{"id":"https://openalex.org/W4400680083","doi":"https://doi.org/10.1109/tcad.2024.3429419","title":"DiMO-CNN: Deep Learning Toolkit-Accelerated Analytical Modeling and Optimization of CNN Hardware and Dataflow","display_name":"DiMO-CNN: Deep Learning Toolkit-Accelerated Analytical Modeling and Optimization of CNN Hardware and Dataflow","publication_year":2024,"publication_date":"2024-07-16","ids":{"openalex":"https://openalex.org/W4400680083","doi":"https://doi.org/10.1109/tcad.2024.3429419"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2024.3429419","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2024.3429419","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-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/A5102483762","display_name":"Jianfeng Song","orcid":"https://orcid.org/0000-0001-7286-3444"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianfeng Song","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Texas A&#x0026;M University, College Station, TX, USA"],"raw_orcid":"https://orcid.org/0000-0001-7286-3444","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Texas A&#x0026;M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013528664","display_name":"Rongjian Liang","orcid":"https://orcid.org/0000-0001-8626-2359"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rongjian Liang","raw_affiliation_strings":["Research Department, NVIDIA Corporation, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0001-8626-2359","affiliations":[{"raw_affiliation_string":"Research Department, NVIDIA Corporation, Austin, TX, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770278","display_name":"Bo Yuan","orcid":"https://orcid.org/0000-0002-3978-2930"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Yuan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Rutgers University, Piscataway, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0002-3978-2930","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103246390","display_name":"Jiang Hu","orcid":"https://orcid.org/0000-0003-1157-7799"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiang Hu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Texas A&#x0026;M University, College Station, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-1157-7799","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Texas A&#x0026;M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1114,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.80755044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"44","issue":"1","first_page":"251","last_page":"265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7383000254631042,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7383000254631042,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.6687999963760376,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.9651044607162476},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7653288245201111},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7361692786216736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5691533088684082},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.46906065940856934},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3922511339187622},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3531334400177002},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.33420759439468384}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.9651044607162476},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7653288245201111},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7361692786216736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5691533088684082},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.46906065940856934},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3922511339187622},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3531334400177002},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.33420759439468384}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2024.3429419","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2024.3429419","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G271639475","display_name":null,"funder_award_id":"CMMI-2038625","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3505881599","display_name":null,"funder_award_id":"CCF-1955909","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6330234832","display_name":null,"funder_award_id":"GRC-CADT-3013.001","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"id":"https://openalex.org/G7173670773","display_name":null,"funder_award_id":"CCF-2106725","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/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2289252105","https://openalex.org/W2547875792","https://openalex.org/W2606722458","https://openalex.org/W2625457103","https://openalex.org/W2742479298","https://openalex.org/W2790925711","https://openalex.org/W2940862705","https://openalex.org/W2979310060","https://openalex.org/W2981680926","https://openalex.org/W3015497938","https://openalex.org/W3016142271","https://openalex.org/W3017521908","https://openalex.org/W3036696276","https://openalex.org/W3045337512","https://openalex.org/W3092020069","https://openalex.org/W3092216346","https://openalex.org/W3092334294","https://openalex.org/W3102790199","https://openalex.org/W3135807226","https://openalex.org/W3159869264","https://openalex.org/W3187481008","https://openalex.org/W3192336523","https://openalex.org/W3211833531","https://openalex.org/W4205146836","https://openalex.org/W4235535008","https://openalex.org/W4249932213","https://openalex.org/W4288083528","https://openalex.org/W4381050415","https://openalex.org/W6754005058","https://openalex.org/W6756718674","https://openalex.org/W6758143911","https://openalex.org/W6766978945","https://openalex.org/W6791098353","https://openalex.org/W6796027562"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2171015181","https://openalex.org/W4239447582","https://openalex.org/W1484403103","https://openalex.org/W1998888015","https://openalex.org/W4390846322"],"abstract_inverted_index":{"The":[0,14,56],"growing":[1],"complexity":[2],"of":[3,60,127],"CNNs":[4],"demands":[5],"both":[6],"hardware":[7,31],"acceleration":[8],"design":[9,32],"and":[10,33,46,102],"dataflow":[11,34],"mapping":[12],"solutions.":[13],"large":[15],"co-design":[16],"solution":[17],"space":[18],"presents":[19],"a":[20,37,118],"huge":[21],"challenge.":[22],"We":[23],"introduce":[24],"an":[25],"analytical":[26,62],"model":[27,63],"for":[28],"assessing":[29],"CNN":[30],"solutions,":[35],"using":[36],"matrix-based":[38],"approach.":[39],"Our":[40],"co-optimization":[41,77],"method,":[42],"combining":[43],"nonlinear":[44],"programming":[45],"parallel":[47],"local":[48],"search,":[49],"excels":[50],"in":[51],"addressing":[52],"the":[53],"power-performance-area":[54],"tradeoff.":[55],"average":[57,81],"relative":[58],"error":[59],"our":[61,76],"compared":[64],"with":[65,80],"Timeloop":[66],"is":[67],"as":[68,70],"small":[69],"1%.":[71],"Compared":[72],"to":[73],"state-of-the-art":[74],"methods,":[75],"achieves":[78],"solutions":[79],"<inline-formula":[82,92,103,119],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[83,93,104,120],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[84,94,105,121],"<tex-math":[85,95,106,122],"notation=\"LaTeX\">$3.14\\times":[86],"$":[87,124],"</tex-math></inline-formula>":[88,98,109,125],"shorter":[89],"inference":[90],"latency,":[91],"notation=\"LaTeX\">$\\mathbf":[96,107],"{68.2\\%}$":[97],"less":[99,110],"power":[100],"consumption,":[101],"{74\\%}$":[108],"area":[111],"on":[112],"all":[113],"testcases.":[114],"It":[115],"also":[116],"provides":[117],"notation=\"LaTeX\">$200\\times":[123],"speedup":[126],"optimization":[128],"runtime.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}