{"id":"https://openalex.org/W2287513402","doi":"https://doi.org/10.1109/fpt.2015.7393159","title":"FPGA implementation of a SIMD-based array processor with torus interconnect","display_name":"FPGA implementation of a SIMD-based array processor with torus interconnect","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2287513402","doi":"https://doi.org/10.1109/fpt.2015.7393159","mag":"2287513402"},"language":"en","primary_location":{"id":"doi:10.1109/fpt.2015.7393159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpt.2015.7393159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on Field Programmable Technology (FPT)","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/A5085153505","display_name":"Yuki Murakami","orcid":"https://orcid.org/0009-0002-1220-7589"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuki Murakami","raw_affiliation_strings":["Graduate School of Computer Science and Engineering, University of Aizu"],"affiliations":[{"raw_affiliation_string":"Graduate School of Computer Science and Engineering, University of Aizu","institution_ids":["https://openalex.org/I141591182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5085153505"],"corresponding_institution_ids":["https://openalex.org/I141591182"],"apc_list":null,"apc_paid":null,"fwci":0.3682,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70145054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"244","last_page":"247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9988999962806702,"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":0.9988999962806702,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.9872999787330627,"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/flops","display_name":"FLOPS","score":0.8750351667404175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7868924140930176},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6476898193359375},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.6123923063278198},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5858114957809448},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5316660404205322},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.5064576864242554},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.47666600346565247},{"id":"https://openalex.org/keywords/interconnection","display_name":"Interconnection","score":0.46823328733444214},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.449796199798584},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3650578260421753},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25246554613113403}],"concepts":[{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.8750351667404175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7868924140930176},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6476898193359375},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.6123923063278198},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5858114957809448},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5316660404205322},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.5064576864242554},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47666600346565247},{"id":"https://openalex.org/C123745756","wikidata":"https://www.wikidata.org/wiki/Q1665949","display_name":"Interconnection","level":2,"score":0.46823328733444214},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.449796199798584},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3650578260421753},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25246554613113403},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fpt.2015.7393159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpt.2015.7393159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on Field Programmable Technology (FPT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1598993252","https://openalex.org/W1667652561","https://openalex.org/W2026883296","https://openalex.org/W2094756095","https://openalex.org/W2114508814","https://openalex.org/W2163605009","https://openalex.org/W2171839729","https://openalex.org/W2950769435","https://openalex.org/W4302296459","https://openalex.org/W6636003222","https://openalex.org/W6637151318","https://openalex.org/W6677192272","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W2079351402","https://openalex.org/W2565725308","https://openalex.org/W1970548269","https://openalex.org/W2560894929","https://openalex.org/W3091978438","https://openalex.org/W4226248541","https://openalex.org/W1861262881","https://openalex.org/W2156524298","https://openalex.org/W2380696053","https://openalex.org/W2588463123"],"abstract_inverted_index":{"Matrix":[0],"computations":[1,51],"are":[2,27],"a":[3,74,126],"fundamental":[4],"tool":[5],"in":[6],"scientific":[7],"and":[8,30,56,121,150],"engineering":[9],"applications.":[10],"Among":[11],"many":[12],"such":[13],"applications,":[14],"Convolutional":[15],"Neural":[16],"Networks":[17],"(CNN)":[18],"that":[19],"can":[20],"be":[21],"effectively":[22],"computed":[23],"by":[24],"matrix-matrix":[25,62],"multiplications":[26],"being":[28],"popular":[29],"an":[31,45],"efficient":[32],"implementation":[33],"of":[34,69,104],"CNN":[35,110],"is":[36,130,148,153],"highly":[37],"important.":[38],"In":[39],"this":[40],"study,":[41],"we":[42,57],"have":[43,65],"designed":[44,81],"parallel":[46],"processor":[47,72,82,141],"for":[48,61],"the":[49,67,70,80,117,135,140],"matrix":[50,118,136],"using":[52],"torus":[53],"interconnect":[54],"topology,":[55],"implemented":[58,109],"Cannon's":[59],"algorithm":[60],"multiply-add.":[63],"We":[64,107,115],"evaluated":[66,96],"scalability":[68],"proposed":[71,123],"on":[73,97,112],"reconfigurable":[75],"FPGA":[76,100],"platform.":[77],"More":[78],"precisely,":[79],"with":[83,89,102],"8":[84,86],"\u00d7":[85,155],"functional":[87,144],"units":[88],"16":[90],"bit":[91],"floating-point":[92],"multiply-add":[93],"unit":[94],"was":[95],"Cyclone":[98],"IV":[99],"chip,":[101],"performance":[103],"27":[105],"GFlops.":[106],"also":[108],"calculations":[111],"our":[113,122,128],"processor.":[114],"compared":[116],"based":[119,137],"approach":[120,138],"method.":[124],"As":[125],"result,":[127],"method":[129],"25":[131],"times":[132],"faster":[133],"than":[134],"if":[139],"has":[142],"8\u00d78":[143],"units,":[145],"image":[146],"size":[147,152],"32\u00d732":[149],"filter":[151],"5":[154],"5.":[156]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}