{"id":"https://openalex.org/W3091795552","doi":"https://doi.org/10.1109/dac18072.2020.9218700","title":"A History-Based Auto-Tuning Framework for Fast and High-Performance DNN Design on GPU","display_name":"A History-Based Auto-Tuning Framework for Fast and High-Performance DNN Design on GPU","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3091795552","doi":"https://doi.org/10.1109/dac18072.2020.9218700","mag":"3091795552"},"language":"en","primary_location":{"id":"doi:10.1109/dac18072.2020.9218700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18072.2020.9218700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5087006435","display_name":"Jiandong Mu","orcid":"https://orcid.org/0000-0002-0023-841X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiandong Mu","raw_affiliation_strings":["Hong Kong University of Science and Technology (HKUST), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (HKUST), China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100707460","display_name":"Mengdi Wang","orcid":"https://orcid.org/0000-0002-2101-9507"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengdi Wang","raw_affiliation_strings":["Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103218411","display_name":"Lanbo Li","orcid":"https://orcid.org/0000-0001-6422-2823"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanbo Li","raw_affiliation_strings":["Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695453","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0002-3365-4989"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yang","raw_affiliation_strings":["Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636012","display_name":"Wei Lin","orcid":"https://orcid.org/0000-0002-3003-0150"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Lin","raw_affiliation_strings":["Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100441532","display_name":"Wei Zhang","orcid":"https://orcid.org/0009-0006-2358-299X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Hong Kong University of Science and Technology (HKUST), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (HKUST), China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9397,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.82975225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.994700014591217,"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/T12676","display_name":"Machine Learning and ELM","score":0.9940000176429749,"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/tuner","display_name":"Tuner","score":0.9447561502456665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7833964228630066},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5856920480728149},{"id":"https://openalex.org/keywords/genetic-algorithm","display_name":"Genetic algorithm","score":0.49875760078430176},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.49237334728240967},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.46392735838890076},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.44234925508499146},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41590559482574463},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.37918126583099365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3227396309375763},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2822023630142212},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21047264337539673},{"id":"https://openalex.org/keywords/radio-frequency","display_name":"Radio frequency","score":0.1466166079044342},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10677239298820496},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09887591004371643}],"concepts":[{"id":"https://openalex.org/C9819579","wikidata":"https://www.wikidata.org/wiki/Q1544018","display_name":"Tuner","level":3,"score":0.9447561502456665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7833964228630066},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5856920480728149},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.49875760078430176},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.49237334728240967},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.46392735838890076},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.44234925508499146},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41590559482574463},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.37918126583099365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3227396309375763},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2822023630142212},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21047264337539673},{"id":"https://openalex.org/C74064498","wikidata":"https://www.wikidata.org/wiki/Q3396184","display_name":"Radio frequency","level":2,"score":0.1466166079044342},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10677239298820496},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09887591004371643}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/dac18072.2020.9218700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18072.2020.9218700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.ust.hk:1783.1-106208","is_oa":false,"landing_page_url":"http://www.scopus.com/record/display.url?eid=2-s2.0-85093936880&origin=inward","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2134645526","https://openalex.org/W2165960883","https://openalex.org/W2194775991","https://openalex.org/W2295598076","https://openalex.org/W2510697685","https://openalex.org/W2617031569","https://openalex.org/W2736230459","https://openalex.org/W2804032941","https://openalex.org/W2886851211","https://openalex.org/W2889647155","https://openalex.org/W2907468472","https://openalex.org/W2947983473","https://openalex.org/W2951810231","https://openalex.org/W2962711501","https://openalex.org/W3102476541","https://openalex.org/W4288346477","https://openalex.org/W6637373629","https://openalex.org/W6751349269","https://openalex.org/W6754777574","https://openalex.org/W6758118383","https://openalex.org/W6763062957"],"related_works":["https://openalex.org/W4313341326","https://openalex.org/W4282568311","https://openalex.org/W4313484792","https://openalex.org/W2951473296","https://openalex.org/W2883928845","https://openalex.org/W4288420200","https://openalex.org/W4285346947","https://openalex.org/W4365793791","https://openalex.org/W3145095675","https://openalex.org/W3134072570"],"abstract_inverted_index":{"While":[0],"Deep":[1],"Neural":[2],"Networks":[3],"(DNNs)":[4],"are":[5],"becoming":[6],"increasingly":[7],"popular,":[8],"there":[9],"is":[10,34],"a":[11,90,98],"growing":[12],"trend":[13],"to":[14,26,36,44,53,74,102],"accelerate":[15],"the":[16,38,45,50,76,82,85,104,112,129,138,145],"DNN":[17,105],"applications":[18],"on":[19,108],"hardware":[20],"platforms":[21,42],"like":[22],"GPUs,":[23],"FPGAs,":[24],"etc.,":[25],"gain":[27],"higher":[28],"performance":[29,39,127],"and":[30,49,66,137,150,156],"efficiency.":[31],"However,":[32],"it":[33],"time-consuming":[35],"tune":[37],"for":[40],"such":[41,62,132],"due":[43],"large":[46],"design":[47,56,77,107],"space":[48,78],"expensive":[51],"cost":[52],"evaluate":[54],"each":[55],"point.":[57],"Although":[58],"many":[59],"tuning":[60,113],"algorithms,":[61],"as":[63,133],"XGBoost":[64,154],"tuner":[65,155,158],"genetic":[67],"algorithm":[68],"(GA)":[69],"tuner,":[70],"have":[71],"been":[72],"proposed":[73],"guide":[75],"exploring":[79],"process":[80],"in":[81,116,159],"previous":[83],"work,":[84,95,131],"timing":[86],"issue":[87],"still":[88],"remains":[89],"critical":[91],"problem.":[92],"In":[93],"this":[94],"we":[96,123],"propose":[97],"novel":[99],"auto-tuning":[100,134],"framework":[101,135],"optimize":[103],"operator":[106],"GPU":[109],"by":[110,148],"leveraging":[111],"history":[114],"efficiently":[115],"different":[117],"scenarios.":[118],"Our":[119],"experiments":[120],"show":[121],"that":[122],"can":[124],"achieve":[125],"superior":[126],"than":[128],"state-of-the-art":[130],"TVM":[136],"handcraft":[139],"optimized":[140],"library":[141],"cuDNN,":[142],"while":[143],"reducing":[144],"searching":[146],"time":[147],"8.96x":[149],"4.58x":[151],"comparing":[152],"with":[153],"GA":[157],"TVM.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}