org/W197049984","https://openalex.org/W1992604140","https://openalex.org/W1993191611","https://openalex.org/W2023938924","https://openalex.org/W2072005592","https://openalex.org/W1990800384","https://openalex.org/W2766023593","https://openalex.org/W2918840249"],"abstract_inverted_index":{"Across":[0],"a":[1,22,57],"broad":[2],"range":[3],"of":[4,25,48,59,79,94,103,138,154],"applications,":[5],"multicore":[6],"technology":[7],"is":[8,21,97],"the":[9,26,71,76,84,147,152,155],"most":[10],"important":[11,45],"factor":[12],"that":[13,33,116],"drives":[14],"today's":[15],"microprocessor":[16],"performance":[17,90,133,153],"improvements.":[18],"Closely":[19],"coupled":[20],"growing":[23],"complexity":[24],"memory":[27,50,72,120,132,156],"subsystems":[28,51],"with":[29,99,107],"several":[30],"cache":[31,80,85],"levels":[32],"need":[34],"to":[35,39,67,82],"be":[36],"exploited":[37],"efficiently":[38],"gain":[40],"optimal":[41],"application":[42],"performance.":[43],"Many":[44],"implementation":[46],"details":[47],"these":[49],"are":[52],"undocumented.":[53],"We":[54,74],"therefore":[55],"present":[56,130],"set":[58],"sophisticated":[60],"benchmarks":[61,128],"for":[62],"latency":[63],"and":[64,88,110,122,135],"bandwidth":[65],"measurements":[66],"arbitrary":[68],"locations":[69],"in":[70,144],"subsystem.":[73,157],"consider":[75],"coherency":[77,86],"state":[78],"lines":[81],"analyze":[83],"protocols":[87],"their":[89],"impact.":[91],"The":[92],"potential":[93],"our":[95,127],"approach":[96],"demonstrated":[98],"an":[100],"in-depth":[101],"comparison":[102,142],"ccNUMA":[104],"multiprocessor":[105],"systems":[106],"AMD":[108],"(Shanghai)":[109],"Intel":[111],"(Nehalem-EP)":[112],"quad-core":[113],"x86-64":[114],"processors":[115],"both":[117,139],"feature":[118],"integrated":[119],"controllers":[121],"coherent":[123],"point-to-point":[124],"interconnects.":[125],"Using":[126],"we":[129],"fundamental":[131],"data":[134],"architectural":[136],"properties":[137],"processors.":[140],"Our":[141],"reveals":[143],"detail":[145],"how":[146],"microarchitectural":[148],"differences":[149],"tremendously":[150],"affect":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":19},{"year":2013,"cited_by_count":16},{"year":2012,"cited_by_count":7}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}