{"id":"https://openalex.org/W4402870437","doi":"https://doi.org/10.1145/3696665","title":"Performance Analysis of CNN Inference/Training with Convolution and Non-Convolution Operations on ASIC Accelerators","display_name":"Performance Analysis of CNN Inference/Training with Convolution and Non-Convolution Operations on ASIC Accelerators","publication_year":2024,"publication_date":"2024-09-26","ids":{"openalex":"https://openalex.org/W4402870437","doi":"https://doi.org/10.1145/3696665"},"language":"en","primary_location":{"id":"doi:10.1145/3696665","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696665","pdf_url":null,"source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic 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/A5084514143","display_name":"Hadi Esmaeilzadeh","orcid":"https://orcid.org/0000-0002-8548-1039"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hadi Esmaeilzadeh","raw_affiliation_strings":["Computer Science and Engineering, University of California San Diego, La Jolla, United States"],"raw_orcid":"https://orcid.org/0000-0002-8548-1039","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of California San Diego, La Jolla, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082499242","display_name":"Soroush Ghodrati","orcid":"https://orcid.org/0000-0001-5514-8027"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soroush Ghodrati","raw_affiliation_strings":["Computer Science and Engineering, University of California San Diego, La Jolla, United States"],"raw_orcid":"https://orcid.org/0000-0001-5514-8027","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of California San Diego, La Jolla, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073558386","display_name":"Andrew B. Kahng","orcid":"https://orcid.org/0000-0002-4490-5018"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew B. Kahng","raw_affiliation_strings":["Computer Science and Engineering, Electrical and Computer Engineering, University of California San Diego, La Jolla, United States","Department of CSE and ECE, University of California San Diego, La Jolla, United States"],"raw_orcid":"https://orcid.org/0000-0002-4490-5018","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Electrical and Computer Engineering, University of California San Diego, La Jolla, United States","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Department of CSE and ECE, University of California San Diego, La Jolla, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000799803","display_name":"Sean Kinzer","orcid":"https://orcid.org/0000-0002-0955-585X"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean Kinzer","raw_affiliation_strings":["Computer Science and Engineering, University of California San Diego, La Jolla, United States"],"raw_orcid":"https://orcid.org/0000-0002-0955-585X","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of California San Diego, La Jolla, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004590102","display_name":"Susmita Dey Manasi","orcid":"https://orcid.org/0000-0001-9358-6255"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]},{"id":"https://openalex.org/I4210101327","display_name":"Twin Cities Orthopedics","ror":"https://ror.org/01en4s460","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210101327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Susmita Dey Manasi","raw_affiliation_strings":["Electrical and Computer Engineering, University of Minnesota Twin Cities, Minneapolis, United States"],"raw_orcid":"https://orcid.org/0000-0001-9358-6255","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Minnesota Twin Cities, Minneapolis, United States","institution_ids":["https://openalex.org/I130238516","https://openalex.org/I4210101327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068714995","display_name":"Sachin S. Sapatnekar","orcid":"https://orcid.org/0000-0002-5353-2364"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]},{"id":"https://openalex.org/I4210101327","display_name":"Twin Cities Orthopedics","ror":"https://ror.org/01en4s460","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210101327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sachin S. Sapatnekar","raw_affiliation_strings":["Electrical and Computer Engineering, University of Minnesota Twin Cities, Minneapolis, United States"],"raw_orcid":"https://orcid.org/0000-0002-5353-2364","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Minnesota Twin Cities, Minneapolis, United States","institution_ids":["https://openalex.org/I130238516","https://openalex.org/I4210101327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078035974","display_name":"Zhiang Wang","orcid":"https://orcid.org/0000-0002-6669-9702"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiang Wang","raw_affiliation_strings":["Electrical and Computer Engineering, University of California San Diego, La Jolla, United States"],"raw_orcid":"https://orcid.org/0000-0002-6669-9702","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of California San Diego, La Jolla, United States","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.329,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53698426,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"30","issue":"1","first_page":"1","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9990000128746033,"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":0.9990000128746033,"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/T11216","display_name":"Radiation Detection and Scintillator Technologies","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/3108","display_name":"Radiation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11949","display_name":"Nuclear