{"id":"https://openalex.org/W2017914730","doi":"https://doi.org/10.1145/2159430.2159443","title":"Reducing off-chip memory traffic by selective cache management scheme in GPGPUs","display_name":"Reducing off-chip memory traffic by selective cache management scheme in GPGPUs","publication_year":2012,"publication_date":"2012-03-03","ids":{"openalex":"https://openalex.org/W2017914730","doi":"https://doi.org/10.1145/2159430.2159443","mag":"2017914730"},"language":"en","primary_location":{"id":"doi:10.1145/2159430.2159443","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2159430.2159443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Annual Workshop on General Purpose Processing with Graphics Processing Units","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/A5065064661","display_name":"Hyojin Choi","orcid":"https://orcid.org/0000-0002-1373-9790"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyojin Choi","raw_affiliation_strings":["Seoul National University, Gwanak-ro, Gwanak-gu, Seoul, Korea","Seoul National University Gwanak-ro, Gwanak-gu, Seoul, Korea#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, Gwanak-ro, Gwanak-gu, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University Gwanak-ro, Gwanak-gu, Seoul, Korea#TAB#","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jaewoo Ahn","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewoo Ahn","raw_affiliation_strings":["Seoul National University, Gwanak-ro, Gwanak-gu, Seoul, Korea","Seoul National University Gwanak-ro, Gwanak-gu, Seoul, Korea#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, Gwanak-ro, Gwanak-gu, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University Gwanak-ro, Gwanak-gu, Seoul, Korea#TAB#","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113491293","display_name":"Wonyong Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonyong Sung","raw_affiliation_strings":["Seoul National University, Gwanak-ro, Gwanak-gu, Seoul, Korea","Seoul National University Gwanak-ro, Gwanak-gu, Seoul, Korea#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, Gwanak-ro, Gwanak-gu, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University Gwanak-ro, Gwanak-gu, Seoul, Korea#TAB#","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.7565,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.65822299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"110","last_page":"119"},"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":0.9997000098228455,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8955512046813965},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6921965479850769},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6402044892311096},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.5928336977958679},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.5524994134902954},{"id":"https://openalex.org/keywords/bus-sniffing","display_name":"Bus sniffing","score":0.48572617769241333},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.4798576235771179},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4719223976135254},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.45610693097114563},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.4442911446094513},{"id":"https://openalex.org/keywords/cache-invalidation","display_name":"Cache invalidation","score":0.42208725214004517},{"id":"https://openalex.org/keywords/cache-coherence","display_name":"Cache coherence","score":0.41753748059272766},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.4055250883102417},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.3342001736164093},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24501267075538635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8955512046813965},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6921965479850769},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6402044892311096},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.5928336977958679},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.5524994134902954},{"id":"https://openalex.org/C51185590","wikidata":"https://www.wikidata.org/wiki/Q1017228","display_name":"Bus sniffing","level":5,"score":0.48572617769241333},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.4798576235771179},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4719223976135254},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.45610693097114563},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.4442911446094513},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.42208725214004517},{"id":"https://openalex.org/C141917322","wikidata":"https://www.wikidata.org/wiki/Q1025017","display_name":"Cache