{"id":"https://openalex.org/W4410808431","doi":"https://doi.org/10.1109/tcsi.2025.3571901","title":"An Energy-Area-Efficient 3D Interleaved-Ring Accelerator With INT/FP Pipelined PE Array and 3D-SRAM Cube for On-Device CNN Training and DM Inference","display_name":"An Energy-Area-Efficient 3D Interleaved-Ring Accelerator With INT/FP Pipelined PE Array and 3D-SRAM Cube for On-Device CNN Training and DM Inference","publication_year":2025,"publication_date":"2025-05-28","ids":{"openalex":"https://openalex.org/W4410808431","doi":"https://doi.org/10.1109/tcsi.2025.3571901"},"language":"en","primary_location":{"id":"doi:10.1109/tcsi.2025.3571901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2025.3571901","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"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 Circuits and Systems I: Regular Papers","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/A5002275070","display_name":"Wei Lu","orcid":"https://orcid.org/0000-0003-4769-9261"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei Lu","raw_affiliation_strings":["Institute of Electronics and the International College of Semiconductor Technology, National Yang Ming Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-4769-9261","affiliations":[{"raw_affiliation_string":"Institute of Electronics and the International College of Semiconductor Technology, National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021615416","display_name":"Hung-Ming Chen","orcid":"https://orcid.org/0000-0001-8173-3131"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Ming Chen","raw_affiliation_strings":["Institute of Electronics and the International College of Semiconductor Technology, National Yang Ming Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electronics and the International College of Semiconductor Technology, National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066525875","display_name":"Po-Tsang Huang","orcid":"https://orcid.org/0000-0001-8679-2755"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Po-Tsang Huang","raw_affiliation_strings":["Institute of Electronics and the International College of Semiconductor Technology, National Yang Ming Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-8679-2755","affiliations":[{"raw_affiliation_string":"Institute of Electronics and the International College of Semiconductor Technology, National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0838397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"72","issue":"12","first_page":"7780","last_page":"7793"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14117","display_name":"Integrated Circuits and Semiconductor Failure Analysis","score":0.9976000189781189,"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/T14117","display_name":"Integrated Circuits and Semiconductor Failure Analysis","score":0.9976000189781189,"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/T10472","display_name":"Semiconductor materials and devices","score":0.9943000078201294,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.992900013923645,"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/cube","display_name":"Cube (algebra)","score":0.7746554613113403},{"id":"https://openalex.org/keywords/ring","display_name":"Ring (chemistry)","score":0.6492882966995239},{"id":"https://openalex.org/keywords/static-random-access-memory","display_name":"Static random-access memory","score":0.633871853351593},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5668864846229553},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5655771493911743},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4693537652492523},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4346773624420166},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4286750257015228},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.36419790983200073},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3618422746658325},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2528303861618042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18646717071533203},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.10833033919334412},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09187215566635132}],"concepts":[{"id":"https://openalex.org/C53051483","wikidata":"https://www.wikidata.org/wiki/Q861555","display_name":"Cube (algebra)","level":2,"score":0.7746554613113403},{"id":"https://openalex.org/C2780378348","wikidata":"https://www.wikidata.org/wiki/Q25351438","display_name":"Ring (chemistry)","level":2,"score":0.6492882966995239},{"id":"https://openalex.org/C68043766","wikidata":"https://www.wikidata.org/wiki/Q267416","display_name":"Static random-access memory","level":2,"score":0.633871853351593},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5668864846229553},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5655771493911743},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4693537652492523},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4346773624420166},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4286750257015228},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.36419790983200073},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3618422746658325},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2528303861618042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18646717071533203},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.10833033919334412},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09187215566635132},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsi.2025.3571901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2025.3571901","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"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 Circuits and Systems I: Regular Papers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8899999856948853,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G3221748285","display_name":null,"funder_award_id":"NSTC 