{"id":"https://openalex.org/W4312121156","doi":"https://doi.org/10.1145/3508352.3549402","title":"Deep Learning Toolkit-Accelerated Analytical Co-Optimization of CNN Hardware and Dataflow","display_name":"Deep Learning Toolkit-Accelerated Analytical Co-Optimization of CNN Hardware and Dataflow","publication_year":2022,"publication_date":"2022-10-30","ids":{"openalex":"https://openalex.org/W4312121156","doi":"https://doi.org/10.1145/3508352.3549402"},"language":"en","primary_location":{"id":"doi:10.1145/3508352.3549402","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3508352.3549402","pdf_url":null,"source":{"id":"https://openalex.org/S4363608844","display_name":"Proceedings of the 41st IEEE/ACM International Conference on Computer-Aided Design","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st IEEE/ACM International Conference on Computer-Aided Design","raw_type":"proceedings-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/A5013528664","display_name":"Rongjian Liang","orcid":"https://orcid.org/0000-0001-8626-2359"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongjian Liang","raw_affiliation_strings":["Nvdia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvdia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057494448","display_name":"Jianfeng Song","orcid":"https://orcid.org/0000-0002-7641-2170"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianfeng Song","raw_affiliation_strings":["Texas A&M University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University","institution_ids":[]}]},{"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/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yuan Bo","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103246390","display_name":"Jiang Hu","orcid":"https://orcid.org/0000-0003-1157-7799"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang Hu","raw_affiliation_strings":["Texas A&M University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.118,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.43193754,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9988999962806702,"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":0.9973999857902527,"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/dataflow","display_name":"Dataflow","score":0.8882738351821899},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.814349889755249},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6016015410423279},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.5859540104866028},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.547709047794342},{"id":"https://openalex.org/keywords/dataflow-architecture","display_name":"Dataflow architecture","score":0.4724714457988739},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.46948108077049255},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.46563899517059326},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4554455280303955},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.4383857846260071},{"id":"https://openalex.org/keywords/automatic-differentiation","display_name":"Automatic differentiation","score":0.428216814994812},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4230915904045105},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.41704726219177246},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35359451174736023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3388834595680237},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.3374297618865967},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32691389322280884},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.11608994007110596}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8882738351821899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.814349889755249},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6016015410423279},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.5859540104866028},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.547709047794342},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.4724714457988739},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.46948108077049255},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.46563899517059326},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4554455280303955},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.4383857846260071},{"id":"https://openalex.org/C133512626","wikidata":"https://www.wikidata.org/wiki/Q787371","display_name":"Automatic differentiation","level":3,"score":0.428216814994812},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4230915904045105},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.41704726219177246},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35359451174736023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3388834595680237},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3374297618865967},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32691389322280884},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.11608994007110596},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3508352.3549402","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3508352.3549402","pdf_url":null,"source":{"id":"https://openalex.org/S4363608844","display_name":"Proceedings of the 41st IEEE/ACM International Conference on Computer-Aided Design","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st IEEE/ACM International Conference on Computer-Aided Design","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G2931540501","display_name":null,"funder_award_id":"CCF-1955909, CMMI-2038625, 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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2143518405","https://openalex.org/W2184060865","https://openalex.org/W2289252105","https://openalex.org/W2606722458","https://openalex.org/W2991044292","https://openalex.org/W3036696276","https://openalex.org/W3045337512","https://openalex.org/W4205146836","https://openalex.org/W4236269344","https://openalex.org/W4244024631","https://openalex.org/W4245185858","https://openalex.org/W4288083528"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3042858012","https://openalex.org/W2742479298","https://openalex.org/W4310520567","https://openalex.org/W2996372837","https://openalex.org/W4310997605","https://openalex.org/W1741246166","https://openalex.org/W4220813584","https://openalex.org/W2704801810"],"abstract_inverted_index":{"The":[0,165],"continuous":[1],"growth":[2],"of":[3,91,108,129,137,161,169,215],"CNN":[4,26,92],"complexity":[5],"not":[6],"only":[7],"intensifies":[8],"the":[9,22,36,127,143],"need":[10],"for":[11,25,64,86,133],"hardware":[12,27,93],"acceleration":[13],"but":[14],"also":[15],"presents":[16],"a":[17,44,104,158,211],"huge":[18],"challenge.":[19],"That":[20],"is,":[21],"solution":[23],"space":[24],"design":[28,94],"and":[29,42,78,89,95,111,140,163,200],"dataflow":[30,96],"mapping":[31],"becomes":[32],"enormously":[33],"large":[34,66],"besides":[35],"fact":[37],"that":[38],"it":[39,209],"is":[40,121,175],"discrete":[41],"lacks":[43],"well":[45],"behaved":[46],"structure.":[47],"Most":[48],"previous":[49],"works":[50],"either":[51],"are":[52,60],"stochastic":[53],"metaheuristics,":[54],"such":[55],"as":[56,176,178],"genetic":[57],"algorithm,":[58],"which":[59,125],"typically":[61],"very":[62],"slow":[63],"solving":[65],"problems,":[67],"or":[68],"rely":[69],"on":[70,99,205],"expensive":[71],"sampling,":[72],"e.g.,":[73],"Gumbel":[74],"Softmax-based":[75],"differentiable":[76],"optimization":[77,216],"Bayesian":[79],"optimization.":[80,144],"We":[81],"propose":[82],"an":[83],"analytical":[84],"model":[85,120,171],"evaluating":[87],"power":[88,162,198],"performance":[90],"solutions.":[97],"Based":[98],"this":[100,119],"model,":[101],"we":[102],"introduce":[103],"co-optimization":[105],"method":[106,150],"consisting":[107],"nonlinear":[109],"programming":[110],"parallel":[112],"local":[113],"search.":[114],"A":[115],"key":[116],"innovation":[117],"in":[118,142],"its":[122],"matrix":[123],"form,":[124],"enables":[126],"use":[128],"deep":[130],"learning":[131],"toolkit":[132],"highly":[134],"efficient":[135],"computations":[136],"power/performance":[138],"values":[139],"gradients":[141],"In":[145],"handling":[146],"power-performance":[147],"tradeoff,":[148],"our":[149,170,184],"can":[151],"lead":[152],"to":[153,181,190],"better":[154],"solutions":[155,187],"than":[156],"minimizing":[157],"weighted":[159],"sum":[160],"latency.":[164],"average":[166],"relative":[167],"error":[168],"compared":[172],"with":[173,188],"Timeloop":[174],"small":[177],"1%.":[179],"Compared":[180],"state-of-the-art":[182],"methods,":[183],"approach":[185],"achieves":[186],"up":[189],"1.7":[191],"\u00d7":[192,202,213],"shorter":[193],"inference":[194],"latency,":[195],"37.5%":[196],"less":[197,203],"consumption,":[199],"3":[201],"area":[204],"ResNet":[206],"18.":[207],"Moreover,":[208],"provides":[210],"6.2":[212],"speedup":[214],"runtime.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}