{"id":"https://openalex.org/W4407319523","doi":"https://doi.org/10.1145/3716876","title":"OptiFX: Automatic Optimization for Convolutional Neural Networks with Aggressive Operator Fusion on GPUs","display_name":"OptiFX: Automatic Optimization for Convolutional Neural Networks with Aggressive Operator Fusion on GPUs","publication_year":2025,"publication_date":"2025-02-10","ids":{"openalex":"https://openalex.org/W4407319523","doi":"https://doi.org/10.1145/3716876"},"language":"en","primary_location":{"id":"doi:10.1145/3716876","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3716876","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1145/3716876","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100425338","display_name":"Xueying Wang","orcid":"https://orcid.org/0000-0002-7835-113X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xueying Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications","Beijing University of Posts and Telecommunications,  Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,  Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088172355","display_name":"Shigang Li","orcid":"https://orcid.org/0000-0003-0022-7865"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shigang Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications","Beijing University of Posts and Telecommunications,  Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,  Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054794287","display_name":"\u8c6a \u65e5\u6d45","orcid":"https://orcid.org/0000-0002-7234-7682"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hao Qian","raw_affiliation_strings":["University of New South Wales","University of New South Wales,  Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"University of New South Wales,  Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087358575","display_name":"Fan Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Luo","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences","University of the Chinese Academy of Sciences","University of the Chinese Academy of Sciences,  Beijing, China","Institute of Computing Technology Chinese Academy of Sciences,  Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences,  Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences,  Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103934748","display_name":"Ziru Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoyang Hao","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences","University of the Chinese Academy of Sciences","Institute of Computing Technology Chinese Academy of Sciences,  Beijing, China","University of the Chinese Academy of Sciences,  Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences,  Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences,  Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112858390","display_name":"Tong Wu","orcid":"https://orcid.org/0009-0001-0472-5178"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Wu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications","Beijing University of Posts and Telecommunications,  Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,  Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102142176","display_name":"Ruiyuan Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiyuan Xu","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences","University of the Chinese Academy of Sciences","University of the Chinese Academy of Sciences,  Beijing, China","Institute of Computing Technology Chinese Academy of Sciences,  Beijing China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences,  Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences,  Beijing China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086633294","display_name":"Huimin Cui","orcid":"https://orcid.org/0000-0002-2491-7679"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huimin Cui","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences","University of the Chinese Academy of Sciences","University of the Chinese Academy of Sciences,  Beijing, China","Institute of Computing Technology Chinese Academy of Sciences,  Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences,  Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences,  Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","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":"government","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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobing Feng","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences","University of the Chinese Academy of Sciences","University of the Chinese Academy of Sciences,  Beijing, China","Institute of Computing Technology Chinese Academy of Sciences,  Beijing China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences,  Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences,  Beijing China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100607669","display_name":"Guangli Li","orcid":"https://orcid.org/0000-0002-9738-261X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"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/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Guangli Li","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences","University of New South Wales","University of the Chinese Academy of Sciences","University of the Chinese Academy of Sciences,  Beijing, China","Institute of Computing Technology Chinese Academy of Sciences,  Beijing China","University of New South Wales,  Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of New South Wales","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences,  Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences,  Beijing China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of New South Wales,  Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024664385","display_name":"Jingling Xue","orcid":"https://orcid.org/0000-0003-0380-3506"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jingling Xue","raw_affiliation_strings":["School of Computer Science and Engieering, UNSW Sydney","School of Computer Science and Engieering, UNSW