{"id":"https://openalex.org/W3117272675","doi":"https://doi.org/10.1109/hpec43674.2020.9286215","title":"Packing Narrow-Width Operands to Improve Energy Efficiency of General-Purpose GPU Computing","display_name":"Packing Narrow-Width Operands to Improve Energy Efficiency of General-Purpose GPU Computing","publication_year":2020,"publication_date":"2020-09-22","ids":{"openalex":"https://openalex.org/W3117272675","doi":"https://doi.org/10.1109/hpec43674.2020.9286215","mag":"3117272675"},"language":"en","primary_location":{"id":"doi:10.1109/hpec43674.2020.9286215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5110667048","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-0246-164X"},"institutions":[{"id":"https://openalex.org/I184840846","display_name":"Virginia Commonwealth University","ror":"https://ror.org/02nkdxk79","country_code":"US","type":"education","lineage":["https://openalex.org/I184840846"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Virginia Commonwealth University, Richmond, VA"],"affiliations":[{"raw_affiliation_string":"Virginia Commonwealth University, Richmond, VA","institution_ids":["https://openalex.org/I184840846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100441493","display_name":"Wei Zhang","orcid":"https://orcid.org/0009-0007-7082-1014"},"institutions":[{"id":"https://openalex.org/I142740786","display_name":"University of Louisville","ror":"https://ror.org/01ckdn478","country_code":"US","type":"education","lineage":["https://openalex.org/I142740786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["University of Louisville, Louisville, KY"],"affiliations":[{"raw_affiliation_string":"University of Louisville, Louisville, KY","institution_ids":["https://openalex.org/I142740786"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110667048"],"corresponding_institution_ids":["https://openalex.org/I184840846"],"apc_list":null,"apc_paid":null,"fwci":0.4621,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62703252,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"51","issue":null,"first_page":"1","last_page":"7"},"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":0.9994000196456909,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9988999962806702,"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":0.8410024642944336},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.8356705904006958},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.75432288646698},{"id":"https://openalex.org/keywords/operand","display_name":"Operand","score":0.729572057723999},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6281563639640808},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5795646905899048},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5292049646377563},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4960421025753021},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.48362675309181213},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.23536214232444763},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22843152284622192},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.10843890905380249}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8410024642944336},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.8356705904006958},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.75432288646698},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.729572057723999},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6281563639640808},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5795646905899048},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5292049646377563},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4960421025753021},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.48362675309181213},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.23536214232444763},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22843152284622192},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.10843890905380249},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec43674.2020.9286215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1516536978","https://openalex.org/W1979527452","https://openalex.org/W1991518265","https://openalex.org/W2019427687","https://openalex.org/W2026186397","https://openalex.org/W2033597569","https://openalex.org/W2043083835","https://openalex.org/W2059301531","https://openalex.org/W2072768743","https://openalex.org/W2080592089","https://openalex.org/W2093043622","https://openalex.org/W2104761433","https://openalex.org/W2115157620","https://openalex.org/W2119306965","https://openalex.org/W2128022558","https://openalex.org/W2128120785","https://openalex.org/W2133834148","https://openalex.org/W2138777150","https://openalex.org/W2150073849","https://openalex.org/W2155503253","https://openalex.org/W2164474450","https://openalex.org/W2232645663","https://openalex.org/W2238992335","https://openalex.org/W2534060050","https://openalex.org/W2755395451","https://openalex.org/W2805642345","https://openalex.org/W2902700387","https://openalex.org/W3006997840","https://openalex.org/W3148444620","https://openalex.org/W4234833047","https://openalex.org/W4241441655","https://openalex.org/W4250945092","https://openalex.org/W6677922359"],"related_works":["https://openalex.org/W2105325426","https://openalex.org/W2245451942","https://openalex.org/W2088203538","https://openalex.org/W2116521658","https://openalex.org/W1580009706","https://openalex.org/W2100504584","https://openalex.org/W2763549657","https://openalex.org/W2123413169","https://openalex.org/W4246431097","https://openalex.org/W4248763955"],"abstract_inverted_index":{"In":[0,17,174],"this":[1],"paper,":[2],"we":[3],"study":[4],"the":[5,22,49,58,61,65,74,110,128,135,156,163],"use":[6,21],"of":[7,46,51,60,76,112,145],"OWAR,":[8],"an_Qperand-Width-A_ware":[9],"Register":[10],"packing":[11,59],"mechanism":[12],"for":[13,39,102,120],"GPU":[14,23,147],"energy":[15,44,67,137,166],"saving.":[16],"order":[18],"to":[19,33,57,86,155,168],"efficiently":[20],"register":[24,37,52,81,113],"file":[25],"(RF),":[26],"OWAR":[27,83,141,160,176],"employs":[28],"a":[29,143],"power":[30],"gating":[31],"method":[32],"shut":[34],"down":[35],"unused":[36],"sub-arrays":[38],"reducing":[40],"dynamic":[41,66],"and":[42,125,170,182],"leakage":[43],"consumption":[45],"RF.":[47],"As":[48],"number":[50],"accesses":[53],"is":[54,69],"reduced":[55],"due":[56],"narrow":[62],"width":[63],"operands,":[64],"dissipation":[68],"further":[70],"decreased.":[71],"Finally,":[72],"with":[73],"help":[75],"RF":[77],"usage":[78],"optimized":[79],"by":[80],"packing,":[82],"allows":[84],"GPUs":[85],"support":[87],"more":[88,122],"TLP":[89,117],"(Thread":[90],"Level":[91],"Parallelism)":[92],"through":[93],"assigning":[94],"additional":[95],"thread":[96],"blocks":[97],"on":[98,172,184],"SMs":[99],"(Streaming":[100],"Multiprocessors)":[101],"GPGPU":[103],"(General-Purpose":[104],"GPU)":[105],"applications":[106],"that":[107,153],"suffer":[108],"from":[109],"deficiency":[111],"resources.":[114],"The":[115,149],"extra":[116],"opens":[118],"opportunities":[119],"hiding":[121],"memory":[123],"latencies":[124],"thus":[126],"reduce":[127,162],"overall":[129,136],"execution":[130],"time,":[131],"which":[132],"can":[133,161],"lower":[134],"consumption.":[138],"We":[139],"evaluate":[140],"using":[142],"set":[144],"representative":[146],"benchmarks.":[148],"experimental":[150],"results":[151],"show":[152],"compared":[154],"baseline":[157],"without":[158],"optimization,":[159],"GPGPU's":[164],"total":[165],"up":[167],"29.6%":[169],"9.5%":[171],"average.":[173,185],"addition,":[175],"achieves":[177],"performance":[178],"improvement":[179],"upto":[180],"1.97X":[181],"1.18X":[183]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}