{"id":"https://openalex.org/W3007907555","doi":"https://doi.org/10.1145/3373087.3375366","title":"Maximizing CNN Throughput on FPGA Clusters","display_name":"Maximizing CNN Throughput on FPGA Clusters","publication_year":2020,"publication_date":"2020-02-23","ids":{"openalex":"https://openalex.org/W3007907555","doi":"https://doi.org/10.1145/3373087.3375366","mag":"3007907555"},"language":"en","primary_location":{"id":"doi:10.1145/3373087.3375366","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3373087.3375366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","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/A5101477549","display_name":"Ruihao Li","orcid":"https://orcid.org/0000-0002-7092-2401"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruihao Li","raw_affiliation_strings":["Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349872","display_name":"Ke Liu","orcid":"https://orcid.org/0000-0003-4151-1416"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Liu","raw_affiliation_strings":["Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061455216","display_name":"Mengying Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengying Zhao","raw_affiliation_strings":["Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019614582","display_name":"Zhaoyan Shen","orcid":"https://orcid.org/0000-0003-1336-8894"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoyan Shen","raw_affiliation_strings":["Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103199799","display_name":"Xiaojun Cai","orcid":"https://orcid.org/0000-0003-1586-375X"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Cai","raw_affiliation_strings":["Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043326110","display_name":"Zhiping Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiping Jia","raw_affiliation_strings":["Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101477549"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":0.0977,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3591786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"319","last_page":"319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9983999729156494,"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":0.9983999729156494,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9830999970436096,"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8905843496322632},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7890858054161072},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.7855926752090454},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6391780376434326},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5084018111228943},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.48168739676475525},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4530656933784485},{"id":"https://openalex.org/keywords/knapsack-problem","display_name":"Knapsack problem","score":0.4122050106525421},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4088480472564697},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4054115116596222},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3690108060836792},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.3603024482727051},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3508967161178589},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3060606122016907},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26202392578125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16399186849594116},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1336107850074768},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.13246402144432068},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09119817614555359},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0804862380027771}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8905843496322632},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7890858054161072},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.7855926752090454},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6391780376434326},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5084018111228943},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.48168739676475525},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4530656933784485},{"id":"https://openalex.org/C113138325","wikidata":"https://www.wikidata.org/wiki/Q864457","display_name":"Knapsack problem","level":2,"score":0.4122050106525421},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4088480472564697},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4054115116596222},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3690108060836792},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.3603024482727051},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3508967161178589},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3060606122016907},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26202392578125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16399186849594116},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1336107850074768},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.13246402144432068},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09119817614555359},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0804862380027771},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3373087.3375366","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3373087.3375366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8799999952316284,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W241127407","https://openalex.org/W2381035939","https://openalex.org/W3034421924","https://openalex.org/W2982536526","https://openalex.org/W4386858688","https://openalex.org/W4380302312","https://openalex.org/W3008689640","https://openalex.org/W4385338604","https://openalex.org/W3081626085","https://openalex.org/W4391382578"],"abstract_inverted_index":{"Field":[0],"Programmable":[1],"Gate":[2],"Array":[3],"(FPGA)":[4],"platform":[5],"has":[6],"been":[7],"a":[8,18,36,97,147],"popular":[9],"choice":[10],"for":[11,112,118],"deploying":[12,119],"Convolutional":[13],"Neural":[14],"Networks":[15],"(CNNs)":[16],"as":[17],"result":[19],"of":[20,32,48,90,100,142],"its":[21],"high":[22],"parallelism":[23],"and":[24,64,75,82,123,155],"low":[25],"energy":[26],"consumption.":[27],"Due":[28],"to":[29,44,58,85],"the":[30,46,60,71,87,91,101,139],"limitation":[31],"on-chip":[33],"resources":[34],"on":[35,79],"single":[37],"board,":[38],"FPGA":[39,66,92,143],"clusters":[40,144],"become":[41],"promising":[42],"solutions":[43,117,154],"improve":[45],"throughput":[47,149],"CNNs.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,69,115],"firstly":[54],"put":[55],"forward":[56],"strategies":[57],"optimize":[59],"resource":[61],"allocation":[62],"intra":[63],"inter":[65],"boards.":[67],"Then":[68],"model":[70],"multi-board":[72,157],"cluster":[73],"problem":[74,81],"design":[76,110],"algorithms":[77],"based":[78],"knapsack":[80],"dynamic":[83],"programming":[84],"calculate":[86],"optimal":[88],"topology":[89,141],"clusters.":[93],"We":[94],"also":[95],"give":[96],"quantitative":[98],"analysis":[99],"inter-board":[102],"data":[103],"transmission":[104],"bandwidth":[105],"requirement.":[106,130],"To":[107],"make":[108],"our":[109],"accommodate":[111],"more":[113],"situations,":[114],"provide":[116],"fully":[120],"connected":[121],"layers":[122,126],"special":[124],"convolution":[125],"with":[127,138],"large":[128],"memory":[129],"Experimental":[131],"results":[132],"show":[133],"that":[134],"typical":[135],"well-known":[136],"CNNs":[137],"proposed":[140],"could":[145],"obtain":[146],"higher":[148],"per":[150],"board":[151],"than":[152],"single-board":[153],"other":[156],"solutions.":[158]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}