{"id":"https://openalex.org/W4409060615","doi":"https://doi.org/10.1109/tpds.2025.3555968","title":"WCET Estimation for CNN Inference on FPGA SoC With Multi-DPU Engines","display_name":"WCET Estimation for CNN Inference on FPGA SoC With Multi-DPU Engines","publication_year":2025,"publication_date":"2025-04-01","ids":{"openalex":"https://openalex.org/W4409060615","doi":"https://doi.org/10.1109/tpds.2025.3555968"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2025.3555968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2025.3555968","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed 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/A5069960498","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0003-2615-2603"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["School of Cyber Science and Technology, Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yunlong Yu","orcid":"https://orcid.org/0009-0007-3679-8359"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunlong Yu","raw_affiliation_strings":["School of Cyber Science and Technology, Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100640343","display_name":"Xiao Jiang","orcid":"https://orcid.org/0000-0001-7335-4238"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Jiang","raw_affiliation_strings":["School of Cyber Science and Technology, Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002245169","display_name":"Nan Guan","orcid":"https://orcid.org/0000-0003-3775-911X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Nan Guan","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026435847","display_name":"Naijun Zhan","orcid":"https://orcid.org/0000-0003-3298-3817"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Naijun Zhan","raw_affiliation_strings":["School of Computer Science and Key Laboratory of High Confidence Software Technology, Peking University, Beijing, China","Quan Cheng Laboratory, Jinan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Key Laboratory of High Confidence Software Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Quan Cheng Laboratory, Jinan, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063104755","display_name":"Lei Ju","orcid":"https://orcid.org/0000-0001-6186-5399"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Ju","raw_affiliation_strings":["Quan Cheng Laboratory, Jinan, China","School of Cyber Science and Technology, Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Quan Cheng Laboratory, Jinan, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"School of Cyber Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5069960498"],"corresponding_institution_ids":["https://openalex.org/I80143920"],"apc_list":null,"apc_paid":null,"fwci":2.3568,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8843873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"36","issue":"6","first_page":"1146","last_page":"1160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9132000207901001,"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":0.9132000207901001,"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":0.8224263191223145},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7927224636077881},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5835491418838501},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.5446131229400635},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.48277226090431213},{"id":"https://openalex.org/keywords/system-on-a-chip","display_name":"System on a chip","score":0.4165002107620239},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3753260672092438},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3384186625480652},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19817781448364258}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8224263191223145},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7927224636077881},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5835491418838501},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5446131229400635},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.48277226090431213},{"id":"https://openalex.org/C118021083","wikidata":"https://www.wikidata.org/wiki/Q610398","display_name":"System on a chip","level":2,"score":0.4165002107620239},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3753260672092438},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3384186625480652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19817781448364258},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2025.3555968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2025.3555968","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1391897444","display_name":null,"funder_award_id":"62432005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4304361298","display_name":null,"funder_award_id":"ZR20220F003","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G5802567463","display_name":null,"funder_award_id":"ZR2024MF099","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G6378334634","display_name":null,"funder_award_id":"62302270","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2069669488","https://openalex.org/W2076285066","https://openalex.org/W2094756095","https://openalex.org/W2108598243","https://openalex.org/W2133420723","https://openalex.org/W2340897893","https://openalex.org/W2887936511","https://openalex.org/W2909139149","https://openalex.org/W2935524202","https://openalex.org/W2963163009","https://openalex.org/W2963701245","https://openalex.org/W2964332990","https://openalex.org/W2977634443","https://openalex.org/W2981854066","https://openalex.org/W2989331028","https://openalex.org/W2997106510","https://openalex.org/W3017135385","https://openalex.org/W3035430964","https://openalex.org/W3061070527","https://openalex.org/W3104284241","https://openalex.org/W3160369968","https://openalex.org/W3184429126","https://openalex.org/W3207507293","https://openalex.org/W4200195825","https://openalex.org/W4293025171","https://openalex.org/W4311463582","https://openalex.org/W4311839580","https://openalex.org/W6694596856","https://openalex.org/W6695314431","https://openalex.org/W6740862897","https://openalex.org/W6750227808","https://openalex.org/W6753213483","https://openalex.org/W6765718025","https://openalex.org/W6777046832","https://openalex.org/W6779702991"],"related_works":["https://openalex.org/W1967938402","https://openalex.org/W2386041993","https://openalex.org/W1608572506","https://openalex.org/W3142211975","https://openalex.org/W1879443270","https://openalex.org/W2018912978","https://openalex.org/W2130914040","https://openalex.org/W2119122672","https://openalex.org/W4292904049","https://openalex.org/W2136848245"],"abstract_inverted_index":{"The":[0,126],"Deep":[1],"Learning":[2],"Processor":[3],"Unit":[4],"(DPU)":[5],"released":[6],"in":[7,55,66,122,177,193],"the":[8,43,70,85,92,107,110,113,161,171,181,194],"official":[9],"Xilinx":[10,29],"Vitis":[11],"AI":[12],"toolchain":[13],"stands":[14],"as":[15],"a":[16,67,76,96,123,130,151,168],"commercial":[17],"off-the-shelf":[18],"solution":[19],"tailored":[20],"for":[21,51,75,100,119,135],"accelerating":[22],"convolutional":[23],"neural":[24],"network":[25],"(CNN)":[26],"inference":[27,73,78,88,121],"on":[28,37],"FPGA":[30,34],"devices.":[31],"While":[32],"most":[33],"accelerator":[35],"focus":[36],"high":[38],"performance":[39],"and":[40,139],"energy-efficiency,":[41],"analyzing":[42],"worst-case":[44,72],"execution":[45],"time":[46,74],"(WCET)":[47],"bound":[48],"is":[49,174],"essential":[50],"using":[52],"CNN":[53,77,102,120],"accelerations":[54],"real-time":[56],"embedded":[57],"systems":[58],"design.":[59],"In":[60],"this":[61],"work,":[62],"we":[63],"show":[64],"that":[65,157],"multi-DPU":[68,124,195],"environment,":[69,170],"observed":[71],"task":[79],"could":[80],"become":[81],"3X":[82],"larger":[83],"w.r.t.":[84],"best":[86,108],"case":[87],"time,":[89],"which":[90],"prompts":[91],"prominent":[93],"importance":[94],"of":[95,109,163],"static":[97,115],"timing":[98,116,132],"analysis":[99,117,156,172],"FPGA-based":[101],"inference.":[103],"We":[104],"propose,":[105],"to":[106],"authors\u2019":[111],"knowledge,":[112],"first":[114],"framework":[118,128],"environment.":[125,196],"proposed":[127,186],"introduces":[129],"generalized":[131],"behavior":[133],"model":[134],"shared":[136],"bus":[137],"arbitration":[138],"memory":[140,153],"access":[141,154],"contention":[142,155],"between":[143],"parallel":[144],"running":[145],"DPU":[146],"engines.":[147],"Additionally,":[148],"it":[149],"incorporates":[150],"fine-grained":[152],"takes":[158],"into":[159],"account":[160],"characteristics":[162],"deep":[164],"learning":[165],"applications.":[166],"For":[167],"single-DPU":[169],"result":[173],"27%":[175],"tighter":[176],"average":[178],"compared":[179],"with":[180],"state-of-the-art":[182],"results.":[183],"Furthermore,":[184],"our":[185],"method":[187],"produces":[188],"relatively":[189],"tight":[190],"estimated":[191],"results":[192]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}