{"id":"https://openalex.org/W3203039380","doi":"https://doi.org/10.1145/3458744.3473351","title":"Accelerate Binarized Neural Networks with Processing-in-Memory Enabled by RISC-V Custom Instructions","display_name":"Accelerate Binarized Neural Networks with Processing-in-Memory Enabled by RISC-V Custom Instructions","publication_year":2021,"publication_date":"2021-08-09","ids":{"openalex":"https://openalex.org/W3203039380","doi":"https://doi.org/10.1145/3458744.3473351","mag":"3203039380"},"language":"en","primary_location":{"id":"doi:10.1145/3458744.3473351","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458744.3473351","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing Workshop","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/A5013968721","display_name":"Che-Chia Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Che-Chia Lin","raw_affiliation_strings":["National Tsing Hua University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034885231","display_name":"Chao-Lin Lee","orcid":"https://orcid.org/0000-0002-4619-3843"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chao-Lin Lee","raw_affiliation_strings":["National Tsing Hua University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038803698","display_name":"Jenq\u2010Kuen Lee","orcid":"https://orcid.org/0000-0001-9919-6258"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jenq-Kuen Lee","raw_affiliation_strings":["National Tsing Hua University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078556323","display_name":"Howard Wang","orcid":"https://orcid.org/0000-0001-9905-4049"},"institutions":[{"id":"https://openalex.org/I4210148979","display_name":"MediaTek (Taiwan)","ror":"https://ror.org/05g9jck81","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210148979"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Howard Wang","raw_affiliation_strings":["MediaTek Inc., Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MediaTek Inc., Taiwan","institution_ids":["https://openalex.org/I4210148979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072319470","display_name":"Ming-Yu Hung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148979","display_name":"MediaTek (Taiwan)","ror":"https://ror.org/05g9jck81","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210148979"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ming-Yu Hung","raw_affiliation_strings":["MediaTek Inc., Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MediaTek Inc., Taiwan","institution_ids":["https://openalex.org/I4210148979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4068,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61397354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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":0.9986000061035156,"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":0.8066821098327637},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6594064235687256},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.624973714351654},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.6005095839500427},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5957998633384705},{"id":"https://openalex.org/keywords/memory-architecture","display_name":"Memory architecture","score":0.5037941336631775},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.4723159968852997},{"id":"https://openalex.org/keywords/in-memory-processing","display_name":"In-Memory Processing","score":0.46367406845092773},{"id":"https://openalex.org/keywords/interleaved-memory","display_name":"Interleaved memory","score":0.46082958579063416},{"id":"https://openalex.org/keywords/flat-memory-model","display_name":"Flat memory model","score":0.4601500630378723},{"id":"https://openalex.org/keywords/memory-refresh","display_name":"Memory refresh","score":0.45898306369781494},{"id":"https://openalex.org/keywords/registered-memory","display_name":"Registered memory","score":0.45820239186286926},{"id":"https://openalex.org/keywords/auxiliary-memory","display_name":"Auxiliary memory","score":0.4445558190345764},{"id":"https://openalex.org/keywords/memory-map","display_name":"Memory map","score":0.43957725167274475},{"id":"https://openalex.org/keywords/uniform-memory-access","display_name":"Uniform memory access","score":0.4190957546234131},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3871777057647705},{"id":"https://openalex.org/keywords/computer-memory","display_name":"Computer