{"id":"https://openalex.org/W4316660865","doi":"https://doi.org/10.1109/tvlsi.2023.3235776","title":"Area-Efficient Parallel Multiplication Units for CNN Accelerators With Output Channel Parallelization","display_name":"Area-Efficient Parallel Multiplication Units for CNN Accelerators With Output Channel Parallelization","publication_year":2023,"publication_date":"2023-01-16","ids":{"openalex":"https://openalex.org/W4316660865","doi":"https://doi.org/10.1109/tvlsi.2023.3235776"},"language":"en","primary_location":{"id":"doi:10.1109/tvlsi.2023.3235776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2023.3235776","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","raw_type":"journal-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/A5074022780","display_name":"Song-Nien Tang","orcid":"https://orcid.org/0000-0002-7969-9015"},"institutions":[{"id":"https://openalex.org/I151221077","display_name":"Chung Yuan Christian University","ror":"https://ror.org/02w8ws377","country_code":"TW","type":"education","lineage":["https://openalex.org/I151221077"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Song-Nien Tang","raw_affiliation_strings":["Department of Information and Computer Engineering, Chung Yuan Christian University, Taoyuan City, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-7969-9015","affiliations":[{"raw_affiliation_string":"Department of Information and Computer Engineering, Chung Yuan Christian University, Taoyuan City, Taiwan","institution_ids":["https://openalex.org/I151221077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5074022780"],"corresponding_institution_ids":["https://openalex.org/I151221077"],"apc_list":null,"apc_paid":null,"fwci":1.4053,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.80558028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"31","issue":"3","first_page":"406","last_page":"410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9984999895095825,"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":0.7505552768707275},{"id":"https://openalex.org/keywords/adder","display_name":"Adder","score":0.6385868191719055},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.613162100315094},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6031432151794434},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5994929075241089},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5583961009979248},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4948226809501648},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.46221819519996643},{"id":"https://openalex.org/keywords/gate-array","display_name":"Gate array","score":0.454343318939209},{"id":"https://openalex.org/keywords/critical-path-method","display_name":"Critical path method","score":0.41598644852638245},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.40053343772888184},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35306018590927124},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13449203968048096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11042240262031555},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09709495306015015}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505552768707275},{"id":"https://openalex.org/C164620267","wikidata":"https://www.wikidata.org/wiki/Q376953","display_name":"Adder","level":3,"score":0.6385868191719055},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.613162100315094},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6031432151794434},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5994929075241089},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5583961009979248},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4948226809501648},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.46221819519996643},{"id":"https://openalex.org/C114237110","wikidata":"https://www.wikidata.org/wiki/Q114901","display_name":"Gate array","level":3,"score":0.454343318939209},{"id":"https://openalex.org/C115874739","wikidata":"https://www.wikidata.org/wiki/Q825377","display_name":"Critical path method","level":2,"score":0.41598644852638245},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.40053343772888184},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35306018590927124},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13449203968048096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11042240262031555},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09709495306015015},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvlsi.2023.3235776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2023.3235776","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2119144962","https://openalex.org/W2260498192","https://openalex.org/W2308155233","https://openalex.org/W2595614461","https://openalex.org/W2604814848","https://openalex.org/W2616014673","https://openalex.org/W2734572653","https://openalex.org/W2795915628","https://openalex.org/W2796659423","https://openalex.org/W2913497278","https://openalex.org/W2963526839","https://openalex.org/W2965976751","https://openalex.org/W3041601967","https://openalex.org/W4205798965","https://openalex.org/W6677580257","https://openalex.org/W6734868079","https://openalex.org/W6750097528"],"related_works":["https://openalex.org/W1002902646","https://openalex.org/W2524802307","https://openalex.org/W2466675884","https://openalex.org/W2951390974","https://openalex.org/W2997828269","https://openalex.org/W2503642292","https://openalex.org/W2047588290","https://openalex.org/W2320205417","https://openalex.org/W2046530291","https://openalex.org/W2097184210"],"abstract_inverted_index":{"Many":[0],"existing":[1],"studies":[2],"on":[3,34],"accelerating":[4],"convolutional":[5],"neural":[6],"networks":[7],"(CNNs)":[8],"use":[9],"parallel":[10,22,43],"data":[11],"operation":[12],"schemes":[13],"to":[14,79,86,90,136],"increase":[15],"the":[16,35,69,103,128,138],"throughput.":[17],"This":[18],"study":[19],"proposes":[20],"area-efficient":[21],"multiplication":[23],"unit":[24],"(PMU)":[25],"designs":[26,58,73,100],"for":[27,61,82,110],"a":[28,39,45,119],"CNN":[29,40,52,139],"accelerator":[30],"that":[31],"uses":[32],"parallelization":[33],"output":[36],"channels":[37],"of":[38,106],"layer,":[41],"which":[42],"multiplies":[44],"common":[46],"feature":[47],"map":[48],"pixel":[49],"with":[50,63,76],"multiple":[51],"kernel":[53],"weights.":[54,67],"First,":[55],"tailored":[56],"PMU":[57,72,99,124],"are":[59,74],"proposed":[60,70],"CNNs":[62],"specific":[64],"low-precision":[65],"3-to-8-bit":[66],"Second,":[68],"5-to-8-bit":[71],"extended":[75],"two-clock-cycle":[77],"operations":[78],"develop":[80],"PMUs":[81,92],"weight":[83,123],"precision":[84],"scalable":[85],"10/12/14/16":[87],"bits.":[88],"Compared":[89],"16-path":[91,121],"directly":[93],"using":[94],"carry-save-adder":[95],"array":[96,133],"multipliers,":[97],"our":[98],"can":[101],"achieve":[102],"area":[104],"reductions":[105],"28.19%\u221256.09%":[107],"and":[108,113],"22.10%\u221230.71%":[109],"3\u20138":[111],"bit":[112],"10-/12-/14-/":[114],"16-bit":[115,122],"weights,":[116],"respectively.":[117],"Moreover,":[118],"resultant":[120],"is":[125],"verified":[126],"through":[127],"system-on-chip":[129],"(SoC)":[130],"field-programmable":[131],"gate":[132],"(FPGA)":[134],"implementation":[135],"demonstrate":[137],"inference.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}