{"id":"https://openalex.org/W4387250389","doi":"https://doi.org/10.1109/jssc.2023.3312615","title":"Multipurpose Deep-Learning Accelerator for Arbitrary Quantization With Reduction of Storage, Logic, and Latency Waste","display_name":"Multipurpose Deep-Learning Accelerator for Arbitrary Quantization With Reduction of Storage, Logic, and Latency Waste","publication_year":2023,"publication_date":"2023-10-02","ids":{"openalex":"https://openalex.org/W4387250389","doi":"https://doi.org/10.1109/jssc.2023.3312615"},"language":"en","primary_location":{"id":"doi:10.1109/jssc.2023.3312615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jssc.2023.3312615","pdf_url":null,"source":{"id":"https://openalex.org/S83637746","display_name":"IEEE Journal of Solid-State Circuits","issn_l":"0018-9200","issn":["0018-9200","1558-173X"],"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 Journal of Solid-State Circuits","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/A5042758402","display_name":"Seunghyun Moon","orcid":"https://orcid.org/0000-0003-0027-2666"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seunghyun Moon","raw_affiliation_strings":["Institute of Artificial Intelligence, Pohang University of Science and Technology, Pohang, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-0027-2666","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Pohang University of Science and Technology, Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133767555","display_name":"Han-Gyeol Mun","orcid":"https://orcid.org/0000-0002-8532-1385"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Han-Gyeol Mun","raw_affiliation_strings":["department of Electrical Engineering, Pohang University of Science and Technology, Pohang, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8532-1385","affiliations":[{"raw_affiliation_string":"department of Electrical Engineering, Pohang University of Science and Technology, Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027088400","display_name":"Hyunwoo Son","orcid":"https://orcid.org/0000-0002-9833-1718"},"institutions":[{"id":"https://openalex.org/I189442560","display_name":"Gyeongsang National University","ror":"https://ror.org/00saywf64","country_code":"KR","type":"education","lineage":["https://openalex.org/I189442560"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunwoo Son","raw_affiliation_strings":["department of Electronic Engineering, Gyeongsang National University, Jinju, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-9833-1718","affiliations":[{"raw_affiliation_string":"department of Electronic Engineering, Gyeongsang National University, Jinju, South Korea","institution_ids":["https://openalex.org/I189442560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033088278","display_name":"Jae\u2010Yoon Sim","orcid":"https://orcid.org/0000-0003-1814-6211"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jae-Yoon Sim","raw_affiliation_strings":["department of Electrical Engineering, Pohang University of Science and Technology, Pohang, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-1814-6211","affiliations":[{"raw_affiliation_string":"department of Electrical Engineering, Pohang University of Science and Technology, Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.17,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.81082682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"59","issue":"1","first_page":"143","last_page":"156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9700999855995178,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9700999855995178,"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":0.9585000276565552,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9319999814033508,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7281869053840637},{"id":"https://openalex.org/keywords/lookup-table","display_name":"Lookup table","score":0.6976590156555176},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5942716598510742},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48114216327667236},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45935821533203125},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.44171229004859924},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.4315694570541382},{"id":"https://openalex.org/keywords/control-reconfiguration","display_name":"Control reconfiguration","score":0.4307800531387329},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.41754698753356934},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.41135403513908386},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.379641592502594},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3504018783569336},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.23769202828407288},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19935396313667297},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.1520758867263794}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7281869053840637},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.6976590156555176},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5942716598510742},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48114216327667236},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45935821533203125},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.44171229004859924},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.4315694570541382},{"id":"https://openalex.org/C119701452","wikidata":"https://www.wikidata.org/wiki/Q5165881","display_name":"Control