{"id":"https://openalex.org/W2064701823","doi":"https://doi.org/10.1109/tc.2015.2395435","title":"GREEN Cache: Exploiting the Disciplined Memory Model of OpenCL on GPUs","display_name":"GREEN Cache: Exploiting the Disciplined Memory Model of OpenCL on GPUs","publication_year":2015,"publication_date":"2015-01-22","ids":{"openalex":"https://openalex.org/W2064701823","doi":"https://doi.org/10.1109/tc.2015.2395435","mag":"2064701823"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2015.2395435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2015.2395435","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-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/A5016864052","display_name":"Jaekyu Lee","orcid":"https://orcid.org/0000-0002-0574-5381"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jaekyu Lee","raw_affiliation_strings":["Intel Corporation, Hillsboro, OR","Intel Corporation, Hillsboro, OR#TAB#"],"affiliations":[{"raw_affiliation_string":"Intel Corporation, Hillsboro, OR","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Corporation, Hillsboro, OR#TAB#","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037812225","display_name":"Dong Hyuk Woo","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Hyuk Woo","raw_affiliation_strings":["Google, Inc., Mountain View, CA","Google Inc., Mountain View, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000822269","display_name":"Hyesoon Kim","orcid":"https://orcid.org/0000-0002-6061-7825"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyesoon Kim","raw_affiliation_strings":["School of Computer Science, Georgia Institute of Technology, Atlanta, GA"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology, Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066664814","display_name":"Mani Azimi","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mani Azimi","raw_affiliation_strings":["Platform Architecture Research team in the Microprocessor and Programming Research group, Intel Labs","Platform Architecture Research team in the Microprocessor and Programming Research group"],"affiliations":[{"raw_affiliation_string":"Platform Architecture Research team in the Microprocessor and Programming Research group, Intel Labs","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Platform Architecture Research team in the Microprocessor and Programming Research group","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016864052"],"corresponding_institution_ids":["https://openalex.org/I1343180700"],"apc_list":null,"apc_paid":null,"fwci":1.9379,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.85951158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"64","issue":"11","first_page":"3167","last_page":"3180"},"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":0.9986000061035156,"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":0.9970999956130981,"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":0.8821327090263367},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6738658547401428},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5975401997566223},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.5778243541717529},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.5664279460906982},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.5549745559692383},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.5047136545181274},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4835814833641052},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.4759621024131775},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.46302902698516846},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4520740509033203},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.44506973028182983},{"id":"https://openalex.org/keywords/cache-oblivious-algorithm","display_name":"Cache-oblivious algorithm","score":0.42818552255630493},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.366071492433548},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35595130920410156},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.29801732301712036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8821327090263367},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6738658547401428},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5975401997566223},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5778243541717529},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.5664279460906982},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.5549745559692383},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.5047136545181274},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4835814833641052},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.4759621024131775},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.46302902698516846},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4520740509033203},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.44506973028182983},{"id":"https://openalex.org/C59687516","wikidata":"https://www.wikidata.org/wiki/Q5015938","display_name":"Cache-oblivious algorithm","level":5,"score":0.42818552255630493},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.366071492433548},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35595130920410156},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.29801732301712036}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2015.2395435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2015.2395435","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8899999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2009387496","https://openalex.org/W2010133494","https://openalex.org/W2024122052","https://openalex.org/W2029577083","https://openalex.org/W2034256066","https://openalex.org/W2043083835","https://openalex.org/W2054206030","https://openalex.org/W2072194234","https://openalex.org/W2080592089","https://openalex.org/W2095258606","https://openalex.org/W2097336080","https://openalex.org/W2100011668","https://openalex.org/W2100901045","https://openalex.org/W2101251064","https://openalex.org/W2101308451","https://openalex.org/W2102683450","https://openalex.org/W2103397328","https://openalex.org/W2106617337","https://openalex.org/W2112052935","https://openalex.org/W2116986122","https://openalex.org/W2124350608","https://openalex.org/W2142033140","https://openalex.org/W2143773524","https://openalex.org/W2155119470","https://openalex.org/W2160996172","https://openalex.org/W2161402454","https://openalex.org/W2163947040","https://openalex.org/W2174102096","https://openalex.org/W4234542536","https://openalex.org/W4238816702","https://openalex.org/W4239853937","https://openalex.org/W4252854535","https://openalex.org/W4256712507","https://openalex.org/W6659083272","https://openalex.org/W6677635799"],"related_works":["https://openalex.org/W2546991807","https://openalex.org/W2098406302","https://openalex.org/W2538519144","https://openalex.org/W2121191383","https://openalex.org/W2076114130","https://openalex.org/W2734782074","https://openalex.org/W1584415117","https://openalex.org/W1505654810","https://openalex.org/W2109265242","https://openalex.org/W2608622083"],"abstract_inverted_index":{"As":[0],"various":[1],"graphics":[2,35,60],"processing":[3,36],"unit":[4],"architectures":[5],"are":[6],"deployed":[7],"across":[8],"broad":[9],"computing":[10,21,33],"spectrum":[11],"from":[12,57],"a":[13,19,116,129],"hand-held":[14],"or":[15,138],"embedded":[16],"device":[17],"to":[18,68,104],"high-performance":[20],"server,":[22],"OpenCL":[23,42,124],"becomes":[24],"the":[25,64,78,120,123,143,160,169,179],"de":[26],"facto":[27],"standard":[28],"programming":[29,61,97],"environment":[30],"for":[31,110],"general-purpose":[32],"on":[34],"units.":[37],"Unlike":[38],"its":[39,49],"CPU":[40],"counterpart,":[41],"has":[43],"several":[44],"distinct":[45],"features":[46],"such":[47,89],"as":[48,115],"disciplined":[50],"memory":[51,71,125],"model,":[52],"which":[53],"is":[54],"partially":[55],"inherited":[56],"conventional":[58],"3D":[59],"models.":[62],"On":[63],"other":[65],"hand,":[66],"due":[67],"ever":[69],"increasing":[70,86],"bandwidth":[72],"pressure":[73],"and":[74,127,172,187],"low":[75],"power":[76],"requirement,":[77],"capacity":[79],"of":[80,122,156,165,175],"on-chip":[81,108],"caches":[82,109],"in":[83,101,159,168,178],"GPUs":[84],"keeps":[85],"overtime.":[87],"Given":[88],"trends,":[90],"we":[91,94,118,151],"believe":[92],"that":[93,150],"have":[95],"interesting":[96],"model/architecture":[98],"co-optimization":[99],"opportunities,":[100],"particular,":[102],"how":[103],"energy-efficiently":[105],"utilize":[106],"large":[107],"GPUs.":[111],"In":[112],"this":[113],"paper,":[114],"showcase,":[117],"study":[119],"characteristics":[121],"model":[126],"propose":[128],"technique":[130],"called":[131],"GPU":[132],"Region-aware":[133],"energy-efficient":[134],"non-inclusive":[135],"cache":[136,140,181],"hierarchy,":[137],"GREEN":[139,144],"hierarchy.":[141],"With":[142],"cache,":[145,162,171],"our":[146],"simulation":[147],"results":[148],"show":[149],"can":[152],"save":[153],"56":[154],"percent":[155,164,174],"dynamic":[157,166],"energy":[158,167,177],"L1":[161],"39":[163],"L2":[170,180],"50":[173],"leakage":[176],"with":[182],"practically":[183],"no":[184],"performance":[185],"degradation":[186],"off-chip":[188],"access":[189],"increases.":[190]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}