{"id":"https://openalex.org/W7130578735","doi":"https://doi.org/10.1109/apccas67402.2025.11377433","title":"A Dual-Mode High Efficient Hardware Architecture Design for Diffusion Models","display_name":"A Dual-Mode High Efficient Hardware Architecture Design for Diffusion Models","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W7130578735","doi":"https://doi.org/10.1109/apccas67402.2025.11377433"},"language":null,"primary_location":{"id":"doi:10.1109/apccas67402.2025.11377433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apccas67402.2025.11377433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","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/A5024306153","display_name":"Tsung\u2010Lin Tsai","orcid":"https://orcid.org/0000-0002-2920-5582"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Tsung-Lin Tsai","raw_affiliation_strings":["Graduate Institute of Electronics Engineering, National Taiwan University,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electronics Engineering, National Taiwan University,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002583275","display_name":"Yi-Cheng Lo","orcid":"https://orcid.org/0000-0002-0619-6396"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Cheng Lo","raw_affiliation_strings":["Graduate Institute of Electronics Engineering, National Taiwan University,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electronics Engineering, National Taiwan University,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126394657","display_name":"Ching-Yao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ching-Yao Chen","raw_affiliation_strings":["Graduate Institute of Electronics Engineering, National Taiwan University,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electronics Engineering, National Taiwan University,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126399205","display_name":"An-Yeu Andy Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"An-Yeu Andy Wu","raw_affiliation_strings":["Graduate Institute of Electronics Engineering, National Taiwan University,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electronics Engineering, National Taiwan University,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024306153"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.63355244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.1818999946117401,"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":0.1818999946117401,"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":0.14350000023841858,"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":0.13899999856948853,"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/overhead","display_name":"Overhead (engineering)","score":0.6255999803543091},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5842999815940857},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5372999906539917},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5055999755859375},{"id":"https://openalex.org/keywords/cmos","display_name":"CMOS","score":0.49880000948905945},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.486299991607666},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.45660001039505005},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4205999970436096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7346000075340271},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6255999803543091},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5842999815940857},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5372999906539917},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C46362747","wikidata":"https://www.wikidata.org/wiki/Q173431","display_name":"CMOS","level":2,"score":0.49880000948905945},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.486299991607666},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.45660001039505005},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4408999979496002},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4205999970436096},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.41510000824928284},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.37940001487731934},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3790000081062317},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3450999855995178},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.25929999351501465},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.25189998745918274},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apccas67402.2025.11377433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apccas67402.2025.11377433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8723329305648804,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G8349783510","display_name":null,"funder_award_id":"113-2218-E-002-036-MBK","funder_id":"https://openalex.org/F2461203286","funder_display_name":"National Science and Technology Council"}],"funders":[{"id":"https://openalex.org/F2461203286","display_name":"National Science and Technology Council","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2172654076","https://openalex.org/W4392746069","https://openalex.org/W4400231729","https://openalex.org/W4401879849","https://openalex.org/W4408183360"],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"models":[1],"have":[2],"achieved":[3],"strong":[4],"performance":[5],"in":[6,89],"generative":[7],"vision":[8],"tasks":[9],"but":[10],"suffer":[11],"from":[12],"high":[13,50],"compute":[14],"and":[15,48,60,94,124],"memory":[16],"demands":[17,79],"due":[18],"to":[19,80],"their":[20],"iterative":[21],"U-Net":[22],"structure.":[23],"This":[24],"paper":[25],"presents":[26],"a":[27,37,54,71,96],"hardware-efficient":[28],"diffusion":[29,126],"accelerator":[30,86],"with":[31],"three":[32],"key":[33],"architectural":[34],"optimizations.":[35],"First,":[36],"Winograd-Enhanced":[38],"DualMode":[39],"Dispatcher":[40],"improves":[41],"convolution":[42],"throughput":[43],"by":[44],"eliminating":[45],"im2col":[46],"overhead":[47],"maintaining":[49],"PE":[51],"utilization.":[52],"Second,":[53],"Dynamic":[55],"Sparse":[56],"Attention":[57],"Engine":[58],"predicts":[59],"prunes":[61],"lowimportance":[62],"attention":[63,117],"scores":[64],"at":[65],"runtime,":[66],"reducing":[67],"unnecessary":[68],"multiplications.":[69],"Third,":[70],"Reconfigurable":[72],"Mixed-Precision":[73],"Processor":[74],"adapts":[75],"different":[76],"bit-width":[77],"workload":[78],"avoid":[81],"resource":[82],"waste.":[83],"The":[84],"proposed":[85],"is":[87],"implemented":[88],"TSMC":[90],"28nm":[91],"CMOS":[92],"technology":[93],"achieves":[95],"peak":[97],"energy":[98],"efficiency":[99],"of":[100],"<tex":[101,110],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[102,111],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{1":[103],"2":[104],"0.":[105],"5":[106],"9}$</tex>":[107],"TOPS/W":[108],"under":[109],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{9":[112],"0":[113],"\\%}$</tex>":[114],"sparsity":[115],"during":[116],"computation,":[118],"demonstrating":[119],"its":[120],"suitability":[121],"for":[122],"real-time":[123],"lowpower":[125],"inference.":[127]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-02-20T00:00:00"}