reconfiguration","level":2,"score":0.4307800531387329},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.41754698753356934},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.41135403513908386},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.379641592502594},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3504018783569336},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.23769202828407288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19935396313667297},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.1520758867263794},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/jssc.2023.3312615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jssc.2023.3312615","pdf_url":null,"source":{"id":"https://openalex.org/S83637746","display_name":"IEEE Journal of Solid-State Circuits","issn_l":"0018-9200","issn":["0018-9200","1558-173X"],"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 Journal of Solid-State Circuits","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2002555321","https://openalex.org/W2194775991","https://openalex.org/W2291160084","https://openalex.org/W2604319603","https://openalex.org/W2748818695","https://openalex.org/W2786771851","https://openalex.org/W2894696827","https://openalex.org/W2895531329","https://openalex.org/W2897083155","https://openalex.org/W2915589364","https://openalex.org/W2955425717","https://openalex.org/W2963480671","https://openalex.org/W2964133305","https://openalex.org/W3015391117","https://openalex.org/W3110533210","https://openalex.org/W3114479342","https://openalex.org/W3157114665","https://openalex.org/W3157506437","https://openalex.org/W3182465333","https://openalex.org/W4220686330","https://openalex.org/W4220764408","https://openalex.org/W4285255298","https://openalex.org/W4286571858","https://openalex.org/W4292779060","https://openalex.org/W4293195632","https://openalex.org/W4297775537","https://openalex.org/W4312687907","https://openalex.org/W4313467202","https://openalex.org/W4313467238","https://openalex.org/W4313535655","https://openalex.org/W4360606017","https://openalex.org/W4385245566","https://openalex.org/W6638632666","https://openalex.org/W6677580257","https://openalex.org/W6687483927","https://openalex.org/W6696798448","https://openalex.org/W6737664043","https://openalex.org/W6739901393","https://openalex.org/W6748224102","https://openalex.org/W6759263581","https://openalex.org/W6762718338","https://openalex.org/W6767298317","https://openalex.org/W6773270737","https://openalex.org/W6778883912","https://openalex.org/W6795140394","https://openalex.org/W6797854001"],"related_works":["https://openalex.org/W2148967747","https://openalex.org/W4256534760","https://openalex.org/W2349845193","https://openalex.org/W3183118997","https://openalex.org/W3214410901","https://openalex.org/W3204400881","https://openalex.org/W3204296682","https://openalex.org/W2917767146","https://openalex.org/W582278231","https://openalex.org/W2496519511"],"abstract_inverted_index":{"Various":[0],"pruning":[1],"and":[2,102,111,120,133,142,163],"quantization":[3,176],"heuristics":[4],"have":[5],"been":[6],"proposed":[7,58],"to":[8,27],"compress":[9],"recent":[10],"deep-learning":[11,44],"models.":[12],"However,":[13],"the":[14,92,147],"rapid":[15],"development":[16],"of":[17,85,94,139,145,160,167],"new":[18],"optimization":[19],"techniques":[20],"makes":[21],"it":[22],"difficult":[23],"for":[24],"domain-specific":[25],"accelerators":[26],"efficiently":[28],"process":[29],"various":[30],"models":[31],"showing":[32],"irregularly":[33],"stored":[34],"parameters":[35],"or":[36],"nonlinear":[37],"quantization.":[38],"This":[39],"article":[40],"presents":[41],"a":[42,75,117,136,157,164],"scalable-precision":[43],"accelerator":[45,59,148,171],"that":[46,124],"supports":[47,172],"multiply-and-accumulate":[48],"operations":[49],"(MACs)":[50],"with":[51,96,127,174],"two":[52,106],"arbitrarily":[53,70],"quantized":[54,71],"data":[55,95,108],"sequences.":[56],"The":[57,83,170],"includes":[60],"three":[61],"main":[62],"features.":[63],"To":[64],"minimize":[65],"logic":[66,101],"overhead":[67],"when":[68],"processing":[69,173],"8-bit":[72],"precision":[73,98,137],"data,":[74],"lookup":[76],"table":[77],"(LUT)-based":[78],"runtime":[79],"reconfiguration":[80],"is":[81],"proposed.":[82],"use":[84],"bit-serial":[86],"execution":[87],"without":[88],"unnecessary":[89],"computations":[90],"enables":[91],"multiplication":[93],"non-equal":[97],"while":[99,178],"minimizing":[100],"latency":[103],"waste.":[104],"Furthermore,":[105],"distinct":[107],"formats,":[109,129],"raw":[110],"run-length":[112],"compressed,":[113],"are":[114,125],"supported":[115],"by":[116],"zero-eliminator":[118],"(ZE)":[119],"runtime-density":[121],"detector":[122],"(RDD)":[123],"compatible":[126],"both":[128],"delivering":[130],"enhanced":[131],"storage":[132],"performance.":[134],"For":[135],"range":[138],"1\u20138":[140],"bit":[141],"fixed":[143],"sparsity":[144],"30%,":[146],"implemented":[149],"in":[150],"28":[151],"nm":[152],"low-power":[153],"(LP)":[154],"CMOS":[155],"shows":[156],"peak":[158],"performance":[159],"0.87\u20135.55":[161],"TOPS":[162],"power":[165,182],"efficiency":[166],"15.1\u201395.9":[168],"TOPS/W.":[169],"arbitrary":[175],"(AQ)":[177],"achieving":[179],"state-of-the-art":[180],"(SOTA)":[181],"efficiency.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"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"}