{"id":"https://openalex.org/W3174389038","doi":"https://doi.org/10.1109/tcad.2021.3093398","title":"Exploring HW/SW Co-Design for Video Analysis on CPU-FPGA Heterogeneous Systems","display_name":"Exploring HW/SW Co-Design for Video Analysis on CPU-FPGA Heterogeneous Systems","publication_year":2021,"publication_date":"2021-06-29","ids":{"openalex":"https://openalex.org/W3174389038","doi":"https://doi.org/10.1109/tcad.2021.3093398","mag":"3174389038"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2021.3093398","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcad.2021.3093398","pdf_url":"https://ieeexplore.ieee.org/ielx7/43/9778249/09467325.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/43/9778249/09467325.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100330729","display_name":"Xiaofan Zhang","orcid":"https://orcid.org/0000-0001-5081-3972"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofan Zhang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois Urbana&#x2013;Champaign, Urbana, IL, USA","University of Illinois Urbana&#x2013"],"raw_orcid":"https://orcid.org/0000-0001-5081-3972","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois Urbana&#x2013;Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois Urbana&#x2013","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100773808","display_name":"Yuan Ma","orcid":"https://orcid.org/0000-0001-6131-6584"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Ma","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois Urbana&#x2013;Champaign, Urbana, IL, USA","University of Illinois Urbana&#x2013"],"raw_orcid":"https://orcid.org/0000-0001-6131-6584","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois Urbana&#x2013;Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois Urbana&#x2013","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030156276","display_name":"Jinjun Xiong","orcid":"https://orcid.org/0000-0002-2620-4859"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinjun Xiong","raw_affiliation_strings":["Cognitive Computing Systems Research, IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-2620-4859","affiliations":[{"raw_affiliation_string":"Cognitive Computing Systems Research, IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040404999","display_name":"Wen\u2010mei Hwu","orcid":"https://orcid.org/0000-0003-2532-5349"},"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":"Wen-Mei W. Hwu","raw_affiliation_strings":["NVIDIA Research, NVIDIA, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2532-5349","affiliations":[{"raw_affiliation_string":"NVIDIA Research, NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060025664","display_name":"Volodymyr Kindratenko","orcid":"https://orcid.org/0000-0002-9336-4756"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Volodymyr Kindratenko","raw_affiliation_strings":["National Center for Supercomputing Applications, University of Illinois Urbana&#x2013;Champaign, Urbana, IL, USA","Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-9336-4756","affiliations":[{"raw_affiliation_string":"National Center for Supercomputing Applications, University of Illinois Urbana&#x2013;Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I4210135837","https://openalex.org/I157725225"]},{"raw_affiliation_string":"Champaign, Urbana, IL, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056321228","display_name":"Deming Chen","orcid":"https://orcid.org/0000-0002-3016-0270"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deming Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois Urbana&#x2013;Champaign, Urbana, IL, USA","University of Illinois Urbana&#x2013"],"raw_orcid":"https://orcid.org/0000-0002-3016-0270","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois Urbana&#x2013;Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois Urbana&#x2013","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0848,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.76552895,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"41","issue":"6","first_page":"1606","last_page":"1619"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9944999814033508,"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":0.8091012239456177},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.6944491863250732},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6382145285606384},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.5474309921264648},{"id":"https://openalex.org/keywords/application-specific-integrated-circuit","display_name":"Application-specific