{"id":"https://openalex.org/W4318328313","doi":"https://doi.org/10.1145/3559009.3569674","title":"Effective Performance Modeling and Domain-Specific Compiler Optimization of CNNs for GPUs","display_name":"Effective Performance Modeling and Domain-Specific Compiler Optimization of CNNs for GPUs","publication_year":2022,"publication_date":"2022-10-08","ids":{"openalex":"https://openalex.org/W4318328313","doi":"https://doi.org/10.1145/3559009.3569674"},"language":"en","primary_location":{"id":"doi:10.1145/3559009.3569674","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3559009.3569674","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3559009.3569674","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3559009.3569674","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015151039","display_name":"Yufan Xu","orcid":"https://orcid.org/0000-0002-7787-6460"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yufan Xu","raw_affiliation_strings":["University of Utah"],"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016676096","display_name":"Qiwei Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiwei Yuan","raw_affiliation_strings":["University of Utah"],"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085062510","display_name":"Erik Curtis Barton","orcid":null},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erik Curtis Barton","raw_affiliation_strings":["University of Utah"],"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448610","display_name":"Rui Li","orcid":"https://orcid.org/0000-0003-1770-906X"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Li","raw_affiliation_strings":["University of Utah"],"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027517817","display_name":"P. Sadayappan","orcid":"https://orcid.org/0000-0002-4737-2034"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Sadayappan","raw_affiliation_strings":["University of Utah"],"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015460842","display_name":"Aravind Sukumaran-Rajam","orcid":"https://orcid.org/0000-0002-4062-0293"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aravind Sukumaran-Rajam","raw_affiliation_strings":["Meta Platforms"],"affiliations":[{"raw_affiliation_string":"Meta Platforms","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5015151039"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":0.5104,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6537014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"252","last_page":"264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9954000115394592,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9951000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8812559247016907},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8562488555908203},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7121490836143494},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7022453546524048},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6561174988746643},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5462245345115662},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4857805073261261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47760009765625},{"id":"https://openalex.org/keywords/vendor","display_name":"Vendor","score":0.444887638092041},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.427217960357666},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.42347830533981323},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33468204736709595},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.172531396150589}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8812559247016907},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8562488555908203},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7121490836143494},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7022453546524048},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6561174988746643},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5462245345115662},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4857805073261261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47760009765625},{"id":"https://openalex.org/C2777338717","wikidata":"https://www.wikidata.org/wiki/Q1762621","display_name":"Vendor","level":2,"score":0.444887638092041},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.427217960357666},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42347830533981323},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33468204736709595},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.172531396150589},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3559009.3569674","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3559009.3569674","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3559009.3569674","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3559009.3569674","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3559009.3569674","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3559009.3569674","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1736414626","display_name":null,"funder_award_id":"2112606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G447955464","display_name":null,"funder_award_id":"2018016","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7035294437","display_name":null,"funder_award_id":"2018016, 2112606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309374","display_name":"Ohio State University","ror":"https://ror.org/00rs6vg23"},{"id":"https://openalex.org/F4320310050","display_name":"University of Utah","ror":"https://ror.org/03r0ha626"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4318328313.pdf","grobid_xml":"https://content.openalex.org/works/W4318328313.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2077143534","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2570343428","https://openalex.org/W2804500013","https://openalex.org/W2905135312","https://openalex.org/W2963037989","https://openalex.org/W2997591727","https://openalex.org/W3012249773","https://openalex.org/W3123054690","https://openalex.org/W3156745629","https://openalex.org/W4206079995","https://openalex.org/W6752057402"],"related_works":["https://openalex.org/W2478661203","https://openalex.org/W2004830053","https://openalex.org/W3008115697","https://openalex.org/W2145175947","https://openalex.org/W3124949371","https://openalex.org/W3096456556","https://openalex.org/W4240253816","https://openalex.org/W2120643196","https://openalex.org/W1567555513","https://openalex.org/W2471694075"],"abstract_inverted_index":{"The":[0,26,39],"Convolutional":[1],"Neural":[2],"Network":[3],"(CNN)":[4],"kernel":[5,123],"is":[6,34,46,86,117,188],"a":[7,113,158,194],"fundamental":[8],"building":[9],"block":[10],"for":[11,23,32,70,81,119,146,173],"deep":[12,20],"learning,":[13],"which":[14,51],"dominates":[15],"the":[16,71,87,120,142,155,183],"computational":[17],"cost":[18],"of":[19,28,36,73,89,141,157,166,185,193],"learning":[21,172,196],"pipelines":[22],"image":[24],"analysis.":[25],"synthesis":[27],"high-performance":[29,79],"GPU":[30,144],"kernels":[31,45,83],"CNNs":[33,147],"thus":[35],"considerable":[37],"interest.":[38],"current":[40],"state-of-the-art":[41],"in":[42],"optimizing":[43,75],"CNN":[44,85,122],"auto-tuning":[47,149,200],"search":[48],"using":[49],"AutoTVM/Ansor,":[50],"has":[52],"been":[53],"shown":[54],"to":[55,77,93,198],"achieve":[56],"higher":[57,139],"performance":[58,91,140,159],"than":[59,148,182],"vendor":[60],"libraries":[61],"as":[62,64,104],"well":[63],"polyhedral":[65],"compilers.":[66],"A":[67],"primary":[68],"reason":[69],"failure":[72],"general-purpose":[74],"compilers":[76],"deliver":[78],"code":[80,145,180],"key":[82],"like":[84],"challenge":[88],"accurate":[90],"modeling":[92,160,165],"enable":[94],"effective":[95],"choice":[96],"among":[97],"alternative":[98],"transformations":[99],"and/or":[100],"parameter":[101],"values":[102],"such":[103],"tile":[105],"sizes.":[106],"In":[107],"this":[108],"paper":[109],"we":[110,153],"ask":[111],"if":[112],"domain-specific":[114],"compiler":[115],"that":[116,131,162,187],"customized":[118],"important":[121],"can":[124,133],"be":[125,134],"more":[126,178],"effective.":[127],"Our":[128],"results":[129],"show":[130],"it":[132],"very":[135],"effective,":[136],"enabling":[137,176],"even":[138],"generated":[143],"with":[150,170],"TVM/Ansor.":[151],"Further,":[152],"demonstrate":[154],"effectiveness":[156],"approach":[161,184],"integrates":[163],"analytical":[164],"data":[167],"movement":[168],"volume":[169],"machine":[171,195],"offline":[174],"training,":[175],"much":[177],"rapid":[179],"optimization":[181],"TVM/Ansor":[186],"based":[189],"on":[190],"online":[191],"construction":[192],"model":[197],"guide":[199],"search.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}