coherence","level":5,"score":0.41753748059272766},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.4055250883102417},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.3342001736164093},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24501267075538635}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2159430.2159443","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2159430.2159443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Annual Workshop on General Purpose Processing with Graphics Processing Units","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G2456577719","display_name":null,"funder_award_id":"NIPA-2011-C1810-1102-0018","funder_id":"https://openalex.org/F4320308943","funder_display_name":"Microsoft Research"},{"id":"https://openalex.org/G259302079","display_name":null,"funder_award_id":"2011-0027502","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3885303764","display_name":null,"funder_award_id":"NIPA-2011-C1810-1102-0018","funder_id":"https://openalex.org/F4320322065","funder_display_name":"National IT Industry Promotion Agency"}],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320322065","display_name":"National IT Industry Promotion Agency","ror":"https://ror.org/026v53e29"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W2010133494","https://openalex.org/W2018337509","https://openalex.org/W2063186542","https://openalex.org/W2080592089","https://openalex.org/W2099958604","https://openalex.org/W2102683450","https://openalex.org/W2106617337","https://openalex.org/W2116986122","https://openalex.org/W2117689653","https://openalex.org/W2118924037","https://openalex.org/W2123119012","https://openalex.org/W2124350608","https://openalex.org/W2128022558","https://openalex.org/W2129960401","https://openalex.org/W2130094715","https://openalex.org/W2136348740","https://openalex.org/W2143285027","https://openalex.org/W2159617380","https://openalex.org/W2164333604","https://openalex.org/W2165735797","https://openalex.org/W2167233984","https://openalex.org/W2169810797","https://openalex.org/W2170642695","https://openalex.org/W2310261370","https://openalex.org/W2913793997","https://openalex.org/W4247641071","https://openalex.org/W6683739747"],"related_works":["https://openalex.org/W2161101294","https://openalex.org/W2026179701","https://openalex.org/W2148571123","https://openalex.org/W4312759433","https://openalex.org/W2108638805","https://openalex.org/W4380881125","https://openalex.org/W4304166325","https://openalex.org/W2155502730","https://openalex.org/W2290179447","https://openalex.org/W2184371594"],"abstract_inverted_index":{"The":[0,59,86,106],"performance":[1],"of":[2,83,126,158],"General":[3],"Purpose":[4],"Graphics":[5],"Processing":[6],"Units":[7],"(GPGPUs)":[8],"is":[9],"frequently":[10],"limited":[11],"by":[12,96,135,149],"the":[13,66,75,81,84,90,124,127,141,150,156,162],"off-chip":[14,142,168],"memory":[15,115,143,169],"bandwidth.":[16],"To":[17],"mitigate":[18],"this":[19,48],"bandwidth":[20],"wall":[21],"problem,":[22],"recent":[23],"GPUs":[24],"are":[25,100],"equipped":[26],"with":[27],"on-chip":[28,42],"L1":[29],"and":[30,57,72,167],"L2":[31],"caches.":[32],"However,":[33],"there":[34],"has":[35],"been":[36],"little":[37],"work":[38],"for":[39,69,130],"better":[40],"utilizing":[41],"shared":[43,67,91],"caches":[44],"in":[45],"GPGPUs.":[46],"In":[47],"paper,":[49],"we":[50],"propose":[51],"two":[52],"cache":[53,68,92,120],"management":[54],"schemes:":[55],"write-buffering":[56],"read-bypassing.":[58],"write":[60],"buffering":[61],"technique":[62],"tries":[63],"to":[64,113],"utilize":[65],"inter-block":[70],"communication,":[71],"thereby":[73],"reduces":[74],"DRAM":[76],"accesses":[77,144],"as":[78,80],"much":[79],"capacity":[82],"cache.":[85],"read-bypassing":[87],"scheme":[88],"prevents":[89],"from":[93],"being":[94],"polluted":[95],"streamed":[97],"data":[98],"that":[99,140],"consumed":[101],"only":[102],"within":[103],"a":[104,131],"thread-block.":[105],"proposed":[107,128,151],"schemes":[108,129],"can":[109,145],"be":[110,146],"selectively":[111],"applied":[112],"global":[114],"instructions":[116],"using":[117],"newly":[118],"defined":[119],"operators.":[121],"We":[122,137,153],"evaluate":[123],"effects":[125],"few":[132],"GPGPU":[133],"applications":[134],"simulations.":[136],"have":[138],"shown":[139],"successfully":[147],"reduced":[148],"techniques.":[152],"also":[154],"analyze":[155],"effectiveness":[157],"these":[159],"methods":[160],"when":[161],"throughput":[163],"gap":[164],"between":[165],"cores":[166],"becomes":[170],"wider.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}