{"id":"https://openalex.org/W2767882261","doi":"https://doi.org/10.1145/3133218","title":"Architecture and Compiler Support for GPUs Using Energy-Efficient Affine Register Files","display_name":"Architecture and Compiler Support for GPUs Using Energy-Efficient Affine Register Files","publication_year":2017,"publication_date":"2017-11-07","ids":{"openalex":"https://openalex.org/W2767882261","doi":"https://doi.org/10.1145/3133218","mag":"2767882261"},"language":"en","primary_location":{"id":"doi:10.1145/3133218","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3133218","pdf_url":null,"source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","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/A5037552091","display_name":"Shao-Chung Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Shao-Chung Wang","raw_affiliation_strings":["National Tsing-Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing-Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087370372","display_name":"Li-Chen Kan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148979","display_name":"MediaTek (Taiwan)","ror":"https://ror.org/05g9jck81","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210148979"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li-Chen Kan","raw_affiliation_strings":["MediaTek Inc., Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"MediaTek Inc., Hsinchu, Taiwan","institution_ids":["https://openalex.org/I4210148979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034885231","display_name":"Chao-Lin Lee","orcid":"https://orcid.org/0000-0002-4619-3843"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chao-Lin Lee","raw_affiliation_strings":["National Tsing-Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing-Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041551416","display_name":"Yuan\u2010Shin Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuan-Shin Hwang","raw_affiliation_strings":["National Taiwan University of Science and Technology, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038803698","display_name":"Jenq\u2010Kuen Lee","orcid":"https://orcid.org/0000-0001-9919-6258"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jenq-Kuen Lee","raw_affiliation_strings":["National Tsing-Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing-Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037552091"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":1.5772,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.85141088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"23","issue":"2","first_page":"1","last_page":"25"},"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":0.9994999766349792,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8828086853027344},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.7512170672416687},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.6969020962715149},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.6818767786026001},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.667719841003418},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.659212589263916},{"id":"https://openalex.org/keywords/register-allocation","display_name":"Register allocation","score":0.5826236605644226},{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.5182761549949646},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35592028498649597},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.32923710346221924},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20398163795471191},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12434780597686768}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8828086853027344},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.7512170672416687},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.6969020962715149},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.6818767786026001},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.667719841003418},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.659212589263916},{"id":"https://openalex.org/C128916667","wikidata":"https://www.wikidata.org/wiki/Q1343660","display_name":"Register