{"id":"https://openalex.org/W2127497003","doi":"https://doi.org/10.1109/hpca.2009.4798258","title":"PageNUCA: Selected policies for page-grain locality management in large shared chip-multiprocessor caches","display_name":"PageNUCA: Selected policies for page-grain locality management in large shared chip-multiprocessor caches","publication_year":2009,"publication_date":"2009-02-01","ids":{"openalex":"https://openalex.org/W2127497003","doi":"https://doi.org/10.1109/hpca.2009.4798258","mag":"2127497003"},"language":"en","primary_location":{"id":"doi:10.1109/hpca.2009.4798258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2009.4798258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE 15th International Symposium on High Performance Computer Architecture","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/A5071818120","display_name":"Mainak Chaudhuri","orcid":"https://orcid.org/0000-0001-8185-1082"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Mainak Chaudhuri","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology, Kanpur, India","Department of Computer Science & Engineering Indian Institute of Technology Kanpur\u2212208016, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology, Kanpur, India","institution_ids":["https://openalex.org/I94234084"]},{"raw_affiliation_string":"Department of Computer Science & Engineering Indian Institute of Technology Kanpur\u2212208016, India","institution_ids":["https://openalex.org/I94234084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5071818120"],"corresponding_institution_ids":["https://openalex.org/I94234084"],"apc_list":null,"apc_paid":null,"fwci":12.0492,"has_fulltext":false,"cited_by_count":81,"citation_normalized_percentile":{"value":0.98864819,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"227","last_page":"238"},"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":0.9995999932289124,"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":0.9995999932289124,"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":0.8474706411361694},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7370733618736267},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6165787577629089},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5959794521331787},{"id":"https://openalex.org/keywords/locality-of-reference","display_name":"Locality of reference","score":0.5915082693099976},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.47933778166770935},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.47564077377319336},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.4721893072128296},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.4599681496620178},{"id":"https://openalex.org/keywords/multiprocessing","display_name":"Multiprocessing","score":0.4306647479534149},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.42216798663139343},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.4215018153190613},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.3912973701953888},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3672720789909363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8474706411361694},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7370733618736267},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6165787577629089},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5959794521331787},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.5915082693099976},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.47933778166770935},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.47564077377319336},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.4721893072128296},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.4599681496620178},{"id":"https://openalex.org/C4822641","wikidata":"https://www.wikidata.org/wiki/Q846651","display_name":"Multiprocessing","level":2,"score":0.4306647479534149},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.42216798663139343},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.4215018153190613},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.3912973701953888},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3672720789909363},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpca.2009.4798258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2009.4798258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE 15th International Symposium on High Performance Computer Architecture","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.155.2858","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.155.2858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.iitk.ac.in/~mainakc/pub/cmpnuca.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W117356634","https://openalex.org/W1978154694","https://openalex.org/W1978187377","https://openalex.org/W1993223688","https://openalex.org/W2090776550","https://openalex.org/W2100720297","https://openalex.org/W2100925799","https://openalex.org/W2102081731","https://openalex.org/W2102727118","https://openalex.org/W2112300321","https://openalex.org/W2112605786","https://openalex.org/W2117324528","https://openalex.org/W2122764141","https://openalex.org/W2125858563","https://openalex.org/W2126372249","https://openalex.org/W2126716774","https://openalex.org/W2131054871","https://openalex.org/W2139239342","https://openalex.org/W2140064132","https://openalex.org/W2140455011","https://openalex.org/W2143515003","https://openalex.org/W2145252892","https://openalex.org/W2153456949","https://openalex.org/W2164988937","https://openalex.org/W2166874382","https://openalex.org/W2171164959","https://openalex.org/W2243416539","https://openalex.org/W6644613506","https://openalex.org/W6648404808"],"related_works":["https://openalex.org/W2734782074","https://openalex.org/W2114386333","https://openalex.org/W2133489088","https://openalex.org/W2098406302","https://openalex.org/W2363769136","https://openalex.org/W2116323004","https://openalex.org/W4252570104","https://openalex.org/W1970102182","https://openalex.org/W2089633376","https://openalex.org/W2524492834"],"abstract_inverted_index":{"As":[0],"the":[1,10,40,66,70,73,80,97,145,148,167,175,190,205,225,230,240,244],"last-level":[2],"on-chip":[3,14],"caches":[4],"in":[5,8],"chip-multiprocessors":[6],"increase":[7],"size,":[9],"physical":[11],"locality":[12,121],"of":[13,34,52,69,75,93,109,128,162,166,183,204],"data":[15,47,60,94],"becomes":[16],"important":[17],"for":[18,45,224],"delivering":[19],"high":[20],"performance.":[21],"The":[22,49,100],"non-uniform":[23],"access":[24,67],"latency":[25],"seen":[26],"by":[27,215],"a":[28,35,56,76,133,140,181,235],"core":[29],"to":[30,78,88,95,143,234],"different":[31],"independent":[32],"banks":[33,151],"large":[36],"cache":[37,112,138,150,170,246],"spread":[38],"over":[39],"chip":[41],"necessitates":[42],"active":[43],"mechanisms":[44,116],"improving":[46],"locality.":[48],"central":[50],"proposal":[51],"this":[53],"paper":[54],"is":[55,104],"fully":[57],"hardwired":[58,154],"coarse-grain":[59],"migration":[61,102,115],"mechanism":[62,103],"that":[63,153,238],"dynamically":[64],"monitors":[65],"patterns":[68],"cores":[71,146],"at":[72],"granularity":[74],"page":[77,92,156],"reduce":[79],"book-keeping":[81,172],"overhead":[82],"and":[83,86,117,147,171,178,196,199,208,217,229],"decides":[84],"when":[85],"where":[87],"migrate":[89],"an":[90,129],"entire":[91],"amortize":[96],"performance":[98,177],"overhead.":[99],"page-grain":[101],"compared":[105,233],"against":[106],"two":[107,118],"variants":[108],"previously":[110],"proposed":[111],"block-grain":[113],"dynamic":[114,155],"OS-assisted":[119],"static":[120],"management":[122],"mechanisms.":[123],"Our":[124],"detailed":[125],"execution-driven":[126],"simulation":[127],"eight-core":[130],"chip-multiprocessor":[131],"with":[132],"shared":[134,184,226],"16":[135],"MB":[136],"L2":[137,149,169,245],"employing":[139],"bidirectional":[141],"ring":[142],"connect":[144],"shows":[152],"migration,":[157],"while":[158],"using":[159],"only":[160],"4.8%":[161],"extra":[163],"storage":[164],"out":[165,203],"total":[168],"budget,":[173],"delivers":[174],"best":[176],"energy-efficiency":[179],"across":[180,243],"set":[182],"memory":[185,227],"parallel":[186],"applications":[187,228],"selected":[188],"from":[189],"SPLASH-2,":[191],"SPEC":[192,206],"OMP,":[193],"DARPA":[194],"DIS,":[195],"FFTW":[197],"suites":[198],"multiprogrammed":[200,231],"workloads":[201,232],"prepared":[202],"2000":[207],"BioBench":[209],"suites.":[210],"It":[211],"reduces":[212],"execution":[213],"time":[214],"18.7%":[216],"12.6%":[218],"on":[219],"average":[220],"(geometric":[221],"mean)":[222],"respectively":[223],"baseline":[236],"architecture":[237],"distributes":[239],"pages":[241],"round-robin":[242],"banks.":[247]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":11}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}