{"id":"https://openalex.org/W4404787918","doi":"https://doi.org/10.1109/tcsi.2024.3505299","title":"A 97.8 GOPS/W FPGA-Based Residual-Block-Aware CNN Accelerator Featuring Multi-Clock PW <sup>2</sup> Pipeline and Adaptive-Resolution Quantization","display_name":"A 97.8 GOPS/W FPGA-Based Residual-Block-Aware CNN Accelerator Featuring Multi-Clock PW <sup>2</sup> Pipeline and Adaptive-Resolution Quantization","publication_year":2024,"publication_date":"2024-11-27","ids":{"openalex":"https://openalex.org/W4404787918","doi":"https://doi.org/10.1109/tcsi.2024.3505299"},"language":"en","primary_location":{"id":"doi:10.1109/tcsi.2024.3505299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2024.3505299","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/A5079735655","display_name":"Jixuan Li","orcid":"https://orcid.org/0009-0001-6615-0680"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN","MO"],"is_corresponding":false,"raw_author_name":"Jixuan Li","raw_affiliation_strings":["ECE Department, State-Key Laboratory of Analog and Mixed-Signal VLSI/Institute of Microelectronics and the Faculty of Science and Technology, University of Macau, Macau, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, State-Key Laboratory of Analog and Mixed-Signal VLSI/Institute of Microelectronics and the Faculty of Science and Technology, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343509","display_name":"Ke Li","orcid":"https://orcid.org/0000-0002-7318-1186"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN","MO"],"is_corresponding":false,"raw_author_name":"Ke Li","raw_affiliation_strings":["ECE Department, State-Key Laboratory of Analog and Mixed-Signal VLSI/Institute of Microelectronics and the Faculty of Science and Technology, University of Macau, Macau, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, State-Key Laboratory of Analog and Mixed-Signal VLSI/Institute of Microelectronics and the Faculty of Science and Technology, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038010873","display_name":"Ka-Fai Un","orcid":"https://orcid.org/0000-0002-7574-4755"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN","MO"],"is_corresponding":false,"raw_author_name":"Ka-Fai Un","raw_affiliation_strings":["ECE Department, State-Key Laboratory of Analog and Mixed-Signal VLSI/Institute of Microelectronics and the Faculty of Science and Technology, University of Macau, Macau, China"],"raw_orcid":"https://orcid.org/0000-0002-7574-4755","affiliations":[{"raw_affiliation_string":"ECE Department, State-Key Laboratory of Analog and Mixed-Signal VLSI/Institute of Microelectronics and the Faculty of Science and Technology, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090222712","display_name":"Wei-Han Yu","orcid":"https://orcid.org/0000-0002-9079-5227"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN","MO"],"is_corresponding":false,"raw_author_name":"Wei-Han Yu","raw_affiliation_strings":["ECE Department, State-Key Laboratory of Analog and Mixed-Signal VLSI/Institute of Microelectronics and the Faculty of Science and Technology, University of Macau, Macau, China"],"raw_orcid":"https://orcid.org/0000-0002-9079-5227","affiliations":[{"raw_affiliation_string":"ECE Department, State-Key Laboratory of Analog and Mixed-Signal VLSI/Institute of Microelectronics and the Faculty of Science and Technology, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106943352","display_name":"Rui P. Martins","orcid":"https://orcid.org/0000-0003-2821-648X"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN","MO"],"is_corresponding":false,"raw_author_name":"Rui P. Martins","raw_affiliation_strings":["ECE Department, State-Key Laboratory of Analog and Mixed-Signal VLSI/Institute of Microelectronics and the Faculty of Science and Technology, University of Macau, Macau, China"],"raw_orcid":"https://orcid.org/0000-0003-2821-648X","affiliations":[{"raw_affiliation_string":"ECE Department, State-Key Laboratory of Analog and Mixed-Signal VLSI/Institute of Microelectronics and the Faculty of Science and Technology, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498","https://openalex.org/I4210119392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058845450","display_name":"Pui\u2010In Mak","orcid":"https://orcid.org/0000-0002-3579-8740"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN","MO"],"is_corresponding":false,"raw_author_name":"Pui-In Mak","raw_affiliation_strings":["ECE Department, State-Key Laboratory of Analog and Mixed-Signal VLSI/Institute of Microelectronics and the Faculty of Science and Technology, University of Macau, Macau, China"],"raw_orcid":"https://orcid.org/0000-0002-3579-8740","affiliations":[{"raw_affiliation_string":"ECE Department, State-Key Laboratory of Analog and Mixed-Signal VLSI/Institute of Microelectronics and the Faculty of Science and Technology, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498","https://openalex.org/I4210119392"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3636,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61469028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"72","issue":"8","first_page":"4031","last_page":"4039"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T11038","display_name":"Advanced SAR Imaging Techniques","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.9968000054359436,"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7396037578582764},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6156521439552307},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6024805307388306},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6013786792755127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5999139547348022},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5973108410835266},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.4377070665359497},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4009600877761841},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3630009889602661},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.3294633626937866},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23483583331108093},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1905977725982666},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17856654524803162},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.07881316542625427},