allocation","level":3,"score":0.5826236605644226},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.5182761549949646},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35592028498649597},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.32923710346221924},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20398163795471191},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12434780597686768},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3133218","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3133218","pdf_url":null,"source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.9100000262260437}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1483717008","https://openalex.org/W1485193134","https://openalex.org/W1979527452","https://openalex.org/W1980364632","https://openalex.org/W1984222112","https://openalex.org/W2000553861","https://openalex.org/W2022632182","https://openalex.org/W2023200270","https://openalex.org/W2026186397","https://openalex.org/W2033597569","https://openalex.org/W2034639175","https://openalex.org/W2042411977","https://openalex.org/W2043083835","https://openalex.org/W2059301531","https://openalex.org/W2080592089","https://openalex.org/W2093043622","https://openalex.org/W2096661534","https://openalex.org/W2118826546","https://openalex.org/W2138761132","https://openalex.org/W2143798346","https://openalex.org/W2150073849","https://openalex.org/W2153185479","https://openalex.org/W2153963140","https://openalex.org/W2170601541","https://openalex.org/W2260256017","https://openalex.org/W2295329047","https://openalex.org/W2417350949","https://openalex.org/W3138798301","https://openalex.org/W4242726609","https://openalex.org/W4246166885","https://openalex.org/W6697163827"],"related_works":["https://openalex.org/W2111377238","https://openalex.org/W1967889241","https://openalex.org/W2165125411","https://openalex.org/W3022691489","https://openalex.org/W3117494601","https://openalex.org/W2091058226","https://openalex.org/W2224192221","https://openalex.org/W2161297616","https://openalex.org/W4247209662","https://openalex.org/W2162270818"],"abstract_inverted_index":{"A":[0,200],"modern":[1],"GPU":[2,307],"can":[3,106,135],"simultaneously":[4],"process":[5],"thousands":[6],"of":[7,24,49,61,76,102,118,167,179,187,202,258,287,305,311],"hardware":[8],"threads.":[9],"These":[10],"threads":[11,85],"are":[12,38],"grouped":[13],"into":[14],"fixed-size":[15],"SIMD":[16,43,89],"batches":[17],"executing":[18],"the":[19,58,77,97,164,169,183,259,279,284,288,301,306],"same":[20,88],"instruction":[21],"on":[22,92],"vectors":[23,122,213,239],"data":[25],"in":[26,86,278],"a":[27,46,87,115,177,226],"lockstep":[28],"to":[29,41,73,161,181,196,208,234,240,255,261,293],"achieve":[30],"high":[31],"throughput":[32],"and":[33,56,95,100,141,171,185,191,211,214,222,237,243,263,270,291,295,298],"performance.":[34],"The":[35],"register":[36,62,151,228,245,289],"files":[37,63,290],"huge":[39],"due":[40,160],"each":[42,188],"group":[44,90],"accessing":[45],"dedicated":[47],"set":[48],"vector":[50,78,190],"registers":[51,79,119,180,273],"for":[52,154,217],"fast":[53],"context":[54],"switching,":[55],"consequently":[57],"power":[59],"consumption":[60,286,304],"has":[64,111,205,231],"become":[65],"an":[66,149,309],"important":[67],"issue.":[68],"One":[69],"proposed":[70],"solution":[71],"is":[72,157],"replace":[74],"some":[75],"by":[80,138,308],"scalar":[81,93,104,221,242,262,269],"registers,":[82],"as":[83],"different":[84],"operate":[91],"values":[94,105],"so":[96],"redundant":[98,165],"computations":[99,260],"accesses":[101],"these":[103],"be":[107,136],"eliminated.":[108],"However,":[109],"it":[110,162,299],"been":[112,206,232],"observed":[113],"that":[114,125,156,250],"significant":[116],"number":[117],"containing":[120],"affine":[121,150,172,189,194,198,212,223,238,244,264,272],"\u03c5":[123],"such":[124],"\u03c5[":[126],"i":[127,132],"]":[128],"=":[129],"b":[130,140],"+":[131],"\u00d7":[133],"s":[134,143],"represented":[137],"base":[139,184],"stride":[142,186],".":[144],"Therefore,":[145],"this":[146,251],"article":[147],"proposes":[148],"file":[152],"design":[153,175,252,281],"GPUs":[155],"energy":[158,285,303],"efficient":[159],"reducing":[163,283],"executions":[166],"both":[168],"uniform":[170],"vectors.":[173],"This":[174,276],"uses":[176],"pair":[178],"store":[182],"provides":[192],"specific":[193],"ALUs":[195,265,292],"execute":[197],"instructions.":[199],"method":[201],"compiler":[203],"analysis":[204],"developed":[207],"detect":[209],"scalars":[210,236],"annotate":[215],"instructions":[216],"facilitating":[218],"their":[219],"corresponding":[220],"computations.":[224],"Furthermore,":[225],"priority-based":[227],"allocation":[229],"scheme":[230],"implemented":[233],"assign":[235],"appropriate":[241],"files.":[246],"Experimental":[247],"results":[248],"show":[249],"was":[253],"able":[254],"dispatch":[256],"43.56%":[257],"when":[266],"using":[267],"eight":[268],"four":[271],"per":[274],"warp.":[275],"resulted":[277],"current":[280],"also":[282],"21.86%":[294],"26.54%,":[296],"respectively,":[297],"reduced":[300],"overall":[302],"average":[310],"5.18%.":[312]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
