{"id":"https://openalex.org/W4319870638","doi":"https://doi.org/10.1145/3543622.3573131","title":"A Flexible Toolflow for Mapping CNN Models to High Performance FPGA-based Accelerators","display_name":"A Flexible Toolflow for Mapping CNN Models to High Performance FPGA-based Accelerators","publication_year":2023,"publication_date":"2023-02-10","ids":{"openalex":"https://openalex.org/W4319870638","doi":"https://doi.org/10.1145/3543622.3573131"},"language":"en","primary_location":{"id":"doi:10.1145/3543622.3573131","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543622.3573131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"},"type":"conference-abstract","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/A5101754297","display_name":"Yongzheng Chen","orcid":"https://orcid.org/0000-0001-6947-8107"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongzheng Chen","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0001-6947-8107","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072969773","display_name":"Gang Wu","orcid":"https://orcid.org/0000-0002-9855-6300"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Wu","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-9855-6300","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"232","last_page":"232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9937999844551086,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9836999773979187,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8448916673660278},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7735432982444763},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6988077759742737},{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.6520640254020691},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6341831684112549},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6102879047393799},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.504397988319397},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4993293285369873},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47534748911857605},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.45576533675193787},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.44581955671310425},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.43254154920578003},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3761866092681885},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3727763295173645},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36870044469833374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25152236223220825},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.10218566656112671},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08654695749282837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8448916673660278},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7735432982444763},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6988077759742737},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.6520640254020691},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6341831684112549},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6102879047393799},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.504397988319397},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4993293285369873},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47534748911857605},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.45576533675193787},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.44581955671310425},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.43254154920578003},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3761866092681885},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3727763295173645},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36870044469833374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25152236223220825},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.10218566656112671},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08654695749282837},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3543622.3573131","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543622.3573131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4240320454","https://openalex.org/W2070314832","https://openalex.org/W2395557210","https://openalex.org/W2111241003","https://openalex.org/W2010232134","https://openalex.org/W2347854075","https://openalex.org/W2132614232","https://openalex.org/W4391183532","https://openalex.org/W2026533826","https://openalex.org/W4283703276"],"abstract_inverted_index":{"There":[0],"have":[1],"been":[2],"many":[3],"studies":[4],"on":[5,183],"developing":[6],"automatic":[7],"tools":[8],"for":[9,179],"mapping":[10],"CNN":[11,177],"models":[12,31,39,178],"onto":[13],"FPGAs.":[14],"However,":[15],"challenges":[16],"remain":[17],"in":[18],"designing":[19],"an":[20,210],"easy-to-use":[21],"toolflow.":[22],"First,":[23],"the":[24,44,82,93,102,111,144,154,162,189,202,231,243],"toolflow":[25,64,223],"should":[26,47],"be":[27],"able":[28],"to":[29,54,72,80,91,126,152,161,215],"handle":[30],"exported":[32],"from":[33],"various":[34],"deep":[35],"learning":[36],"frameworks":[37],"and":[38,104,119,147,157,174],"with":[40,169,219],"different":[41,74,170],"topologies.":[42],"Second,":[43],"hardware":[45],"architecture":[46],"make":[48],"better":[49,236],"use":[50],"of":[51,191,201,213,230,239],"on-chip":[52,117],"resources":[53],"achieve":[55,209],"high":[56],"performance.":[57],"In":[58],"this":[59],"work,":[60],"we":[61,132],"build":[62],"a":[63,134,149,184],"upon":[65],"Open":[66],"Neural":[67],"Network":[68],"Exchange":[69],"(ONNX)":[70],"IR":[71],"support":[73],"DL":[75],"frameworks.":[76],"We":[77,89,165,207],"also":[78,109,124,208,235],"try":[79],"maximize":[81],"overall":[83,211],"throughput":[84,204,212],"via":[85],"multiple":[86],"hardware-level":[87],"efforts.":[88],"propose":[90],"accelerate":[92],"convolution":[94,145],"operation":[95],"by":[96],"applying":[97],"parallelism":[98],"not":[99],"only":[100],"at":[101,110,140,242],"input":[103],"output":[105,112],"channel":[106],"level,":[107],"but":[108],"feature":[113,159],"map":[114],"level.":[115],"Several":[116],"buffers":[118],"corresponding":[120],"management":[121],"algorithms":[122],"are":[123],"designed":[125],"leverage":[127],"abundant":[128],"memory":[129],"resources.":[130],"Moreover,":[131],"employ":[133],"fully":[135],"pipelined":[136],"systolic":[137,163,171],"array":[138,172],"running":[139],"400":[141],"MHz":[142],"as":[143],"engine,":[146],"develop":[148],"dedicated":[150],"bus":[151],"implement":[153],"im2col":[155],"algorithm":[156],"provide":[158],"inputs":[160],"array.":[164],"generated":[166,232],"4":[167],"accelerators":[168,233],"shapes":[173],"compiled":[175],"12":[176],"each":[180],"accelerator.":[181],"Deployed":[182],"Xilinx":[185],"VCU118":[186],"evaluation":[187],"board,":[188],"performance":[190,229],"convolutional":[192],"layers":[193],"can":[194],"reach":[195],"3267.61":[196],"GOPS,":[197],"which":[198],"is":[199,224,234],"99.72%":[200],"ideal":[203],"(3276.8":[205],"GOPS).":[206],"up":[214],"2424.73":[216],"GOPS.":[217],"Compared":[218],"previous":[220],"studies,":[221],"our":[222],"more":[225],"user-friendly.":[226],"The":[227],"end-to-end":[228],"than":[237],"that":[238],"related":[240],"work":[241],"same":[244],"DSP":[245],"utilization.":[246]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}