{"id":"https://openalex.org/W1989061323","doi":"https://doi.org/10.1145/2540708.2540717","title":"A locality-aware memory hierarchy for energy-efficient GPU architectures","display_name":"A locality-aware memory hierarchy for energy-efficient GPU architectures","publication_year":2013,"publication_date":"2013-12-07","ids":{"openalex":"https://openalex.org/W1989061323","doi":"https://doi.org/10.1145/2540708.2540717","mag":"1989061323"},"language":"en","primary_location":{"id":"doi:10.1145/2540708.2540717","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2540708.2540717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th Annual IEEE/ACM International Symposium on Microarchitecture","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/A5091648103","display_name":"Minsoo Rhu","orcid":"https://orcid.org/0000-0003-3303-8681"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Minsoo Rhu","raw_affiliation_strings":["University of Texas at Austin, Austin, Texas","Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, Texas 78712-1684"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, Texas","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, Texas 78712-1684","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076752182","display_name":"Michael B. Sullivan","orcid":"https://orcid.org/0000-0001-6537-2065"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Sullivan","raw_affiliation_strings":["University of Texas at Austin, Austin, Texas","Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, Texas 78712-1684"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, Texas","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, Texas 78712-1684","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003939279","display_name":"Jingwen Leng","orcid":"https://orcid.org/0000-0002-5660-5493"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingwen Leng","raw_affiliation_strings":["University of Texas at Austin, Austin, Texas","Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, Texas 78712-1684"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, Texas","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, Texas 78712-1684","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013680653","display_name":"Mattan Erez","orcid":"https://orcid.org/0000-0002-1567-4097"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mattan Erez","raw_affiliation_strings":["University of Texas at Austin, Austin, Texas","Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, Texas 78712-1684"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, Texas","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, Texas 78712-1684","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091648103"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":11.7344,"has_fulltext":false,"cited_by_count":116,"citation_normalized_percentile":{"value":0.98733959,"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":"86","last_page":"98"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11478","display_name":"Caching and Content Delivery","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8799223899841309},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6763466596603394},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.674248218536377},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.6697899699211121},{"id":"https://openalex.org/keywords/locality-of-reference","display_name":"Locality of reference","score":0.5760613083839417},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5027401447296143},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.48766839504241943},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.48631152510643005},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.4402036964893341},{"id":"https://openalex.org/keywords/uniform-memory-access","display_name":"Uniform memory access","score":0.41598576307296753},{"id":"https://openalex.org/keywords/interleaved-memory","display_name":"Interleaved memory","score":0.4157832860946655},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.3683515787124634},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3653647005558014},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.2811709940433502},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2790156900882721},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18440678715705872}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8799223899841309},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6763466596603394},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.674248218536377},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.6697899699211121},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.5760613083839417},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5027401447296143},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.48766839504241943},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.48631152510643005},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4402036964893341},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.41598576307296753},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.4157832860946655},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3683515787124634},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3653647005558014},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.2811709940433502},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2790156900882721},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18440678715705872},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2540708.2540717","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2540708.2540717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.648.4052","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.648.4052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://lph.ece.utexas.edu/merez/uploads/MattanErez/micro2013_lamar.