{"id":"https://openalex.org/W4200456425","doi":"https://doi.org/10.1109/hpec49654.2021.9622798","title":"Software-Hardware Co-Optimization on Partial-Sum Problem for PIM-based Neural Network Accelerator","display_name":"Software-Hardware Co-Optimization on Partial-Sum Problem for PIM-based Neural Network Accelerator","publication_year":2021,"publication_date":"2021-09-20","ids":{"openalex":"https://openalex.org/W4200456425","doi":"https://doi.org/10.1109/hpec49654.2021.9622798"},"language":"en","primary_location":{"id":"doi:10.1109/hpec49654.2021.9622798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5000968348","display_name":"Qizhe Wu","orcid":"https://orcid.org/0000-0002-4977-5363"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"],"is_corresponding":true,"raw_author_name":"Qizhe Wu","raw_affiliation_strings":["State Key Laboratory of Particle Detection and Electronics, Chinese Academy of Sciences, Institute of Microelectronics, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Particle Detection and Electronics, Chinese Academy of Sciences, Institute of Microelectronics, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060373137","display_name":"Linfeng Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"],"is_corresponding":false,"raw_author_name":"Linfeng Tao","raw_affiliation_strings":["State Key Laboratory of Particle Detection and Electronics, Chinese Academy of Sciences, Institute of Microelectronics, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Particle Detection and Electronics, Chinese Academy of Sciences, Institute of Microelectronics, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051492842","display_name":"Huawen Liang","orcid":"https://orcid.org/0000-0003-3196-2942"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"],"is_corresponding":false,"raw_author_name":"Huawen Liang","raw_affiliation_strings":["State Key Laboratory of Particle Detection and Electronics, Chinese Academy of Sciences, Institute of Microelectronics, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Particle Detection and Electronics, Chinese Academy of Sciences, Institute of Microelectronics, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071938250","display_name":"Yuan Wei","orcid":"https://orcid.org/0000-0002-2844-846X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"],"is_corresponding":false,"raw_author_name":"Wei Yuan","raw_affiliation_strings":["State Key Laboratory of Particle Detection and Electronics, Chinese Academy of Sciences, Institute of Microelectronics, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Particle Detection and Electronics, Chinese Academy of Sciences, Institute of Microelectronics, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017010290","display_name":"Teng Tian","orcid":"https://orcid.org/0000-0002-0594-5957"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"],"is_corresponding":false,"raw_author_name":"Teng Tian","raw_affiliation_strings":["State Key Laboratory of Particle Detection and Electronics, Chinese Academy of Sciences, Institute of Microelectronics, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Particle Detection and Electronics, Chinese Academy of Sciences, Institute of Microelectronics, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070394553","display_name":"Shuang Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"],"is_corresponding":false,"raw_author_name":"Shuang Xue","raw_affiliation_strings":["State Key Laboratory of Particle Detection and Electronics, Chinese Academy of Sciences, Institute of Microelectronics, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Particle Detection and Electronics, Chinese Academy of Sciences, Institute of Microelectronics, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210119392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079471306","display_name":"Xi Jin","orcid":"https://orcid.org/0000-0002-4159-2925"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"],"is_corresponding":false,"raw_author_name":"Xi Jin","raw_affiliation_strings":["State Key Laboratory of Particle Detection and Electronics, Chinese Academy of Sciences, Institute of Microelectronics, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Particle Detection and Electronics, Chinese Academy of Sciences, Institute of Microelectronics, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210119392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5000968348"],"corresponding_institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210119392"],"apc_list":null,"apc_paid":null,"fwci":0.1012,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46328513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9997000098228455,"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/T12676","display_name":"Machine Learning and ELM","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/crossbar-switch","display_name":"Crossbar switch","score":0.8392776250839233},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7144165635108948},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5547547936439514},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5436230897903442},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4459291398525238},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4377225637435913},{"id":"https://openalex.org/keywords/operand","display_name":"Operand","score":0.41607773303985596},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.38211578130722046},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.37976783514022827},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.34404176473617554},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24267122149467468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21074190735816956},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10056343674659729}],"concepts":[{"id":"https://openalex.org/C29984679","wikidata":"https://www.wikidata.org/wiki/Q1929149","display_name":"Crossbar