integrated circuit","score":0.5102989673614502},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.47730696201324463},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4591062068939209},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.45822274684906006},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.42109471559524536},{"id":"https://openalex.org/keywords/design-flow","display_name":"Design flow","score":0.4173389673233032},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.24328076839447021},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.22948697209358215},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18780454993247986}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8091012239456177},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.6944491863250732},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6382145285606384},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5474309921264648},{"id":"https://openalex.org/C77390884","wikidata":"https://www.wikidata.org/wiki/Q217302","display_name":"Application-specific integrated circuit","level":2,"score":0.5102989673614502},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.47730696201324463},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4591062068939209},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.45822274684906006},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.42109471559524536},{"id":"https://openalex.org/C37135326","wikidata":"https://www.wikidata.org/wiki/Q931942","display_name":"Design flow","level":2,"score":0.4173389673233032},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.24328076839447021},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.22948697209358215},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18780454993247986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2021.3093398","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcad.2021.3093398","pdf_url":"https://ieeexplore.ieee.org/ielx7/43/9778249/09467325.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1109/tcad.2021.3093398","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcad.2021.3093398","pdf_url":"https://ieeexplore.ieee.org/ielx7/43/9778249/09467325.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8999999761581421}],"awards":[{"id":"https://openalex.org/G7388224766","display_name":null,"funder_award_id":"1725729","funder_id":"https://openalex.org/F4320332222","funder_display_name":"University of Illinois at Urbana-Champaign"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320316786","display_name":"Center for Cognitive Computing Systems Research","ror":null},{"id":"https://openalex.org/F4320332222","display_name":"University of Illinois at Urbana-Champaign","ror":"https://ror.org/047426m28"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3174389038.pdf","grobid_xml":"https://content.openalex.org/works/W3174389038.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1947481528","https://openalex.org/W1982052956","https://openalex.org/W1997113918","https://openalex.org/W2094756095","https://openalex.org/W2107449576","https://openalex.org/W2194775991","https://openalex.org/W2276486856","https://openalex.org/W2294282016","https://openalex.org/W2585560244","https://openalex.org/W2585720638","https://openalex.org/W2585774018","https://openalex.org/W2625954420","https://openalex.org/W2627042741","https://openalex.org/W2727238169","https://openalex.org/W2761085955","https://openalex.org/W2762910930","https://openalex.org/W2885901248","https://openalex.org/W2887782013","https://openalex.org/W2889959382","https://openalex.org/W2896983500","https://openalex.org/W2899915146","https://openalex.org/W2900082550","https://openalex.org/W2917087921","https://openalex.org/W2962856739","https://openalex.org/W2964010167","https://openalex.org/W3012249773","https://openalex.org/W3016142271","https://openalex.org/W3047848469","https://openalex.org/W3091969046","https://openalex.org/W3092020069","https://openalex.org/W3112948415","https://openalex.org/W3115388607","https://openalex.org/W3130641740","https://openalex.org/W3132460984","https://openalex.org/W6675365184","https://openalex.org/W6763347759","https://openalex.org/W6767525790"],"related_works":["https://openalex.org/W2070693700","https