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8999999761581421}],"awards":[{"id":"https://openalex.org/G7555909470","display_name":null,"funder_award_id":"954107","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/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1513547380","https://openalex.org/W1964108470","https://openalex.org/W1971997351","https://openalex.org/W1973538724","https://openalex.org/W1973961119","https://openalex.org/W1979527452","https://openalex.org/W1979866689","https://openalex.org/W1983235612","https://openalex.org/W1984271364","https://openalex.org/W1987405813","https://openalex.org/W1997162567","https://openalex.org/W2016481757","https://openalex.org/W2020572638","https://openalex.org/W2024122052","https://openalex.org/W2038932419","https://openalex.org/W2047060659","https://openalex.org/W2054882590","https://openalex.org/W2065132365","https://openalex.org/W2080592089","https://openalex.org/W2081533422","https://openalex.org/W2090584832","https://openalex.org/W2092406519","https://openalex.org/W2093043622","https://openalex.org/W2096661534","https://openalex.org/W2099084006","https://openalex.org/W2104751776","https://openalex.org/W2118231788","https://openalex.org/W2119296805","https://openalex.org/W2121386169","https://openalex.org/W2123845384","https://openalex.org/W2125979435","https://openalex.org/W2126540423","https://openalex.org/W2129513794","https://openalex.org/W2129817042","https://openalex.org/W2136385615","https://openalex.org/W2141302915","https://openalex.org/W2142444503","https://openalex.org/W2144764850","https://openalex.org/W2145866640","https://openalex.org/W2148443481","https://openalex.org/W2151917022","https://openalex.org/W2155568054","https://openalex.org/W2156403661","https://openalex.org/W2156831150","https://openalex.org/W2166621589","https://openalex.org/W2167680146","https://openalex.org/W2169855483","https://openalex.org/W2169880332","https://openalex.org/W3146509083","https://openalex.org/W4231459869","https://openalex.org/W4245880889","https://openalex.org/W6677946485","https://openalex.org/W6680359875"],"related_works":["https://openalex.org/W2606565524","https://openalex.org/W2115061140","https://openalex.org/W4311294724","https://openalex.org/W1975901677","https://openalex.org/W1975444747","https://openalex.org/W2170960248","https://openalex.org/W2126827366","https://openalex.org/W1655459528","https://openalex.org/W2564569739","https://openalex.org/W2173219398"],"abstract_inverted_index":{"As":[0,149],"GPU's":[1],"compute":[2],"capabilities":[3],"grow,":[4],"their":[5,65],"memory":[6,14,18,36,52,70,88,124,153,160],"hierarchy":[7,89,154],"increasingly":[8],"becomes":[9],"a":[10,40,86,163],"bottleneck.":[11],"Current":[12],"GPU":[13,45,80,156],"hierarchies":[15,67],"use":[16],"coarse-grained":[17,35,103],"accesses":[19,104],"to":[20,116],"exploit":[21],"spatial":[22,147],"locality,":[23],"maximize":[24],"peak":[25],"bandwidth,":[26],"simplify":[27],"control,":[28],"and":[29,51,61,84,107,126,159],"reduce":[30],"cache":[31,66],"meta-data":[32],"storage.":[33],"These":[34],"accesses,":[37],"however,":[38],"are":[39,128],"poor":[41],"match":[42],"for":[43,74,90,105,130,143,162],"emerging":[44],"applications":[46],"with":[47,132,145],"irregular":[48,79],"control":[49,138],"flow":[50],"access":[53,115,122],"patterns.":[54],"Meanwhile,":[55],"the":[56,62,76,100,121],"massive":[57],"multi-threading":[58],"of":[59,64,78,102,166],"GPUs":[60],"simplicity":[63],"make":[68],"CPU-specific":[69],"system":[71],"enhancements":[72],"ineffective":[73],"improving":[75],"performance":[77],"applications.":[81,167],"We":[82],"design":[83,98],"evaluate":[85],"locality-aware":[87,152],"throughput":[91,161],"processors,":[92],"such":[93],"as":[94],"GPUs.":[95],"Our":[96],"proposed":[97],"retains":[99],"advantages":[101],"spatially":[106],"temporally":[108],"local":[109],"programs":[110],"while":[111],"permitting":[112],"selective":[113],"fine-grained":[114],"memory.":[117],"By":[118],"adaptively":[119],"adjusting":[120],"granularity,":[123],"bandwidth":[125],"energy":[127],"reduced":[129],"data":[131,144],"low":[133],"spatial/temporal":[134],"locality":[135],"without":[136],"wasting":[137],"overheads":[139],"or":[140],"prefetching":[141],"potential":[142],"high":[146],"locality.":[148],"such,":[150],"our":[151],"improves":[155],"performance,":[157],"energy-efficiency,":[158],"large":[164],"range":[165]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":19},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}