Sydney, Kensington, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engieering, UNSW Sydney","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"School of Computer Science and Engieering, UNSW Sydney, Kensington, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5100425338"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":2.4362,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8701821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"22","issue":"2","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T10320","display_name":"Neural Networks and Applications","score":0.9987000226974487,"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":0.9962000250816345,"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":0.7962639927864075},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6450991630554199},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.617682695388794},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4693252444267273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4636942148208618},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3555552661418915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7962639927864075},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6450991630554199},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.617682695388794},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4693252444267273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4636942148208618},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3555552661418915},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3716876","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3716876","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3716876","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3716876","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3454282639","display_name":null,"funder_award_id":"DP250104934","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G3881994376","display_name":null,"funder_award_id":"62302479, 62232015, 62090024, and 62372055","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5450936095","display_name":null,"funder_award_id":"2023ZD0120502","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2002555321","https://openalex.org/W2023415862","https://openalex.org/W2035430533","https://openalex.org/W2078504799","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2899971035","https://openalex.org/W2905135312","https://openalex.org/W2922008702","https://openalex.org/W2949967139","https://openalex.org/W2963446712","https://openalex.org/W2963918968","https://openalex.org/W2970971581","https://openalex.org/W2981758446","https://openalex.org/W3012249773","https://openalex.org/W3047049572","https://openalex.org/W3081486497","https://openalex.org/W3100341797","https://openalex.org/W3122286897","https://openalex.org/W3139307480","https://openalex.org/W3174529902","https://openalex.org/W3177229224","https://openalex.org/W3177452048","https://openalex.org/W4211021930","https://openalex.org/W4212986322","https://openalex.org/W4244917406","https://openalex.org/W4251637954","https://openalex.org/W4255653201","https://openalex.org/W4281758439","https://openalex.org/W4360831828","https://openalex.org/W4380874786","https://openalex.org/W4384155663","https://openalex.org/W4392265934","https://openalex.org/W4394998528","https://openalex.org/W4394998532","https://openalex.org/W4398146107"],"related_works":["https://openalex.org/W4391621807","https://openalex.org/W4321487865","https://openalex.org/W4313906399","https://openalex.org/W4391621790","https://openalex.org/W4239306820","https://openalex.org/W4391266461","https://openalex.org/W2590798552","https://openalex.org/W2811106690","https://openalex.org/W2947043951","https://openalex.org/W4399188509"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"are":[4,36],"fundamental":[5],"to":[6,40,45,105,116],"advancing":[7],"computer":[8],"vision":[9],"technologies.":[10],"As":[11],"CNNs":[12],"become":[13],"more":[14],"complex":[15],"and":[16,28,89,111,137,144,166],"larger,":[17],"optimizing":[18],"model":[19],"inference":[20,61,87,170],"remains":[21],"a":[22,79,101],"critical":[23],"challenge":[24],"in":[25,168],"both":[26],"industry":[27],"academia.":[29],"On":[30],"modern":[31],"GPU":[32],"platforms,":[33,174],"CNN":[34,130],"operators":[35,57,68],"typically":[37],"memory-bound,":[38],"leading":[39],"significant":[41],"performance":[42,171],"degradation":[43],"due":[44],"memory":[46],"wall":[47],"effects.":[48],"While":[49],"recent":[50],"advancements":[51],"have":[52],"utilized":[53],"operator":[54,81],"fusion\u2013merging":[55],"multiple":[56,66],"into":[58],"one\u2013to":[59],"enhance":[60],"performance,":[62,88],"the":[63],"fusion":[64,82,110],"of":[65,161],"region-based":[67],"like":[69],"convolution":[70],"is":[71],"seldom":[72],"addressed.":[73],"This":[74],"article":[75],"introduces":[76],"AFusion":[77],",":[78,163,165],"novel":[80],"technique":[83],"aimed":[84],"at":[85],"improving":[86],"OptiFX,":[90],"an":[91],"automatic":[92],"optimization":[93],"framework":[94],"based":[95],"on":[96,172],"this":[97],"approach.":[98],"OptiFX":[99,126,153],"employs":[100],"cost-based":[102],"backtracking":[103],"search":[104],"identify":[106],"optimal":[107],"sub-graphs":[108],"for":[109,120],"utilizes":[112],"template-based":[113],"code":[114],"generation":[115],"create":[117],"efficient":[118],"kernels":[119],"these":[121,173],"fused":[122],"sub-graphs.":[123],"We":[124],"evaluate":[125],"across":[127],"seven":[128],"prominent":[129],"architectures\u2013GoogLeNet,":[131],"ResNet,":[132],"DenseNet,":[133],"MobileNet,":[134],"SqueezeNet,":[135],"NasNet,":[136],"UNet\u2013on":[138],"Nvidia":[139],"A6000":[140],"Ada,":[141],"RTX":[142],"4090,":[143],"Jetson":[145],"AGX":[146],"Orin":[147],"platforms.":[148],"Our":[149],"results":[150],"demonstrate":[151],"that":[152],"significantly":[154],"outperforms":[155],"existing":[156],"methods,":[157],"achieving":[158],"average":[159],"speedups":[160],"\\(2.91\\times\\)":[162],"\\(3.30\\times\\)":[164],"\\(2.09\\times\\)":[167],"accelerating":[169],"respectively.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
