{"id":"https://openalex.org/W3114514344","doi":"https://doi.org/10.1109/icecs49266.2020.9294850","title":"A High-Performance and Power-Efficient SIMD Convolution Engine for FPGAs","display_name":"A High-Performance and Power-Efficient SIMD Convolution Engine for FPGAs","publication_year":2020,"publication_date":"2020-11-23","ids":{"openalex":"https://openalex.org/W3114514344","doi":"https://doi.org/10.1109/icecs49266.2020.9294850","mag":"3114514344"},"language":"en","primary_location":{"id":"doi:10.1109/icecs49266.2020.9294850","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icecs49266.2020.9294850","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 27th IEEE International Conference on Electronics, Circuits and Systems (ICECS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5035230230","display_name":"Fanny Spagnolo","orcid":"https://orcid.org/0000-0002-2197-4563"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanny Spagnolo","raw_affiliation_strings":["Department of Informatics, Modeling, Electronics and System Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Modeling, Electronics and System Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011214102","display_name":"Fabio Frustaci","orcid":"https://orcid.org/0000-0001-5795-4321"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabio Frustaci","raw_affiliation_strings":["Department of Informatics, Modeling, Electronics and System Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Modeling, Electronics and System Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074662921","display_name":"Stefania Perri","orcid":"https://orcid.org/0000-0003-1363-9201"},"institutions":[{"id":"https://openalex.org/I45204951","display_name":"University of Calabria","ror":"https://ror.org/02rc97e94","country_code":"IT","type":"education","lineage":["https://openalex.org/I45204951"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stefania Perri","raw_affiliation_strings":["Department of Mechanical, Energy and Management Engineering, University of Calabria, Arcavacata di Rende, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical, Energy and Management Engineering, University of Calabria, Arcavacata di Rende, Italy","institution_ids":["https://openalex.org/I45204951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003003043","display_name":"Pasquale Corsonello","orcid":"https://orcid.org/0000-0002-9528-1110"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pasquale Corsonello","raw_affiliation_strings":["Department of Informatics, Modeling, Electronics and System Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Modeling, Electronics and System Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10741","display_name":"Video Coding and Compression Technologies","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9991000294685364,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9987999796867371,"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":0.8270256519317627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7529577016830444},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6509376168251038},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.6314358711242676},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.49267107248306274},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.48055532574653625},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.47004976868629456},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4662104547023773},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.4654444456100464},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4634074866771698},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32147207856178284},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09840545058250427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09463831782341003}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8270256519317627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7529577016830444},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6509376168251038},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.6314358711242676},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.49267107248306274},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.48055532574653625},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47004976868629456},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4662104547023773},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.4654444456100464},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4634074866771698},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32147207856178284},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09840545058250427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09463831782341003},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icecs49266.2020.9294850","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icecs49266.2020.9294850","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 27th IEEE International Conference on Electronics, Circuits and Systems (ICECS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8999999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2068395868","https://openalex.org/W2747705082","https://openalex.org/W2795961274","https://openalex.org/W2884002000","https://openalex.org/W2908001587","https://openalex.org/W2913497278","https://openalex.org/W2946355854","https://openalex.org/W6758031559"],"related_works":["https://openalex.org/W1876592433","https://openalex.org/W2083269738","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/W3008689640","https://openalex.org/W4385338604"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,23,72],"power-efficient":[4],"hardware":[5,47],"architecture":[6],"designed":[7],"to":[8,28,38,112],"perform":[9],"3D":[10],"convolution":[11,69,108],"operations":[12],"in":[13,101],"modern":[14],"high-performance":[15],"FPGA-based":[16],"video":[17],"processors.":[18],"The":[19],"proposed":[20,68,107],"design":[21],"exploits":[22],"novel":[24],"platform-independent":[25],"Single-Instruction-Multiple-Data":[26],"modality":[27],"process":[29],"input":[30],"data,":[31],"thus":[32],"allowing":[33],"multiple":[34],"levels":[35],"of":[36,43],"parallelism":[37],"be":[39],"supported.":[40],"For":[41],"purposes":[42],"comparison":[44],"with":[45],"existing":[46,118],"accelerators,":[48],"several":[49],"implementations":[50],"are":[51,96],"characterized":[52],"using":[53],"different":[54],"FPGA":[55,104],"devices.":[56],"When":[57,91],"accommodated":[58],"within":[59],"low-end":[60],"chips,":[61],"such":[62],"as":[63],"the":[64,67,82,87,106],"Xilinx":[65,102],"XC7Z020,":[66],"engine":[70,109],"exhibits":[71],"maximum":[73],"clock":[74],"frequency":[75],"22":[76],"<sup":[77],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[78],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">%</sup>":[79],"higher":[80],"than":[81,117],"competitors,":[83],"without":[84,120],"significantly":[85],"increasing":[86],"dynamic":[88,115],"energy":[89,116],"consumption.":[90],"more":[92],"advanced":[93],"DSP":[94],"slices":[95],"used,":[97],"like":[98],"those":[99],"available":[100],"Ultrascale":[103],"devices":[105],"dissipates":[110],"up":[111],"40%":[113],"less":[114],"counterparts,":[119],"significant":[121],"speed":[122],"performance":[123],"penalties.":[124]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}