{"id":"https://openalex.org/W4249294209","doi":"https://doi.org/10.1109/cgo.2019.8661168","title":"Accelerating GPU Computing at Runtime with Binary Optimization","display_name":"Accelerating GPU Computing at Runtime with Binary Optimization","publication_year":2019,"publication_date":"2019-02-01","ids":{"openalex":"https://openalex.org/W4249294209","doi":"https://doi.org/10.1109/cgo.2019.8661168"},"language":"en","primary_location":{"id":"doi:10.1109/cgo.2019.8661168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2019.8661168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","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/A5100607669","display_name":"Guangli Li","orcid":"https://orcid.org/0000-0002-9738-261X"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guangli Li","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349661","display_name":"Lei Liu","orcid":"https://orcid.org/0000-0003-4854-7382"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Liu","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053070701","display_name":"Xiaobing Feng","orcid":"https://orcid.org/0000-0003-2909-7750"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobing Feng","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100607669"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":0.2024,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57807808,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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/T12676","display_name":"Machine Learning and ELM","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8695712089538574},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7259458303451538},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.717380940914154},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5850874781608582},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5295836925506592},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5142097473144531},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5080323219299316},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.43495696783065796},{"id":"https://openalex.org/keywords/idle","display_name":"Idle","score":0.41284382343292236},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.333549439907074},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.23572087287902832},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21541941165924072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10337275266647339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8695712089538574},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7259458303451538},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.717380940914154},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5850874781608582},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5295836925506592},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5142097473144531},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5080323219299316},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.43495696783065796},{"id":"https://openalex.org/C16320812","wikidata":"https://www.wikidata.org/wiki/Q1812200","display_name":"Idle","level":2,"score":0.41284382343292236},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.333549439907074},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.23572087287902832},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21541941165924072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10337275266647339},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo.2019.8661168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2019.8661168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2112796928","https://openalex.org/W2155893237","https://openalex.org/W2194775991","https://openalex.org/W2595314725"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W2023572661","https://openalex.org/W4245975140","https://openalex.org/W2532592438","https://openalex.org/W1977763331","https://openalex.org/W2078166177","https://openalex.org/W3032652555","https://openalex.org/W4236348942"],"abstract_inverted_index":{"Nowadays,":[0],"many":[1],"applications":[2],"use":[3,14],"GPUs":[4],"(Graphics":[5],"Processing":[6],"Units)":[7],"to":[8,39,64,117,128],"achieve":[9],"high":[10,71],"performance.":[11],"When":[12],"we":[13,30,98],"GPU":[15,42,53,119],"servers,":[16],"the":[17,22,32,35,70,92,100,136],"idle":[18,36],"CPU":[19,37],"resource":[20,38],"of":[21,73,95,132],"servers":[23],"is":[24,62,115],"often":[25],"ignored.":[26],"In":[27],"this":[28],"paper,":[29],"explore":[31],"idea:":[33],"using":[34],"speed":[40],"up":[41],"programs.":[43],"We":[44],"design":[45],"a":[46],"dynamic":[47],"binary":[48,59,88,122,126],"optimization":[49,60,96,127],"framework":[50],"for":[51],"accelerating":[52],"computing":[54],"at":[55],"runtime.":[56],"A":[57],"template-based":[58],"method":[61,77],"proposed":[63],"optimize":[65],"kernels,":[66],"which":[67],"can":[68,140],"avoid":[69],"cost":[72],"kernel":[74],"compilation.":[75],"This":[76],"replaces":[78],"determined":[79],"variables":[80],"with":[81,103],"constant":[82],"values":[83],"and":[84],"generates":[85],"an":[86],"optimized":[87,104],"kernel.":[89],"Based":[90],"on":[91],"analysis":[93],"results":[94,111],"opportunities,":[97],"replace":[99],"original":[101],"kernels":[102,105],"during":[106],"program":[107],"execution.":[108],"The":[109],"experimental":[110],"show":[112],"that":[113],"it":[114],"feasible":[116],"accelerate":[118],"programs":[120],"via":[121],"optimization.":[123],"After":[124],"applying":[125],"five":[129],"convolution":[130],"layers":[131],"deep":[133],"neural":[134],"networks,":[135],"average":[137],"performance":[138],"improvement":[139],"reach":[141],"20%.":[142]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}