://openalex.org/W2037960874","https://openalex.org/W2097839191","https://openalex.org/W2132107645","https://openalex.org/W3005710104","https://openalex.org/W3092334294","https://openalex.org/W3200538824","https://openalex.org/W2505126014","https://openalex.org/W2014496217","https://openalex.org/W3007361144"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network":[2,284],"(DNN)-based":[3],"video":[4,21,109,157,290],"analysis":[5,28,110],"has":[6,73],"become":[7],"one":[8,49,293],"of":[9,50,69,204,243],"the":[10,27,51,67,120,124,129,169,172,221,226,231,262,268,280,288,308,319],"most":[11],"essential":[12],"and":[13,34,37,58,71,83,92,96,128,148,171,180,200,224,235,238,255,264,291,303,313,322,333],"challenging":[14],"tasks":[15],"to":[16,87,101,145,175,278,318],"capture":[17],"implicit":[18],"information":[19],"from":[20,119,208],"streams.":[22],"Although":[23],"DNNs":[24],"significantly":[25],"improve":[26],"quality,":[29],"they":[30],"introduce":[31],"intensive":[32],"compute":[33],"memory":[35,165,258],"demands":[36],"require":[38],"dedicated":[39],"hardware":[40,206],"for":[41,77,155,261,267,296],"efficient":[42,177,257],"processing.":[43],"The":[44],"customized":[45,173,205],"heterogeneous":[46,65,153,233],"system":[47,234],"is":[48],"promising":[52],"solutions":[53,228],"with":[54,80,93,185,311],"general-purpose":[55],"processors":[56,60],"(CPUs)":[57],"specialized":[59],"(DNN":[61],"Accelerators).":[62],"Among":[63],"various":[64],"systems,":[66],"combination":[68],"CPU":[70,88,102,112,321],"FPGA":[72,114,324],"been":[74],"intensively":[75],"studied":[76],"DNN":[78,182,210],"inference":[79],"improved":[81],"latency":[82],"energy":[84],"consumption":[85],"compared":[86,100],"&#x002B;":[89,103,113],"GPU":[90],"schemes":[91],"increased":[94],"flexibility":[95],"reduced":[97,186],"time-to-market":[98],"cost":[99],"ASIC":[104],"designs.":[105],"However,":[106],"deploying":[107],"DNN-based":[108],"on":[111,151],"systems":[115,154],"still":[116],"presents":[117],"challenges":[118],"tedious":[121],"RTL":[122],"programming,":[123],"intricate":[125],"design":[126,131,193,198,214,222,260,276],"verification,":[127],"time-consuming":[130],"space":[132,166,215,223],"exploration.":[133],"To":[134],"address":[135],"these":[136],"challenges,":[137],"we":[138,273],"present":[139],"a":[140,163,213,240,247,250],"novel":[141],"framework,":[142],"called":[143],"EcoSys,":[144],"explore":[146],"co-design":[147],"optimization":[149],"opportunities":[150],"CPU-FPGA":[152],"accelerating":[156],"analysis.":[158],"Novel":[159],"technologies":[160],"include":[161],"1)":[162],"coherent":[164],"shared":[167],"by":[168,229,306],"host":[170],"accelerator":[174,263],"enable":[176],"task":[178],"partitioning":[179],"online":[181],"model":[183,310],"refinement":[184],"data":[187],"transfer":[188],"latency;":[189],"2)":[190],"an":[191,256],"end-to-end":[192],"flow":[194],"that":[195,219],"supports":[196],"high-level":[197],"abstraction":[199],"allows":[201],"rapid":[202],"development":[203],"accelerators":[207],"Python-based":[209],"descriptions;":[211],"3)":[212],"exploration":[216],"(DSE)":[217],"engine":[218],"determines":[220],"explores":[225],"optimized":[227],"considering":[230],"targeted":[232],"user-specific":[236],"constraints;":[237],"4)":[239],"complete":[241],"set":[242],"co-optimization":[244],"solutions,":[245],"including":[246],"layer-based":[248],"pipeline,":[249],"feature":[251],"map":[252],"partition":[253],"scheme,":[254],"hierarchical":[259],"multithreading":[265],"programming":[266],"CPU.":[269],"In":[270],"this":[271],"article,":[272],"demonstrate":[274],"our":[275],"framework":[277],"accelerate":[279],"long-term":[281],"recurrent":[282],"convolution":[283],"(LRCN),":[285],"which":[286],"analyzes":[287],"input":[289],"output":[292],"semantic":[294],"caption":[295],"each":[297],"frame.":[298],"EcoSys":[299,326],"can":[300],"deliver":[301],"314.7":[302],"58.1":[304],"frames/s":[305],"targeting":[307],"LRCN":[309],"AlexNet":[312],"VGG-16":[314],"backbone,":[315],"respectively.":[316],"Compared":[317],"multithreaded":[320],"pure":[323],"design,":[325],"achieves":[327],"<inline-formula>":[328,334],"<tex-math":[329,335],"notation=\"LaTeX\">$20.6\\times":[330],"$":[331,337],"</tex-math></inline-formula>":[332,338],"notation=\"LaTeX\">$5.3\\times":[336],"higher":[339],"throughput":[340],"performance.":[341]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}