{"id":"https://openalex.org/W4313484872","doi":"https://doi.org/10.1109/dsd57027.2022.00050","title":"An FPGA based Tiled Systolic Array Generator to Accelerate CNNs","display_name":"An FPGA based Tiled Systolic Array Generator to Accelerate CNNs","publication_year":2022,"publication_date":"2022-08-01","ids":{"openalex":"https://openalex.org/W4313484872","doi":"https://doi.org/10.1109/dsd57027.2022.00050"},"language":"en","primary_location":{"id":"doi:10.1109/dsd57027.2022.00050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsd57027.2022.00050","pdf_url":null,"source":{"id":"https://openalex.org/S4363608375","display_name":"2022 25th Euromicro Conference on Digital System Design (DSD)","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":"2022 25th Euromicro Conference on Digital System Design (DSD)","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/A5029853349","display_name":"Veerendra S. Devaraddi","orcid":null},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Veerendra S Devaraddi","raw_affiliation_strings":["International Institute of Information Technology Bangalore,India","International Institute of Information Technology Bangalore, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Bangalore,India","institution_ids":["https://openalex.org/I181514455"]},{"raw_affiliation_string":"International Institute of Information Technology Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101502774","display_name":"Nanditha Rao","orcid":"https://orcid.org/0000-0003-2369-0836"},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nanditha Rao","raw_affiliation_strings":["International Institute of Information Technology Bangalore,India","International Institute of Information Technology Bangalore, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Bangalore,India","institution_ids":["https://openalex.org/I181514455"]},{"raw_affiliation_string":"International Institute of Information Technology Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029853349"],"corresponding_institution_ids":["https://openalex.org/I181514455"],"apc_list":null,"apc_paid":null,"fwci":0.3612,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.68722373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"316","last_page":"323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9955999851226807,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9905999898910522,"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7825443744659424},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7793561220169067},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.7310640215873718},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6824119091033936},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.5852065086364746},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5653451085090637},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5188959240913391},{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.49931836128234863},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.45968908071517944},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.39987778663635254},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3015560507774353},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.297305166721344},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.17939293384552002},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14360424876213074},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.11173543334007263},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09448772668838501}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7825443744659424},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7793561220169067},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7310640215873718},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6824119091033936},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.5852065086364746},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5653451085090637},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5188959240913391},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.49931836128234863},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.45968908071517944},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.39987778663635254},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3015560507774353},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.297305166721344},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.17939293384552002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14360424876213074},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.11173543334007263},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09448772668838501},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsd57027.2022.00050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsd57027.2022.00050","pdf_url":null,"source":{"id":"https://openalex.org/S4363608375","display_name":"2022 25th Euromicro Conference on Digital System Design (DSD)","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":"2022 25th Euromicro Conference on Digital System Design (DSD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.7599999904632568,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2094756095","https://openalex.org/W2466675884","https://openalex.org/W2525740295","https://openalex.org/W2625954420","https://openalex.org/W2742152118","https://openalex.org/W2764337919","https://openalex.org/W2805473054","https://openalex.org/W2936278485","https://openalex.org/W2945146780","https://openalex.org/W2973770306","https://openalex.org/W2977634443","https://openalex.org/W2989762710","https://openalex.org/W3012178976","https://openalex.org/W3031172388","https://openalex.org/W4249932213"],"related_works":["https://openalex.org/W1876592433","https://openalex.org/W2083269738","https://openalex.org/W2347854075","https://openalex.org/W2169963286","https://openalex.org/W2021406864","https://openalex.org/W3034421924","https://openalex.org/W2982536526","https://openalex.org/W4386858688","https://openalex.org/W4380302312","https://openalex.org/W2132614232"],"abstract_inverted_index":{"The":[0],"main":[1],"computation":[2,10],"in":[3],"any":[4],"CNN":[5,31],"is":[6],"convolution":[7,49,55,79,105,147,161],"operation.":[8,50],"This":[9],"shows":[11],"significant":[12],"potential":[13],"for":[14,30,44],"massively":[15],"parallel":[16,178],"implementations":[17],"on":[18,116],"an":[19,53],"FPGA.":[20,183],"Systolic":[21],"arrays":[22],"with":[23,59,77],"their":[24],"intrinsic":[25],"pipelining":[26],"have":[27],"been":[28],"explored":[29],"inference.":[32],"In":[33],"this":[34,167],"paper,":[35],"we":[36,124],"present":[37],"a":[38,45,170],"systolic":[39,172],"array":[40],"architecture":[41,101,173],"suitably":[42],"designed":[43],"novel":[46],"method":[47,106],"of":[48,181],"We":[51,72,84,96,157,165],"implement":[52],"image-kernel":[54],"and":[56,70,80,107,113,132],"test":[57],"it":[58],"representative":[60],"image":[61],"inputs":[62],"to":[63,88,128],"several":[64],"models":[65],"like":[66],"LeNet-5,":[67],"AlexNet,":[68],"VGG-16,":[69],"Resnet-34.":[71],"compare":[73],"the":[74,99,103,134,153,160,177,182],"proposed":[75,100],"design":[76],"conventional":[78],"HLS":[81,108,154],"based":[82],"designs.":[83],"limit":[85],"our":[86,126,138],"implementation":[87,127,139],"resource":[89],"constrained":[90],"FPGA:":[91],"AMD-Xilinx":[92],"Zynq":[93],"7020":[94],"platform.":[95],"observe":[97],"that":[98,174],"outperforms":[102],"direct":[104],"pipelined":[109,155],"designs":[110],"by":[111,163,168],"2\u00d7":[112],"2.1\u00d7,":[114],"respectively,":[115],"average.":[117],"Since":[118],"DSP":[119,130],"blocks":[120,131],"are":[121],"scarce":[122],"resources,":[123],"constrain":[125],"avoid":[129],"use":[133],"LUTs":[135,144,151],"instead.":[136],"Thus,":[137],"uses":[140],"nearly":[141],"9\u00d7":[142],"more":[143],"than":[145,152],"baseline":[146],"but":[148],"8\u00d7":[149],"fewer":[150],"implementation.":[156],"further":[158],"accelerate":[159],"throughput":[162],"11\u00d7.":[164],"achieve":[166],"implementing":[169],"tiled":[171],"completely":[175],"utilises":[176],"computing":[179],"resources":[180]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"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"}