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07755166292190552}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7396037578582764},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6156521439552307},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6024805307388306},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6013786792755127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5999139547348022},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5973108410835266},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.4377070665359497},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4009600877761841},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3630009889602661},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3294633626937866},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23483583331108093},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1905977725982666},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17856654524803162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.07881316542625427},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07755166292190552},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsi.2024.3505299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2024.3505299","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":[],"awards":[{"id":"https://openalex.org/G2299472110","display_name":null,"funder_award_id":"0160/2022/A","funder_id":"https://openalex.org/F4320315893","funder_display_name":"VNU Science and Technology Development Fund"},{"id":"https://openalex.org/G5378438400","display_name":null,"funder_award_id":"MYRGGRG2023-00012-IME","funder_id":"https://openalex.org/F4320322841","funder_display_name":"Universidade de Macau"},{"id":"https://openalex.org/G6548532224","display_name":null,"funder_award_id":"004/2023/SKL","funder_id":"https://openalex.org/F4320315893","funder_display_name":"VNU Science and Technology Development Fund"}],"funders":[{"id":"https://openalex.org/F4320315893","display_name":"VNU Science and Technology Development Fund","ror":"https://ror.org/044vr6g03"},{"id":"https://openalex.org/F4320322841","display_name":"Universidade de Macau","ror":"https://ror.org/01r4q9n85"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2279098554","https://openalex.org/W2549139847","https://openalex.org/W2620983607","https://openalex.org/W2768993447","https://openalex.org/W2786771851","https://openalex.org/W2887936511","https://openalex.org/W2933438941","https://openalex.org/W2963163009","https://openalex.org/W2974135602","https://openalex.org/W3093796669","https://openalex.org/W3162993841","https://openalex.org/W3164217046","https://openalex.org/W3167976421","https://openalex.org/W3178956316","https://openalex.org/W4200400428","https://openalex.org/W4205884968","https://openalex.org/W4211085526","https://openalex.org/W4214870144","https://openalex.org/W4221154945","https://openalex.org/W4249932213","https://openalex.org/W4285146087","https://openalex.org/W4285507310","https://openalex.org/W4286910290","https://openalex.org/W4312036002","https://openalex.org/W4312857960","https://openalex.org/W4321637080","https://openalex.org/W4360605374","https://openalex.org/W4385832149","https://openalex.org/W4386076206","https://openalex.org/W4390872670","https://openalex.org/W4392828138","https://openalex.org/W6637373629","https://openalex.org/W6684191040","https://openalex.org/W6695314431","https://openalex.org/W6738686954","https://openalex.org/W6748224102","https://openalex.org/W6785834052","https://openalex.org/W6790152577","https://openalex.org/W6802648153"],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W2560215812","https://openalex.org/W2355315220","https://openalex.org/W4200391368","https://openalex.org/W2210979487","https://openalex.org/W2949601986","https://openalex.org/W2316202402","https://openalex.org/W2074043759","https://openalex.org/W2082487009","https://openalex.org/W2373535795"],"abstract_inverted_index":{"Enhancing":[0],"the":[1,5,27,42,72,92,105,123,128,135,140,155],"energy":[2,181],"efficiency":[3,94,165,182],"for":[4,10,41],"residual":[6,33,79],"block":[7],"is":[8],"crucial":[9],"an":[11,180],"energy-efficient":[12],"deep":[13],"neural":[14],"network":[15],"accelerator.":[16],"This":[17],"paper":[18],"presents":[19],"a":[20,56,68,113,163,171,187],"multi-clock":[21],"pointwise-pointwise":[22],"(MCPW2)":[23],"technique":[24],"to":[25,37,62,120],"process":[26],"adjacent":[28],"PW":[29],"convolution":[30,143],"layers":[31,144],"across":[32],"blocks,":[34],"reducing":[35],"up":[36,95],"75.0%":[38],"DRAM":[39,99],"access":[40,100],"intermediate":[43],"feature":[44],"maps":[45],"while":[46],"securing":[47],">88.1%":[48],"processing":[49],"element":[50],"(PE)":[51],"utilization.":[52],"Moreover,":[53],"we":[54],"introduce":[55],"dual-precision":[57],"packing":[58],"(DPP)":[59],"DSP":[60,87,93,117,164],"array":[61],"compute":[63],"multiple":[64],"4/8-bit":[65],"multiplications":[66],"in":[67],"shared":[69],"DSP,":[70],"improving":[71],"accuracy":[73],"by":[74,101],"1.5%":[75],"(ImageNet)":[76],"using":[77],"low-precision":[78],"distillation":[80],"(RD)":[81],"with":[82,145],"adaptive-resolution":[83,89],"quantization.":[84],"The":[85],"DPP":[86],"and":[88,103,170,186],"RD":[90],"boost":[91],"to$4.0\\times":[96],"$,":[97,169],"reduce":[98],"50.0%,":[102],"improve":[104],"throughput":[106,172,189],"by$\\gt":[107],"2.7\\times":[108],"$.":[109],"We":[110],"also":[111,133],"propose":[112],"dynamic":[114],"accumulator/multiplier":[115],"(A/M)":[116],"reconfiguration":[118],"scheme":[119],"dynamically":[121],"adjust":[122],"level":[124],"of":[125,161,183,190],"parallelism":[126],"along":[127],"input/output":[129],"channel":[130],"dimensions.":[131],"It":[132],"increases":[134],"PE":[136,159],"utilization":[137,160],"by$1.8\\times":[138],"$for":[139],"depthwise":[141],"(DW)":[142],"33%":[146],"less":[147],"hardware":[148],"resource":[149],"overhead.":[150],"Implemented":[151],"on":[152,174],"Xilinx":[153],"VC709,":[154],"proposed":[156],"accelerator":[157],"achieves":[158],">93.0%,":[162],"gain":[166],"of$\\gt":[167],"2.9\\times":[168],"improvement":[173],"benchmarked":[175],"networks":[176],"of$4.9\\times":[177],"$while":[178],"exhibiting":[179],"97.8":[184],"GOPs/W":[185],"normalized":[188],"1.18":[191],"GOPS/DSP.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2024-11-28T00:00:00"}