{"id":"https://openalex.org/W3025579719","doi":"https://doi.org/10.1109/access.2020.2994657","title":"A Scalable Architecture for Accelerating Multi-operation and Continuous Floating-point Matrix Computing on FPGAs","display_name":"A Scalable Architecture for Accelerating Multi-operation and Continuous Floating-point Matrix Computing on FPGAs","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3025579719","doi":"https://doi.org/10.1109/access.2020.2994657","mag":"3025579719"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.2994657","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2994657","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09093911.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09093911.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101503175","display_name":"Longlong Zhang","orcid":"https://orcid.org/0000-0002-0780-5683"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Longlong Zhang","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043043084","display_name":"Yuanxi Peng","orcid":"https://orcid.org/0000-0002-6647-8862"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanxi Peng","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010685789","display_name":"Ahui Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ahui Huang","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050750924","display_name":"Xiao Hu","orcid":"https://orcid.org/0000-0003-1128-4099"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Hu","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101503175"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.6931,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65824623,"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":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12162","display_name":"Cellular Automata and Applications","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/computer-science","display_name":"Computer science","score":0.7443089485168457},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6577696800231934},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.5511762499809265},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5425291061401367},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5236077904701233},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.513934314250946},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5058324337005615},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4942939281463623},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.432849645614624},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4325399398803711},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2721039056777954},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.27202725410461426},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10101279616355896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7443089485168457},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6577696800231934},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.5511762499809265},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5425291061401367},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5236077904701233},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.513934314250946},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5058324337005615},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4942939281463623},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.432849645614624},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4325399398803711},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2721039056777954},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.27202725410461426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10101279616355896},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.2994657","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2994657","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09093911.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:eef89e2c424a48c2b52237304a54fdcd","is_oa":true,"landing_page_url":"https://doaj.org/article/eef89e2c424a48c2b52237304a54fdcd","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 92469-92478 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.2994657","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2994657","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09093911.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5}],"awards":[],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3025579719.pdf","grobid_xml":"https://content.openalex.org/works/W3025579719.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1511216606","https://openalex.org/W1553214226","https://openalex.org/W1582059966","https://openalex.org/W1925692259","https://openalex.org/W1989881993","https://openalex.org/W2013281636","https://openalex.org/W2047268718","https://openalex.org/W2061624656","https://openalex.org/W2073510583","https://openalex.org/W2080275298","https://openalex.org/W2081874478","https://openalex.org/W2098279409","https://openalex.org/W2106111377","https://openalex.org/W2107356030","https://openalex.org/W2108308693","https://openalex.org/W2119560898","https://openalex.org/W2131316979","https://openalex.org/W2150773026","https://openalex.org/W2165376228","https://openalex.org/W2276069931","https://openalex.org/W2404540148","https://openalex.org/W2737762472","https://openalex.org/W2806371009","https://openalex.org/W2908586725","https://openalex.org/W2962882427","https://openalex.org/W2963140246","https://openalex.org/W4237611199","https://openalex.org/W4249774071","https://openalex.org/W6630990198"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W4206811032","https://openalex.org/W2995605830","https://openalex.org/W4239424132","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2086123442"],"abstract_inverted_index":{"Matrix":[0],"computing":[1,66,75,95,102,115,135,160],"is":[2,197],"a":[3,22,28,62,111,141,158,182],"basic":[4],"operational":[5],"model":[6],"that":[7,178],"was":[8],"broadly":[9],"used":[10,100],"in":[11,101,136,171,200],"science":[12],"and":[13,30,46,94,139,192,203],"engineering":[14,138,166],"applications.":[15],"In":[16],"this":[17],"study,":[18],"we":[19,60,109],"first":[20],"propose":[21,110],"novel":[23],"optimization":[24],"method":[25],"to":[26,81,156,164],"obtain":[27],"high-performance":[29],"scalable":[31],"architecture":[32,196],"for":[33],"matrix":[34,65,74,78,82,84,114,134,159],"multiplication,":[35,87],"including":[36],"reducing":[37],"data":[38,41,146],"transmission,":[39],"optimizing":[40],"flow,":[42],"improving":[43],"resource":[44],"utilization,":[45],"dynamically":[47],"changing":[48],"the":[49,52,57,71,122,130,149,152,172,179],"length":[50],"of":[51,73,105,125,132,144,185],"linear":[53],"array.":[54],"Based":[55],"on":[56],"optimized":[58],"architecture,":[59],"present":[61],"multi-operation":[63,126],"floating-point":[64,113],"unit":[67,116,154],"(design-I),":[68],"which":[69,118],"extends":[70],"function":[72,124],"from":[76],"single":[77],"multiplication":[79],"operation":[80],"addition,":[83],"subtraction,":[85],"matrix-vector":[86],"matrix-scalar":[88],"multiplication.":[89],"With":[90],"low":[91],"storage":[92],"demand":[93],"efficiency,":[96],"design-I":[97],"can":[98],"be":[99],"dense":[103],"matrices":[104],"arbitrary":[106],"sizes.":[107],"Moreover,":[108],"continuous":[112,133],"(design-II),":[117],"not":[119],"only":[120],"has":[121],"same":[123],"but":[127],"also":[128],"meets":[129],"requirement":[131],"practical":[137],"avoids":[140],"large":[142],"amount":[143],"intermediate":[145],"transfer.":[147],"Finally,":[148],"authors":[150],"adopt":[151],"above-mentioned":[153],"cores":[155],"build":[157],"acceleration":[161],"system":[162],"according":[163],"different":[165],"requirements.":[167],"The":[168,195],"experiments":[169],"implemented":[170],"Xilinx":[173],"585T":[174],"FPGA":[175],"device":[176],"show":[177],"accelerator":[180],"achieves":[181],"maximum":[183],"frequency":[184],"195Mhz":[186],"with":[187,206],"256":[188],"processing":[189],"elements":[190],"(PEs)":[191],"performs":[193],"99.8GFLOPS.":[194],"more":[198],"outstanding":[199],"application":[201],"scope":[202],"prospects":[204],"compared":[205],"state-of-the-art":[207],"methods.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
