{"id":"https://openalex.org/W4380881150","doi":"https://doi.org/10.1145/3579371.3589039","title":"R2D2: Removing ReDunDancy Utilizing Linearity of Address Generation in GPUs","display_name":"R2D2: Removing ReDunDancy Utilizing Linearity of Address Generation in GPUs","publication_year":2023,"publication_date":"2023-06-16","ids":{"openalex":"https://openalex.org/W4380881150","doi":"https://doi.org/10.1145/3579371.3589039"},"language":"en","primary_location":{"id":"doi:10.1145/3579371.3589039","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579371.3589039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 50th Annual International Symposium on Computer Architecture","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/A5103111147","display_name":"Dongho Ha","orcid":"https://orcid.org/0009-0005-4090-4025"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Dongho Ha","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0005-4090-4025","affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015526090","display_name":"Yunho Oh","orcid":"https://orcid.org/0000-0001-6442-3705"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yunho Oh","raw_affiliation_strings":["Korea University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-6442-3705","affiliations":[{"raw_affiliation_string":"Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017913155","display_name":"Won Woo Ro","orcid":"https://orcid.org/0000-0001-5390-6445"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Won Woo Ro","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-5390-6445","affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103111147"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":2.6932,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.89850655,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"14"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.996999979019165,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8816430568695068},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7453125715255737},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6645753979682922},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6172494888305664},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5096383094787598},{"id":"https://openalex.org/keywords/context-switch","display_name":"Context switch","score":0.46839213371276855},{"id":"https://openalex.org/keywords/memory-address","display_name":"Memory address","score":0.4155641496181488},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.411490261554718},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3313060700893402},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2447672188282013},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.22871321439743042},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18062278628349304}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8816430568695068},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7453125715255737},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6645753979682922},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6172494888305664},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5096383094787598},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.46839213371276855},{"id":"https://openalex.org/C153247305","wikidata":"https://www.wikidata.org/wiki/Q835713","display_name":"Memory address","level":3,"score":0.4155641496181488},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.411490261554718},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3313060700893402},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2447672188282013},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.22871321439743042},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18062278628349304},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3579371.3589039","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579371.3589039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 50th Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.9200000166893005}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1964471912","https://openalex.org/W1971421905","https://openalex.org/W1975274780","https://openalex.org/W1979527452","https://openalex.org/W1991518265","https://openalex.org/W2010452422","https://openalex.org/W2029926205","https://openalex.org/W2042411977","https://openalex.org/W2076090418","https://openalex.org/W2080592089","https://openalex.org/W2093043622","https://openalex.org/W2095667776","https://openalex.org/W2095872092","https://openalex.org/W2103246828","https://openalex.org/W2107922025","https://openalex.org/W2118826546","https://openalex.org/W2130653499","https://openalex.org/W2134427337","https://openalex.org/W2138761132","https://openalex.org/W2143798346","https://openalex.org/W2144334298","https://openalex.org/W2146451305","https://openalex.org/W2150073849","https://openalex.org/W2153963140","https://openalex.org/W2155503253","https://openalex.org/W2166908913","https://openalex.org/W2235785597","https://openalex.org/W2273440736","https://openalex.org/W2325153866","https://openalex.org/W2470243357","https://openalex.org/W2486564422","https://openalex.org/W2538356068","https://openalex.org/W2604269348","https://openalex.org/W2613066110","https://openalex.org/W2626935846","https://openalex.org/W2787181861","https://openalex.org/W2794887017","https://openalex.org/W2795002137","https://openalex.org/W2884590322","https://openalex.org/W2905475640","https://openalex.org/W2950656546","https://openalex.org/W3012406028","https://openalex.org/W3041406277","https://openalex.org/W3091933744","https://openalex.org/W3102510044","https://openalex.org/W4211127289","https://openalex.org/W4233285768","https://openalex.org/W4253750843","https://openalex.org/W4255681033"],"related_works":["https://openalex.org/W2101387113","https://openalex.org/W2168921806","https://openalex.org/W4206718021","https://openalex.org/W2047885859","https://openalex.org/W2491664907","https://openalex.org/W1487451557","https://openalex.org/W91723605","https://openalex.org/W2057513248","https://openalex.org/W3023369457","https://openalex.org/W1680705574"],"abstract_inverted_index":{"A":[0],"generally":[1],"used":[2],"GPU":[3,40,86],"programming":[4],"methodology":[5],"is":[6,146],"that":[7,28],"adjacent":[8],"threads":[9,59,136],"access":[10],"data":[11,63],"in":[12,111],"neighbor":[13],"or":[14],"specific-stride":[15],"memory":[16,30,54,74,113,126,151],"addresses":[17,31,114,127,152],"and":[18,48,115,131,172],"perform":[19],"computations":[20],"with":[21,128,153],"the":[22,29,53,58,73,102,112,125,135,138,141],"fetched":[23],"data.":[24],"This":[25],"paper":[26],"demonstrates":[27],"often":[32],"exhibit":[33,79],"a":[34,67,80,85,98],"simple":[35,81],"linear":[36,109],"value":[37],"pattern":[38],"across":[39],"threads,":[41],"as":[42],"each":[43,144],"thread":[44,145],"uses":[45],"built-in":[46],"variables":[47],"constant":[49],"values":[50],"to":[51,71,148],"compute":[52,60,149],"addresses.":[55],"However,":[56],"since":[57],"their":[61],"context":[62],"individually,":[64],"GPUs":[65],"incur":[66],"heavy":[68],"instruction":[69,104,166],"overhead":[70],"calculate":[72],"addresses,":[75],"even":[76],"though":[77],"they":[78],"pattern.":[82],"We":[83],"propose":[84],"architecture":[87],"called":[88],"Removing":[89],"ReDunDancy":[90],"Utilizing":[91],"Linearity":[92],"of":[93,101,124],"Address":[94],"Generation":[95],"(R2D2),":[96],"reducing":[97],"large":[99],"amount":[100],"dynamic":[103,155,165],"count":[105],"by":[106,168,176],"detecting":[107],"such":[108],"patterns":[110],"exploiting":[116],"them":[117,133],"for":[118],"kernel":[119],"computations.":[120],"R2D2":[121,163],"detects":[122],"linearities":[123],"software":[129],"support":[130],"pre-computes":[132],"before":[134],"execute":[137],"instructions.":[139],"With":[140],"proposed":[142],"scheme,":[143],"able":[147],"its":[150],"fewer":[154],"instructions":[156],"than":[157],"conventional":[158],"GPUs.":[159],"In":[160],"our":[161],"evaluation,":[162],"achieves":[164],"reduction":[167,175],"28%,":[169],"1.25x":[170],"speedup,":[171],"energy":[173],"consumption":[174],"17%":[177],"over":[178],"baseline":[179],"GPU.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}