{"id":"https://openalex.org/W2999509507","doi":"https://doi.org/10.1109/lca.2019.2959298","title":"Locality-Aware GPU Register File","display_name":"Locality-Aware GPU Register File","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2999509507","doi":"https://doi.org/10.1109/lca.2019.2959298","mag":"2999509507"},"language":"en","primary_location":{"id":"doi:10.1109/lca.2019.2959298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2019.2959298","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"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 Computer Architecture Letters","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/A5081531196","display_name":"Hyeran Jeon","orcid":"https://orcid.org/0000-0002-1767-8198"},"institutions":[{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyeran Jeon","raw_affiliation_strings":["San Jose State University, San Jose, USA"],"raw_orcid":"https://orcid.org/0000-0002-1767-8198","affiliations":[{"raw_affiliation_string":"San Jose State University, San Jose, USA","institution_ids":["https://openalex.org/I51504820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046230478","display_name":"Hodjat Asghari Esfeden","orcid":"https://orcid.org/0000-0002-7200-6757"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hodjat Asghari Esfeden","raw_affiliation_strings":["University of California Riverside, Riverside, USA"],"raw_orcid":"https://orcid.org/0000-0002-7200-6757","affiliations":[{"raw_affiliation_string":"University of California Riverside, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059614371","display_name":"Nael Abu\u2010Ghazaleh","orcid":"https://orcid.org/0000-0002-9485-5370"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nael B. Abu-Ghazaleh","raw_affiliation_strings":["University of California Riverside, Riverside, USA"],"raw_orcid":"https://orcid.org/0000-0002-9485-5370","affiliations":[{"raw_affiliation_string":"University of California Riverside, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000712719","display_name":"Daniel Wong","orcid":"https://orcid.org/0000-0002-5376-7868"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Wong","raw_affiliation_strings":["University of California Riverside, Riverside, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Riverside, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064233034","display_name":"Sindhuja Gopalakrishnan Elango","orcid":null},"institutions":[{"id":"https://openalex.org/I4210088951","display_name":"Synopsys (United States)","ror":"https://ror.org/013by2m91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210088951"]},{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sindhuja Elango","raw_affiliation_strings":["San Jose State University","Synopsis Inc., Mountain View, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"San Jose State University","institution_ids":["https://openalex.org/I51504820"]},{"raw_affiliation_string":"Synopsis Inc., Mountain View, USA","institution_ids":["https://openalex.org/I4210088951"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7276,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.84945556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"18","issue":"2","first_page":"153","last_page":"156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9965999722480774,"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":0.9062622785568237},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.8699208498001099},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6813250184059143},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6030786037445068},{"id":"https://openalex.org/keywords/processor-register","display_name":"Processor register","score":0.5430504679679871},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5426040887832642},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4634961783885956},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4203700125217438},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.42011743783950806},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3993499279022217},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.3083627223968506},{"id":"https://openalex.org/keywords/memory-address","display_name":"Memory address","score":0.1856977343559265},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.18395668268203735}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9062622785568237},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.8699208498001099},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6813250184059143},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6030786037445068},{"id":"https://openalex.org/C2871975","wikidata":"https://www.wikidata.org/wiki/Q187466","display_name":"Processor register","level":4,"score":0.5430504679679871},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5426040887832642},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4634961783885956},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4203700125217438},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.42011743783950806},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3993499279022217},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.3083627223968506},{"id":"https://openalex.org/C153247305","wikidata":"https://www.wikidata.org/wiki/Q835713","display_name":"Memory address","level":3,"score":0.1856977343559265},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.18395668268203735},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lca.2019.2959298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2019.2959298","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"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 Computer Architecture Letters","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":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1667652561","https://openalex.org/W2238992335","https://openalex.org/W2285660444","https://openalex.org/W2442974303","https://openalex.org/W2795002137","https://openalex.org/W2886858179","https://openalex.org/W2887760990","https://openalex.org/W2904283553","https://openalex.org/W2905475640","https://openalex.org/W2937249639","https://openalex.org/W4302296459","https://openalex.org/W6637151318"],"related_works":["https://openalex.org/W2224192221","https://openalex.org/W2356166161","https://openalex.org/W2009783759","https://openalex.org/W1971263764","https://openalex.org/W1521414776","https://openalex.org/W2545358510","https://openalex.org/W3005928625","https://openalex.org/W74994880","https://openalex.org/W2139539906","https://openalex.org/W2157149066"],"abstract_inverted_index":{"In":[0,17,31],"many":[1],"emerging":[2],"applications":[3],"such":[4],"as":[5,97,99],"deep":[6,171],"learning,":[7],"large":[8],"data":[9,20,43,48,63,71,78,92,117,130],"set":[10],"is":[11],"essential":[12],"to":[13,115,121,193],"generate":[14],"reliable":[15],"solutions.":[16],"these":[18],"big":[19,47,70],"workloads,":[21],"memory":[22,85,143],"latency":[23],"and":[24,73,88,164,174,188],"bandwidth":[25],"are":[26],"the":[27,69,90,122,129,132,142,149,178],"main":[28],"performance":[29,165],"bottlenecks.":[30],"this":[32],"article,":[33],"we":[34],"propose":[35],"a":[36],"locality-aware":[37,180],"GPU":[38,181],"register":[39,106,133,150,182,190],"file":[40,107,134,151,183],"that":[41,177],"enables":[42,113],"sharing":[44,64,138],"for":[45,158,162],"memory-intensive":[46],"workloads":[49,72,173],"on":[50,54,169],"GPUs":[51],"without":[52],"relying":[53],"small":[55,100],"on-chip":[56],"memories.":[57],"We":[58],"exploit":[59],"two":[60,170],"types":[61],"of":[62,83],"patterns":[65],"commonly":[66],"found":[67],"from":[68,128],"have":[74],"warps":[75,114],"opportunistically":[76],"share":[77,116],"in":[79,94,131],"physical":[80,124],"registers":[81,96,125,155],"instead":[82],"issuing":[84],"loads":[86],"separately":[87],"storing":[89],"same":[91,123],"redundantly":[93],"their":[95],"well":[98],"shared":[101],"memory.":[102],"With":[103],"an":[104],"extended":[105],"mapping":[108,120],"mechanism,":[109],"our":[110],"proposed":[111,137,179],"design":[112],"by":[118],"simply":[119],"or":[126],"reconstructing":[127],"already.":[135],"The":[136,153],"not":[139],"only":[140],"reduces":[141],"transactions":[144],"but":[145],"also":[146],"further":[147],"decreases":[148],"usage.":[152],"spared":[154],"make":[156],"rooms":[157],"applying":[159],"orthogonal":[160],"optimizations":[161],"energy":[163],"improvement.":[166],"Our":[167],"evaluation":[168],"learning":[172],"matrixMul":[175],"show":[176],"achieves":[184],"over":[185],"2\u00d7":[186],"speedup":[187],"saves":[189],"space":[191],"up":[192],"57":[194],"percent.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}