{"id":"https://openalex.org/W2065562952","doi":"https://doi.org/10.1145/2716282.2716283","title":"Adaptive GPU cache bypassing","display_name":"Adaptive GPU cache bypassing","publication_year":2015,"publication_date":"2015-02-03","ids":{"openalex":"https://openalex.org/W2065562952","doi":"https://doi.org/10.1145/2716282.2716283","mag":"2065562952"},"language":"en","primary_location":{"id":"doi:10.1145/2716282.2716283","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2716282.2716283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop on General Purpose Processing using GPUs","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/A5078433306","display_name":"Yingying Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yingying Tian","raw_affiliation_strings":["Texas A&amp;M University, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&amp;M University, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024878606","display_name":"Sooraj Puthoor","orcid":"https://orcid.org/0000-0003-0285-5742"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]},{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Sooraj Puthoor","raw_affiliation_strings":["AMD Research, USA","[AMD Research, USA]"],"affiliations":[{"raw_affiliation_string":"AMD Research, USA","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"[AMD Research, USA]","institution_ids":["https://openalex.org/I1311921367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034110574","display_name":"Joseph L. Greathouse","orcid":"https://orcid.org/0000-0003-0181-5511"},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]},{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Joseph L. Greathouse","raw_affiliation_strings":["AMD Research, USA","[AMD Research, USA]"],"affiliations":[{"raw_affiliation_string":"AMD Research, USA","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"[AMD Research, USA]","institution_ids":["https://openalex.org/I1311921367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077056823","display_name":"Bradford M. Beckmann","orcid":"https://orcid.org/0000-0002-5444-6521"},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]},{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Bradford M. Beckmann","raw_affiliation_strings":["AMD Research, USA","[AMD Research, USA]"],"affiliations":[{"raw_affiliation_string":"AMD Research, USA","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"[AMD Research, USA]","institution_ids":["https://openalex.org/I1311921367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100612822","display_name":"Daniel A. Jim\u00e9nez","orcid":"https://orcid.org/0000-0001-5658-4883"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel A. Jim\u00e9nez","raw_affiliation_strings":["Texas A&amp;M University, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&amp;M University, USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5078433306"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":12.2733,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.99035775,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"35"},"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":0.9965000152587891,"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":0.9962000250816345,"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":0.8842124938964844},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.8467162847518921},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.8016839027404785},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.7481805682182312},{"id":"https://openalex.org/keywords/cache-invalidation","display_name":"Cache invalidation","score":0.7247268557548523},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6826379895210266},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.6790621280670166},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.6483063101768494},{"id":"https://openalex.org/keywords/page-cache","display_name":"Page cache","score":0.6173251867294312},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5650990605354309},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.4628210961818695},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.41516023874282837},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.390848845243454},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.34058672189712524},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.2792290449142456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8842124938964844},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.8467162847518921},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.8016839027404785},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.7481805682182312},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.7247268557548523},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6826379895210266},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.6790621280670166},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.6483063101768494},{"id":"https://openalex.org/C36340418","wikidata":"https://www.wikidata.org/wiki/Q7124288","display_name":"Page