Physics and Applications","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/3108","display_name":"Radiation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8706093430519104},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.8625849485397339},{"id":"https://openalex.org/keywords/application-specific-integrated-circuit","display_name":"Application-specific integrated circuit","score":0.6957546472549438},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6642158031463623},{"id":"https://openalex.org/keywords/overlap\u2013add-method","display_name":"Overlap\u2013add method","score":0.4782937169075012},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4274926483631134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4115801155567169},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2508615255355835},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.20533058047294617},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12738513946533203},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.09161704778671265},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.060060739517211914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8706093430519104},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.8625849485397339},{"id":"https://openalex.org/C77390884","wikidata":"https://www.wikidata.org/wiki/Q217302","display_name":"Application-specific integrated circuit","level":2,"score":0.6957546472549438},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6642158031463623},{"id":"https://openalex.org/C181002996","wikidata":"https://www.wikidata.org/wiki/Q1611641","display_name":"Overlap\u2013add method","level":5,"score":0.4782937169075012},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4274926483631134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4115801155567169},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2508615255355835},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.20533058047294617},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12738513946533203},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.09161704778671265},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.060060739517211914},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C76563020","wikidata":"https://www.wikidata.org/wiki/Q4817582","display_name":"Fractional Fourier transform","level":4,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696665","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696665","pdf_url":null,"source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2112796928","https://openalex.org/W2194775991","https://openalex.org/W2761132374","https://openalex.org/W2798544842","https://openalex.org/W2912949188","https://openalex.org/W2963114857","https://openalex.org/W2990138404","https://openalex.org/W3017521908","https://openalex.org/W3036878841","https://openalex.org/W3125935828","https://openalex.org/W3127676525","https://openalex.org/W3131920484","https://openalex.org/W3160236860","https://openalex.org/W4318685300"],"related_works":["https://openalex.org/W4372260258","https://openalex.org/W2267589039","https://openalex.org/W2369791303","https://openalex.org/W2133280289","https://openalex.org/W2360069155","https://openalex.org/W2759540840","https://openalex.org/W2169963286","https://openalex.org/W4254230825","https://openalex.org/W2919798019","https://openalex.org/W2159795102"],"abstract_inverted_index":{"Today\u2019s":[0],"performance":[1,60,107,126,162],"analysis":[2,61,127],"frameworks":[3,33,42],"for":[4,51,64,118,142,170],"deep":[5],"learning":[6],"accelerators":[7],"suffer":[8],"from":[9],"two":[10],"significant":[11],"limitations.":[12],"First,":[13],"although":[14],"modern":[15],"convolutional":[16],"neural":[17],"networks":[18],"(CNNs)":[19],"consist":[20],"of":[21,24,74,82,139],"many":[22],"types":[23],"layers":[25,38],"other":[26],"than":[27],"convolution,":[28],"especially":[29],"during":[30],"training,":[31],"these":[32,41],"largely":[34],"focus":[35],"on":[36,88,130],"convolution":[37,78],"only.":[39],"Second,":[40],"are":[43],"generally":[44],"targeted":[45],"towards":[46],"inference":[47,85,121],"and":[48,79,86,103,116,122,155],"lack":[49],"support":[50],"training":[52,87,123,144],"operations.":[53],"This":[54],"work":[55],"proposes":[56],"a":[57,89,98,131,165],"novel":[58],"open-source":[59],"framework,":[62],"SimDIT,":[63],"general":[65],"ASIC-based":[66],"systolic":[67],"hardware":[68,92],"accelerator":[69],"platforms.":[70],"The":[71],"modeling":[72],"effort":[73],"SimDIT":[75,94,159],"comprehensively":[76],"covers":[77],"non-convolution":[80,135],"operations":[81,136],"both":[83],"CNN":[84,120],"highly":[90],"parameterizable":[91],"substrate.":[93],"is":[95],"integrated":[96],"with":[97],"backend":[99],"silicon":[100],"implementation":[101],"flow":[102],"provides":[104],"detailed":[105],"end-to-end":[106],"statistics":[108],"(i.e.,":[109],"data":[110],"access":[111],"cost,":[112],"cycle":[113],"counts,":[114],"energy,":[115],"power)":[117],"executing":[119],"workloads.":[124],"SimDIT-enabled":[125],"reveals":[128],"that":[129],"64\u00d764":[132],"processing":[133],"array,":[134],"constitute":[137],"59.5%":[138],"total":[140],"runtime":[141],"ResNet-50":[143,171],"workload.":[145],"In":[146],"addition,":[147],"by":[148],"optimally":[149],"distributing":[150],"available":[151],"off-chip":[152],"DRAM":[153],"bandwidth":[154],"on-chip":[156],"SRAM":[157],"resources,":[158],"achieves":[160],"18\u00d7":[161],"improvement":[163],"over":[164],"generic":[166],"static":[167],"resource":[168],"allocation":[169],"inference.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2024-09-27T00:00:00"}
