{"id":"https://openalex.org/W4386763617","doi":"https://doi.org/10.1109/dac56929.2023.10247977","title":"A Convolution Neural Network Accelerator Design with Weight Mapping and Pipeline Optimization","display_name":"A Convolution Neural Network Accelerator Design with Weight Mapping and Pipeline Optimization","publication_year":2023,"publication_date":"2023-07-09","ids":{"openalex":"https://openalex.org/W4386763617","doi":"https://doi.org/10.1109/dac56929.2023.10247977"},"language":"en","primary_location":{"id":"doi:10.1109/dac56929.2023.10247977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac56929.2023.10247977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 60th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102941473","display_name":"Lixia Han","orcid":"https://orcid.org/0000-0002-4721-1564"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lixia Han","raw_affiliation_strings":["Peking University,School of Integrated Circuits","School of Integrated Circuits, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Integrated Circuits","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Integrated Circuits, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089747900","display_name":"Peng Huang","orcid":"https://orcid.org/0000-0003-3280-0099"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Huang","raw_affiliation_strings":["Peking University,School of Integrated Circuits","School of Integrated Circuits, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Integrated Circuits","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Integrated Circuits, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108670530","display_name":"Zheng Zhou","orcid":"https://orcid.org/0000-0002-5976-7172"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Zhou","raw_affiliation_strings":["Peking University,School of Integrated Circuits","School of Integrated Circuits, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Integrated Circuits","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Integrated Circuits, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087811347","display_name":"Yiyang Chen","orcid":"https://orcid.org/0000-0001-9960-9040"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyang Chen","raw_affiliation_strings":["Peking University,School of Integrated Circuits","School of Integrated Circuits, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Integrated Circuits","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Integrated Circuits, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324668","display_name":"Xiaoyan Liu","orcid":"https://orcid.org/0009-0007-8018-651X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Liu","raw_affiliation_strings":["Peking University,School of Integrated Circuits","School of Integrated Circuits, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Integrated Circuits","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Integrated Circuits, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010857702","display_name":"Jinfeng Kang","orcid":"https://orcid.org/0000-0002-6286-0423"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinfeng Kang","raw_affiliation_strings":["Peking University,School of Integrated Circuits","School of Integrated Circuits, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Integrated Circuits","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Integrated Circuits, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":4.3269,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.95865496,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":1.0,"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":1.0,"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":0.9994999766349792,"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":0.8180209398269653},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7722087502479553},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5357206463813782},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5302944779396057},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.5279421210289001},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4995086193084717},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.4561154544353485},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4449620842933655},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.42650750279426575},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.414264440536499},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.39237162470817566},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3877691328525543},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.38679739832878113},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3840191066265106},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3722914457321167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19619709253311157},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18723002076148987},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.11512064933776855},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11398360133171082},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.11079871654510498},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08336234092712402}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8180209398269653},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7722087502479553},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5357206463813782},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5302944779396057},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.5279421210289001},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4995086193084717},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.4561154544353485},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4449620842933655},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.42650750279426575},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.414264440536499},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.39237162470817566},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3877691328525543},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38679739832878113},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3840191066265106},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3722914457321167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19619709253311157},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18723002076148987},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.11512064933776855},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11398360133171082},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.11079871654510498},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08336234092712402},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac56929.2023.10247977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac56929.2023.10247977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 60th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2104823269","https://openalex.org/W2464177207","https://openalex.org/W2508602506","https://openalex.org/W2518281301","https://openalex.org/W2588666075","https://openalex.org/W2900128795","https://openalex.org/W2910442417","https://openalex.org/W2943765373","https://openalex.org/W2963387357","https://openalex.org/W3003821665","https://openalex.org/W3013080934","https://openalex.org/W3015982917","https://openalex.org/W3044192339","https://openalex.org/W3092601938","https://openalex.org/W3126707065","https://openalex.org/W3134195144","https://openalex.org/W3183264033","https://openalex.org/W3213412675","https://openalex.org/W4220882094","https://openalex.org/W4221118949","https://openalex.org/W4292121737","https://openalex.org/W4293023010","https://openalex.org/W6675609000","https://openalex.org/W6719768283","https://openalex.org/W6776511271","https://openalex.org/W6791463985","https://openalex.org/W6809326210","https://openalex.org/W6809622522"],"related_works":["https://openalex.org/W2030816003","https://openalex.org/W4239992647","https://openalex.org/W1554458299","https://openalex.org/W4319952061","https://openalex.org/W4280636456","https://openalex.org/W4388913998","https://openalex.org/W4310584535","https://openalex.org/W4295935044","https://openalex.org/W4307927141","https://openalex.org/W3159906349"],"abstract_inverted_index":{"The":[0],"pipeline":[1,29,58,132,146],"is":[2,81,97,112],"an":[3],"efficient":[4],"solution":[5],"to":[6,83,99,114],"boost":[7],"performance":[8],"in":[9,14],"non-volatile":[10],"memory":[11,15],"based":[12],"computing":[13,67],"(nvCIM)":[16],"convolution":[17],"neural":[18],"network":[19],"(CNN)":[20],"accelerators.":[21],"However,":[22],"the":[23,32,35,40,65,69,73,89,101,105,116,123,134],"previous":[24],"works":[25],"seldom":[26],"focus":[27],"on":[28],"optimization":[30],"from":[31],"perspective":[33],"of":[34,42,63,158],"whole":[36],"system,":[37],"especially":[38],"overlooking":[39],"effect":[41],"buffer":[43,70,85],"access.":[44,71],"In":[45],"this":[46],"work,":[47],"we":[48,128],"propose":[49],"a":[50,56,76,108,130,138],"high-performance":[51],"NVM-based":[52],"CNN":[53,120],"accelerator":[54,136],"with":[55,160],"balanced":[57],"design,":[59],"which":[60],"takes":[61],"account":[62],"both":[64],"macro":[66,90],"and":[68,94,152,163],"At":[72,88,104],"operator":[74],"level,":[75,91,107],"matrix-based":[77],"weight":[78],"mapping":[79],"method":[80],"proposed":[82],"reduce":[84],"access":[86,93],"delay.":[87],"decoupled":[92],"execution":[95],"design":[96,111,147],"introduced":[98],"shorten":[100],"single-layer":[102],"latency.":[103],"system":[106],"hybrid":[109],"inter/intra-tile":[110],"presented":[113],"balance":[115],"overall":[117],"latency":[118],"across":[119],"layers.":[121],"With":[122],"collaboration":[124],"among":[125],"three":[126],"methods,":[127],"construct":[129],"well-balanced":[131],"for":[133,156],"nvCIM":[135],"at":[137],"smaller":[139],"hardware":[140],"cost.":[141],"Experiments":[142],"show":[143],"that":[144],"our":[145],"can":[148],"achieve":[149],"3.7\u0445,":[150],"7.5\u0445,":[151],"3.5\u0445":[153],"throughput":[154],"improvement":[155],"recognition":[157],"ImageNet":[159],"ResNet18,":[161],"VGG19,":[162],"ResNet34":[164],"models,":[165],"respectively.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}