{"id":"https://openalex.org/W3123054690","doi":"https://doi.org/10.1145/3445814.3446759","title":"Analytical characterization and design space exploration for optimization of CNNs","display_name":"Analytical characterization and design space exploration for optimization of CNNs","publication_year":2021,"publication_date":"2021-04-11","ids":{"openalex":"https://openalex.org/W3123054690","doi":"https://doi.org/10.1145/3445814.3446759","mag":"3123054690"},"language":"en","primary_location":{"id":"doi:10.1145/3445814.3446759","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3445814.3446759","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3445814.3446759","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3445814.3446759","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Rui Li","orcid":"https://orcid.org/0000-0001-9847-5642"},"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":"Rui Li","raw_affiliation_strings":["University of Utah, USA"],"affiliations":[{"raw_affiliation_string":"University of Utah, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":null,"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":false,"raw_author_name":"Yufan Xu","raw_affiliation_strings":["University of Utah, USA"],"affiliations":[{"raw_affiliation_string":"University of Utah, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Aravind Sukumaran-Rajam","orcid":"https://orcid.org/0000-0002-4062-0293"},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aravind Sukumaran-Rajam","raw_affiliation_strings":["Washington State University, USA"],"affiliations":[{"raw_affiliation_string":"Washington State University, USA","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Atanas Rountev","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atanas Rountev","raw_affiliation_strings":["Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":null,"display_name":"P. Sadayappan","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":"P. Sadayappan","raw_affiliation_strings":["University of Utah, USA"],"affiliations":[{"raw_affiliation_string":"University of Utah, USA","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":3.6901,"has_fulltext":true,"cited_by_count":49,"citation_normalized_percentile":{"value":0.94426224,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"928","last_page":"942"},"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/T10320","display_name":"Neural Networks and Applications","score":0.9991000294685364,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9962999820709229,"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/bottleneck","display_name":"Bottleneck","score":0.718500018119812},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5690000057220459},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.4560000002384186},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.4465999901294708},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.43230000138282776},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.42750000953674316},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.3946000039577484},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.3781000077724457},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.3682999908924103}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.718500018119812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6736999750137329},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5690000057220459},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.4560000002384186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45559999346733093},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43869999051094055},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3946000039577484},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2865999937057495},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C73586568","wikidata":"https://www.wikidata.org/wiki/Q2600211","display_name":"Parameter space","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26499998569488525},{"id":"https://openalex.org/C164752517","wikidata":"https://www.wikidata.org/wiki/Q5570875","display_name":"Global optimization","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C104060986","wikidata":"https://www.wikidata.org/wiki/Q180046","display_name":"Space exploration","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3445814.3446759","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3445814.3446759","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3445814.3446759","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2101.09808","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.09808","pdf_url":"https://arxiv.org/pdf/2101.09808","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3445814.3446759","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3445814.3446759","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3445814.3446759","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1134857894","display_name":"SPX: Collaborative Research: Parallel Algorithm by Blocks - A Data-centric Compiler/runtime System for Productive Programming of Scalable Parallel Systems","funder_award_id":"1946752","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1459384902","display_name":null,"funder_award_id":"1919122","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/G6958952275","display_name":null,"funder_award_id":"1946752,2018016","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3123054690.pdf","grobid_xml":"https://content.openalex.org/works/W3123054690.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W38784877","https://openalex.org/W1579556664","https://openalex.org/W1690163247","https://openalex.org/W1961751213","https://openalex.org/W2077143534","https://openalex.org/W2102976251","https://openalex.org/W2108737583","https://openalex.org/W2123680107","https://openalex.org/W2123871098","https://openalex.org/W2129463564","https://openalex.org/W2147505032","https://openalex.org/W2149207009","https://openalex.org/W2156316655","https://openalex.org/W2302255633","https://openalex.org/W2510697685","https://openalex.org/W2516525699","https://openalex.org/W2570343428","https://openalex.org/W2905135312","https://openalex.org/W2954478959","https://openalex.org/W2970971581","https://openalex.org/W2985039650","https://openalex.org/W3203568064","https://openalex.org/W4232598359","https://openalex.org/W4239685157","https://openalex.org/W4251637954","https://openalex.org/W6713134421"],"related_works":[],"abstract_inverted_index":{"Moving":[0],"data":[1,40],"through":[2],"the":[3,13,43,48,65],"memory":[4],"hierarchy":[5],"is":[6,53],"a":[7],"fundamental":[8,36],"bottleneck":[9],"that":[10,78],"can":[11],"limit":[12],"performance":[14,85],"of":[15,18],"core":[16],"algorithms":[17],"machine":[19],"learning,":[20],"such":[21],"as":[22],"convolutional":[23],"neural":[24],"networks":[25],"(CNNs).":[26],"Loop-level":[27],"optimization,":[28],"including":[29],"loop":[30,33],"tiling":[31],"and":[32,89],"permutation,":[34],"are":[35],"transformations":[37],"to":[38],"reduce":[39],"movement.":[41],"However,":[42],"search":[44],"space":[45],"for":[46,63,70,93],"finding":[47,64],"best":[49,66],"loop-level":[50,67],"optimization":[51,68],"configuration":[52,69],"explosively":[54],"large.":[55],"This":[56],"paper":[57],"develops":[58],"an":[59],"analytical":[60],"modeling":[61],"approach":[62,80],"CNNs":[71],"on":[72],"multi-core":[73],"CPUs.":[74],"Experimental":[75],"evaluation":[76],"shows":[77],"this":[79],"achieves":[81],"comparable":[82],"or":[83],"better":[84],"than":[86],"state-of-the-art":[87],"libraries":[88],"auto-tuning":[90],"based":[91],"optimizers":[92],"CNNs.":[94]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2021-02-01T00:00:00"}