112-2628-E-A49-021-MY3","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"},{"id":"https://openalex.org/G4886518252","display_name":null,"funder_award_id":"NSTC 114-2640-E-A49-011","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"}],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2062718228","https://openalex.org/W2162454039","https://openalex.org/W2217751126","https://openalex.org/W2508936709","https://openalex.org/W2512785086","https://openalex.org/W2515277349","https://openalex.org/W2999599167","https://openalex.org/W3016542674","https://openalex.org/W3017909826","https://openalex.org/W3040850704","https://openalex.org/W3047948099","https://openalex.org/W3127736057","https://openalex.org/W3132455321","https://openalex.org/W3190973916","https://openalex.org/W3201924642","https://openalex.org/W3210586215","https://openalex.org/W4220889234","https://openalex.org/W4220943275","https://openalex.org/W4285264221","https://openalex.org/W4312532564","https://openalex.org/W4324292875","https://openalex.org/W4360605760","https://openalex.org/W4367721918","https://openalex.org/W4385516735","https://openalex.org/W4385525225","https://openalex.org/W4385801275","https://openalex.org/W4385901095","https://openalex.org/W4387411224","https://openalex.org/W4390874074","https://openalex.org/W4392746141","https://openalex.org/W4392746501","https://openalex.org/W4396712846","https://openalex.org/W4400233352","https://openalex.org/W4401879849","https://openalex.org/W4402475889","https://openalex.org/W4402754224"],"related_works":["https://openalex.org/W4392590355","https://openalex.org/W3151633427","https://openalex.org/W2212894501","https://openalex.org/W1979375376","https://openalex.org/W2793465010","https://openalex.org/W3024050170","https://openalex.org/W1976168335","https://openalex.org/W2109451123","https://openalex.org/W4378977321","https://openalex.org/W3211992815"],"abstract_inverted_index":{"Deep":[0],"neural":[1,30],"networks":[2,31],"(DNNs)":[3],"have":[4],"demonstrated":[5],"exceptional":[6],"performance":[7],"in":[8,59,99],"image-related":[9,70],"artificial":[10],"intelligence":[11],"(AI)":[12],"applications.":[13],"However,":[14],"the":[15,26,67,89,117,128,145,168,178,192,228,262],"inference":[16],"of":[17,28,69,91,181,188,194,200],"generative":[18],"models,":[19],"such":[20],"as":[21],"Diffusion":[22],"Models":[23],"(DMs),":[24],"and":[25,45,132,164,190,231,243,268,281,295],"training":[27],"convolutional":[29],"(CNNs)":[32],"are":[33,50],"computationally":[34],"intensive":[35],"tasks,":[36],"requiring":[37],"extensive":[38],"floating-point":[39,133],"(FP)":[40,134],"operations":[41],"to":[42,86,126,203,220,273,291],"maintain":[43],"accuracy":[44],"high-quality":[46],"results.":[47],"These":[48],"tasks":[49],"also":[51],"memory-bound,":[52],"generating":[53],"large":[54],"intermediate":[55],"data":[56,183,222],"that":[57,215],"result":[58],"significant":[60],"external":[61],"memory":[62],"access":[63],"(EMA),":[64],"thus":[65],"complicating":[66],"deployment":[68],"DNNs":[71],"on":[72,227],"edge":[73],"devices.":[74],"While":[75],"3D-stacked":[76],"SRAM":[77],"with":[78,139,161],"through-silicon":[79],"via":[80],"(TSV)":[81],"technology":[82],"offers":[83],"promising":[84],"solutions":[85],"alleviate":[87],"EMA,":[88],"complexities":[90],"3D":[92,113,118,123,149,170,174,205,264],"interconnect":[93,114],"architectures":[94],"can":[95],"introduce":[96,210],"substantial":[97],"overhead":[98,146],"intra-chip":[100],"communication,":[101],"potentially":[102],"degrading":[103],"overall":[104],"efficiency.":[105],"In":[106],"this":[107],"paper,":[108],"we":[109,209],"propose":[110],"a":[111,140,186,198],"flexible":[112],"architecture,":[115],"termed":[116],"interleaved-ring,":[119],"which":[120],"utilizes":[121],"multiple":[122],"interleaved":[124],"rings":[125],"connect":[127],"pipelined":[129],"integer":[130],"(INT)":[131],"processing":[135],"element":[136],"(PE)":[137],"arrays":[138],"3D-SRAM":[141,229],"cube,":[142,230],"effectively":[143],"mitigating":[144],"caused":[147],"by":[148,185,197,247,271],"interconnection.":[150],"We":[151],"design":[152],"<inline-formula":[153,250,274,282],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[154,251,275,283],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[155,252,276,284],"<tex-math":[156,253,277,285],"notation=\"LaTeX\">$3\\times":[157],"3$</tex-math>":[158],"</inline-formula>":[159,256,280],"micro-routers":[160],"dedicated":[162],"channels":[163],"embedded":[165],"adders":[166],"for":[167],"proposed":[169,236,263],"interconnection":[171],"architecture.":[172],"This":[173],"ring-based":[175],"architecture":[176],"reduces":[177,244],"power":[179],"consumption":[180],"on-chip":[182],"movement":[184],"factor":[187,199],"4.5":[189],"decreases":[191],"number":[193],"required":[195],"TSVs":[196],"4.2,":[201],"compared":[202,290],"conventional":[204],"mesh-based":[206],"interconnects.":[207],"Additionally,":[208],"efficient":[211],"mixed-bit":[212],"precision":[213],"dataflows":[214],"incorporates":[216],"dynamic":[217],"workload":[218],"distribution":[219],"optimize":[221],"reuse,":[223],"reduce":[224],"bandwidth":[225],"demands":[226],"improve":[232],"PE":[233,241],"utilization.":[234],"The":[235],"work":[237],"achieves":[238],"over":[239],"90%":[240],"utilization":[242],"DRAM":[245],"accesses":[246],"more":[248],"than":[249],"notation=\"LaTeX\">$7\\times":[254],"$</tex-math>":[255,279,287],"across":[257],"various":[258],"DNN":[259,293],"models.":[260],"Overall,":[261],"accelerator":[265],"improves":[266],"energy":[267],"area":[269],"efficiency":[270],"up":[272],"notation=\"LaTeX\">$8.4\\times":[278],"notation=\"LaTeX\">$3.4\\times":[286],"</inline-formula>,":[288],"respectively,":[289],"state-of-the-art":[292],"accelerators":[294],"processors.":[296]},"counts_by_year":[],"updated_date":"2025-11-28T02:08:47.144824","created_date":"2025-10-10T00:00:00"}
