{"id":"https://openalex.org/W4386078132","doi":"https://doi.org/10.1109/les.2023.3307622","title":"Triple-A: Early Operand Collector Allocation for Maximizing GPU Register Bank Utilization","display_name":"Triple-A: Early Operand Collector Allocation for Maximizing GPU Register Bank Utilization","publication_year":2023,"publication_date":"2023-08-22","ids":{"openalex":"https://openalex.org/W4386078132","doi":"https://doi.org/10.1109/les.2023.3307622"},"language":"en","primary_location":{"id":"doi:10.1109/les.2023.3307622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/les.2023.3307622","pdf_url":null,"source":{"id":"https://openalex.org/S22443479","display_name":"IEEE Embedded Systems Letters","issn_l":"1943-0663","issn":["1943-0663","1943-0671"],"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 Embedded Systems 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/A5012141172","display_name":"Ipoom Jeong","orcid":"https://orcid.org/0000-0001-7513-2858"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ipoom Jeong","raw_affiliation_strings":["University of Illinois Urbana&#x2013;Champaign, Champaign, IL, USA"],"raw_orcid":"https://orcid.org/0000-0001-7513-2858","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana&#x2013;Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108904859","display_name":"Eunbi Jeong","orcid":"https://orcid.org/0009-0002-8583-3695"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eunbi Jeong","raw_affiliation_strings":["Department of Computer Science and Engineering, Ewha Womans University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0002-8583-3695","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ewha Womans University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037648751","display_name":"Nam Sung Kim","orcid":"https://orcid.org/0000-0002-0442-5634"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nam Sung Kim","raw_affiliation_strings":["University of Illinois Urbana&#x2013;Champaign, Champaign, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-0442-5634","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana&#x2013;Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040253395","display_name":"Myung Kuk Yoon","orcid":"https://orcid.org/0000-0002-9332-0251"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myung Kuk Yoon","raw_affiliation_strings":["Department of Computer Science and Engineering, Ewha Womans University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-9332-0251","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ewha Womans University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I138925566"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10882924,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"2","first_page":"206","last_page":"209"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9965000152587891,"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/operand","display_name":"Operand","score":0.9556512832641602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.845031201839447},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.7674823999404907},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5644909739494324},{"id":"https://openalex.org/keywords/processor-register","display_name":"Processor register","score":0.5630492568016052},{"id":"https://openalex.org/keywords/register-allocation","display_name":"Register allocation","score":0.5471954345703125},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3894154727458954},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.16450059413909912},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.11657547950744629},{"id":"https://openalex.org/keywords/memory-address","display_name":"Memory address","score":0.08179935812950134}],"concepts":[{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.9556512832641602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.845031201839447},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.7674823999404907},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5644909739494324},{"id":"https://openalex.org/C2871975","wikidata":"https://www.wikidata.org/wiki/Q187466","display_name":"Processor register","level":4,"score":0.5630492568016052},{"id":"https://openalex.org/C128916667","wikidata":"https://www.wikidata.org/wiki/Q1343660","display_name":"Register allocation","level":3,"score":0.5471954345703125},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3894154727458954},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.16450059413909912},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.11657547950744629},{"id":"https://openalex.org/C153247305","wikidata":"https://www.wikidata.org/wiki/Q835713","display_name":"Memory address","level":3,"score":0.08179935812950134},{"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:10.1109/les.2023.3307622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/les.2023.3307622","pdf_url":null,"source":{"id":"https://openalex.org/S22443479","display_name":"IEEE Embedded Systems Letters","issn_l":"1943-0663","issn":["1943-0663","1943-0671"],"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 Embedded Systems Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.9200000166893005,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G5929260102","display_name":null,"funder_award_id":"2021-0-02068","funder_id":"https://openalex.org/F4320322030","funder_display_name":"Ministry of Science, ICT and Future Planning"}],"funders":[{"id":"https://openalex.org/F4320322030","display_name":"Ministry of Science, ICT and Future Planning","ror":"https://ror.org/032e49973"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2010202670","https://openalex.org/W2080592089","https://openalex.org/W2090584832","https://openalex.org/W2128120785","https://openalex.org/W2920798074","https://openalex.org/W3100327344","https://openalex.org/W3102510044","https://openalex.org/W3206857466","https://openalex.org/W4225959196","https://openalex.org/W6760272376"],"related_works":["https://openalex.org/W2224192221","https://openalex.org/W1967889241","https://openalex.org/W2111377238","https://openalex.org/W2161297616","https://openalex.org/W3117494601","https://openalex.org/W4247209662","https://openalex.org/W2195435904","https://openalex.org/W2088203538","https://openalex.org/W2148662141","https://openalex.org/W2159389028"],"abstract_inverted_index":{"Recent":[0],"GPUs":[1],"provisioned":[2],"with":[3,102,139],"large":[4],"register":[5,14,29,112,117,159,173],"files":[6,15],"cannot":[7],"fully":[8],"utilize":[9],"the":[10,13,20,28,34,111,122,133,143,158,179],"bandwidth":[11],"between":[12],"and":[16,168],"execution":[17],"pipelines,":[18],"as":[19],"current":[21],"policy":[22],"for":[23],"allocating":[24,149],"operand":[25,48,64,99,107,150],"collectors":[26,151],"defers":[27],"file":[30,118,174],"accesses":[31],"until":[32],"all":[33],"source":[35,75],"operands":[36,76],"become":[37],"ready.":[38],"To":[39],"tackle":[40],"this":[41,43],"issue,":[42],"paper":[44],"introduces":[45],"a":[46,67,88,103,163],"new":[47],"collector":[49,65,100],"allocation":[50,135],"mechanism":[51],"called":[52],"Triple-A.":[53],"Triple-A":[54,60,115],"comprises":[55],"four":[56],"key":[57],"operations.":[58],"First,":[59],"proactively":[61],"allocates":[62],"an":[63,96,169],"to":[66,95,178],"warp":[68],"instruction":[69],"even":[70],"if":[71,121],"one":[72],"of":[73,83],"its":[74],"is":[77,125,136],"not":[78,126],"yet":[79],"ready,":[80],"taking":[81],"advantage":[82],"GPUs\u2019":[84],"in-order":[85],"execution.":[86],"Second,":[87],"computation":[89],"result":[90],"can":[91],"be":[92],"directly":[93],"forwarded":[94,123],"early":[97,134],"allocated":[98],"along":[101],"data":[104,124],"dependence,":[105],"reducing":[106],"loading":[108],"time":[109],"from":[110],"files.":[113],"Third,":[114],"bypasses":[116],"write":[119],"operations":[120],"consumed":[127],"by":[128,148],"any":[129],"other":[130],"instruction.":[131],"Lastly,":[132],"further":[137],"enhanced":[138],"latency-aware":[140],"optimization,":[141],"alleviating":[142],"potential":[144],"performance":[145,167],"degradation":[146],"caused":[147],"aggressively.":[152],"Together,":[153],"these":[154],"techniques":[155],"synergistically":[156],"improve":[157],"bank":[160],"utilization,":[161],"demonstrating":[162],"14.1%":[164],"improvement":[165],"in":[166,172],"11.8%":[170],"reduction":[171],"energy":[175],"consumption":[176],"compared":[177],"state-of-the-art":[180],"GPUs.":[181]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