switch","level":2,"score":0.8392776250839233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7144165635108948},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5547547936439514},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5436230897903442},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4459291398525238},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4377225637435913},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.41607773303985596},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.38211578130722046},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.37976783514022827},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.34404176473617554},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24267122149467468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21074190735816956},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10056343674659729},{"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/hpec49654.2021.9622798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8999999761581421,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1987760418","https://openalex.org/W2014402164","https://openalex.org/W2117726386","https://openalex.org/W2163359472","https://openalex.org/W2163605009","https://openalex.org/W2408724663","https://openalex.org/W2508602506","https://openalex.org/W2518281301","https://openalex.org/W2531409750","https://openalex.org/W2588666075","https://openalex.org/W2603636614","https://openalex.org/W2613989746","https://openalex.org/W2627034335","https://openalex.org/W2785346409","https://openalex.org/W2943765373","https://openalex.org/W2946659370","https://openalex.org/W3003821665","https://openalex.org/W3005619596","https://openalex.org/W6684191040","https://openalex.org/W6728184133"],"related_works":["https://openalex.org/W4214834240","https://openalex.org/W4318686055","https://openalex.org/W2910506572","https://openalex.org/W2970793270","https://openalex.org/W3109300165","https://openalex.org/W1937036045","https://openalex.org/W4293243600","https://openalex.org/W2971450774","https://openalex.org/W2408724663","https://openalex.org/W2945569829"],"abstract_inverted_index":{"The":[0,62],"crossbar":[1,138,212],"architecture,":[2],"which":[3,68],"is":[4,30,69],"comprised":[5],"of":[6,25,217],"novel":[7],"memristor":[8],"devices,":[9],"enables":[10],"high-speed":[11],"and":[12,55,75,146,169,206,222,230],"energy-efficient":[13],"processing-in-memory":[14],"(PIM)":[15],"for":[16,137,161,194],"neural":[17,40,63,119],"network":[18,64,209],"computing.":[19],"However,":[20],"because":[21],"to":[22,32,51,113,117,236],"the":[23,26,39,46,53,59,80,86,98,126,134,167,174,186,203,207,237],"limitations":[24],"manufacturing":[27],"process,":[28,67],"it":[29,111],"difficult":[31,112],"fabricate":[33],"huge":[34],"arrays.":[35],"As":[36,89],"a":[37,90,151,191],"consequence,":[38,91],"network\u2019s":[41],"vector-matrix-multiplication":[42],"(VMM)":[43],"must":[44],"split":[45],"operands":[47],"into":[48,104],"several":[49],"arrays":[50],"get":[52],"partial-sum":[54,87,103,135,165],"then":[56],"add":[57],"up":[58],"partial":[60],"results.":[61],"(NN)":[65],"training":[66],"often":[70],"influenced":[71],"by":[72],"device":[73],"variations":[74],"ADC":[76],"quantization":[77],"noise":[78],"in":[79,220,225],"PIM":[81,99,115,239],"system,":[82],"does":[83],"not":[84],"perceive":[85],"process.":[88],"when":[92,234],"inferring":[93],"NN":[94],"models":[95],"directly":[96],"on":[97,133,210,228],"platform":[100],"without":[101],"taking":[102],"account,":[105],"accuracy":[106],"suffers":[107],"significantly.":[108],"This":[109],"makes":[110,125],"apply":[114],"computing":[116,141],"large-scale":[118],"networks.":[120],"In":[121],"particular,":[122],"our":[123],"work":[124],"following":[127],"contributions:":[128],"(i)":[129],"We":[130],"conducted":[131,201],"research":[132],"issue":[136],"architecture":[139,193],"while":[140],"high":[142],"channel":[143],"convolution":[144],"(Conv),":[145],"got":[147],"three":[148],"lessons":[149],"as":[150],"result.":[152],"(ii)":[153],"To":[154],"address":[155],"this":[156],"issue,":[157],"we":[158,177,189],"offer":[159],"techniques":[160],"avoiding":[162],"or":[163],"minimizing":[164],"at":[166,185],"software":[168,175,229],"hardware":[170,187,231],"levels,":[171,232],"respectively.":[172],"At":[173],"level,":[176,188],"utilized":[178],"group":[179],"Conv":[180],"rather":[181],"than":[182],"conventional":[183,238],"Conv;":[184],"presented":[190],"new":[192],"adapting":[195],"depthwise":[196],"separable":[197],"Conv.":[198],"Experiments":[199],"were":[200],"using":[202],"Cifar10":[204],"dataset":[205],"VGG8":[208],"RRAM":[211],"architecture.":[213],"Results":[214],"show":[215],"improvements":[216],"15.53%,":[218],"14.55%":[219],"accuracy,":[221],"0.28\u00d7,":[223],"0.94\u00d7":[224],"energy":[226],"efficiency":[227],"respectively,":[233],"compared":[235],"scheme.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}