cache","level":5,"score":0.6173251867294312},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5650990605354309},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.4628210961818695},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.41516023874282837},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.390848845243454},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.34058672189712524},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.2792290449142456},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2716282.2716283","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2716282.2716283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop on General Purpose Processing using GPUs","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9200000166893005,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G793011302","display_name":null,"funder_award_id":"1216604,1012127","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307757","display_name":"Advanced Micro Devices","ror":"https://ror.org/04kd6c783"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1675130169","https://openalex.org/W1968432902","https://openalex.org/W2000335122","https://openalex.org/W2023999916","https://openalex.org/W2028499920","https://openalex.org/W2029577083","https://openalex.org/W2034256066","https://openalex.org/W2047060659","https://openalex.org/W2067441262","https://openalex.org/W2080592089","https://openalex.org/W2090809553","https://openalex.org/W2092300541","https://openalex.org/W2095258606","https://openalex.org/W2096648046","https://openalex.org/W2097336080","https://openalex.org/W2099084006","https://openalex.org/W2100011668","https://openalex.org/W2100901045","https://openalex.org/W2101216289","https://openalex.org/W2106617337","https://openalex.org/W2122108187","https://openalex.org/W2126952393","https://openalex.org/W2128022558","https://openalex.org/W2131154433","https://openalex.org/W2135639895","https://openalex.org/W2141302915","https://openalex.org/W2146623049","https://openalex.org/W2147657366","https://openalex.org/W2149412112","https://openalex.org/W2152356827","https://openalex.org/W2152609355","https://openalex.org/W2156064678","https://openalex.org/W2167357818","https://openalex.org/W2169880332","https://openalex.org/W2295862081","https://openalex.org/W2399715892","https://openalex.org/W2464177207","https://openalex.org/W3138798301","https://openalex.org/W4231459869","https://openalex.org/W4250981202","https://openalex.org/W6637266722"],"related_works":["https://openalex.org/W2133489088","https://openalex.org/W2363769136","https://openalex.org/W2114386333","https://openalex.org/W2126408955","https://openalex.org/W2734782074","https://openalex.org/W2539712666","https://openalex.org/W2148571123","https://openalex.org/W2118932116","https://openalex.org/W2396934146","https://openalex.org/W2369103246"],"abstract_inverted_index":{"Modern":[0],"graphics":[1],"processing":[2],"units":[3],"(GPUs)":[4],"include":[5,34],"hardware-":[6],"controlled":[7],"caches":[8,66,105,206],"to":[9,33,47,97,124,165,199,208,216,231],"reduce":[10],"bandwidth":[11],"requirements":[12],"and":[13,140,176,212],"energy":[14,134,172],"consumption.":[15,112],"However,":[16],"current":[17,61,204],"GPU":[18,26,93,104,117,205],"cache":[19,50,94,118,144,169,218],"hierarchies":[20],"are":[21,122],"inefficient":[22],"for":[23,119,185,223],"general":[24],"purpose":[25],"(GPGPU)":[27],"comput-":[28],"ing.":[29],"GPGPU":[30],"workloads":[31],"tend":[32],"data":[35,74,82,157],"structures":[36],"that":[37,83,121,187],"would":[38],"not":[39,189],"fit":[40,86],"in":[41,147],"any":[42],"reasonably":[43],"sized":[44],"caches,":[45],"leading":[46],"very":[48],"low":[49],"hit":[51],"rates.":[52],"This":[53,131],"problem":[54],"is":[55,182,235],"exacerbated":[56],"by":[57,135,174,178],"the":[58,88,100,116,201,214,224,229],"design":[59],"of":[60,102,203],"GPUs,":[62],"which":[63,217],"share":[64],"small":[65,103],"be-":[67],"tween":[68],"many":[69],"threads.":[70],"Caching":[71],"these":[72],"streaming":[73],"struc-":[75],"tures":[76],"needlessly":[77],"burns":[78],"power":[79,111,177],"while":[80,106,142,170],"evicting":[81],"may":[84],"otherwise":[85],"into":[87],"cache.":[89],"We":[90,150,194],"propose":[91],"a":[92,154,166,196],"management":[95],"technique":[96,132,181],"im-":[98],"prove":[99],"efficiency":[101],"further":[107],"re-":[108],"ducing":[109],"their":[110],"It":[113],"adaptively":[114],"bypasses":[115],"blocks":[120],"unlikely":[123],"be":[125],"referenced":[126],"again":[127],"before":[128],"being":[129],"evicted.":[130],"saves":[133],"avoid-":[136],"ing":[137],"needless":[138],"insertions":[139],"evictions":[141],"avoiding":[143],"pollution,":[145],"resulting":[146],"better":[148],"performance.":[149],"show":[151,213],"that,":[152],"with":[153],"16KB":[155],"L1":[156,168],"cache,":[158],"dynamic":[159],"bypassing":[160,219],"achieves":[161],"sim-":[162],"ilar":[163],"performance":[164,226],"double-sized":[167],"reducing":[171],"consumption":[173],"25%":[175],"18%.":[179],"The":[180],"especially":[183],"interesting":[184],"programs":[186],"do":[188],"use":[190],"programmer-managed":[191,209],"scratchpad":[192,210,233],"memories.":[193],"give":[195],"case":[197],"study":[198],"demonstrate":[200],"inefficiency":[202],"compared":[207],"memories":[211,234],"extent":[215],"can":[220],"make":[221],"up":[222],"potential":[225],"loss":[227],"where":[228],"effort":[230],"program":[232],"impractical.":[236]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