memory","score":0.30064234137535095},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.28701257705688477},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.274135559797287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8066821098327637},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6594064235687256},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.624973714351654},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.6005095839500427},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5957998633384705},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.5037941336631775},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.4723159968852997},{"id":"https://openalex.org/C123593499","wikidata":"https://www.wikidata.org/wiki/Q6008583","display_name":"In-Memory Processing","level":5,"score":0.46367406845092773},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.46082958579063416},{"id":"https://openalex.org/C57863822","wikidata":"https://www.wikidata.org/wiki/Q905488","display_name":"Flat memory model","level":4,"score":0.4601500630378723},{"id":"https://openalex.org/C87907426","wikidata":"https://www.wikidata.org/wiki/Q6815755","display_name":"Memory refresh","level":4,"score":0.45898306369781494},{"id":"https://openalex.org/C93446704","wikidata":"https://www.wikidata.org/wiki/Q449328","display_name":"Registered memory","level":3,"score":0.45820239186286926},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.4445558190345764},{"id":"https://openalex.org/C74426580","wikidata":"https://www.wikidata.org/wiki/Q719484","display_name":"Memory map","level":3,"score":0.43957725167274475},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.4190957546234131},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3871777057647705},{"id":"https://openalex.org/C92855701","wikidata":"https://www.wikidata.org/wiki/Q5830907","display_name":"Computer memory","level":3,"score":0.30064234137535095},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.28701257705688477},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.274135559797287},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.0},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.0},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.0},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3458744.3473351","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458744.3473351","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing Workshop","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1980891674","https://openalex.org/W2279098554","https://openalex.org/W2396622873","https://openalex.org/W2766489088","https://openalex.org/W2780077279","https://openalex.org/W2804032941","https://openalex.org/W2805566098","https://openalex.org/W3037899338","https://openalex.org/W3098220359","https://openalex.org/W6713134421","https://openalex.org/W6780119413"],"related_works":["https://openalex.org/W1979982061","https://openalex.org/W1575240748","https://openalex.org/W3093911585","https://openalex.org/W2044064773","https://openalex.org/W1837030695","https://openalex.org/W2133063415","https://openalex.org/W2062140197","https://openalex.org/W3025845664","https://openalex.org/W3180803030","https://openalex.org/W2948799117"],"abstract_inverted_index":{"As":[0],"the":[1,8,15,20,23,35,48,54,78,86,95,169,172,184],"speed":[2,16],"of":[3,10,17,40,143,171,187],"processing":[4],"units":[5],"grows":[6],"rapidly,":[7],"bottleneck":[9],"system\u2019s":[11],"performance":[12],"is":[13,22,42,108,164],"usually":[14],"memory,":[18],"and":[19,38,68,98,104,123,127],"situation":[21],"so-called":[24],"\u201dMemory":[25,36],"Wall\u201d.":[26],"There":[27],"are":[28,50],"emerging":[29],"technologies":[30],"trying":[31],"to":[32,61,64,75,114,177],"take":[33,62],"down":[34],"Wall\u201d,":[37],"one":[39],"them":[41],"Processing-in-Memory":[43,45],"(PIM).":[44],"means":[46],"that":[47],"data":[49],"processed":[51],"just":[52],"inside":[53],"memory":[55,76,79,87,162],"itself.":[56],"It":[57],"does":[58],"not":[59],"need":[60],"time":[63,186],"travel":[65],"between":[66],"CPU":[67],"Memory.":[69],"Moreover,":[70],"for":[71,111,145,155,183],"very":[72],"little":[73],"modifications":[74],"devices,":[77],"can":[80],"do":[81],"primitive":[82],"bit-wise":[83,102],"operations":[84,100,126,130],"at":[85],"side.":[88],"Binarized":[89],"Neural":[90],"Network":[91],"(BNN),":[92],"which":[93,159],"replaces":[94],"convolution\u2019s":[96],"multiplication":[97],"addition":[99],"with":[101,180],"AND":[103],"population":[105,124],"count":[106,125],"operations,":[107],"therefore":[109],"suited":[110],"utilizing":[112],"PIM":[113,120,129],"gain":[115],"performance.":[116],"This":[117],"work":[118],"architects":[119],"AND,":[121],"NOT,":[122],"enables":[128],"working":[131],"under":[132],"RISC-V":[133],"custom":[134],"instruction":[135],"encodings.":[136],"Besides,":[137],"we":[138,150],"also":[139],"utilize":[140],"TVM\u2019s":[141],"support":[142],"BNN":[144,189],"application":[146],"sources.":[147],"In":[148],"addition,":[149],"offer":[151],"a":[152,160],"new":[153],"design":[154],"BNN\u2019s":[156],"convolution":[157],"in":[158],"better":[161],"layout":[163],"considered.":[165],"With":[166],"our":[167],"design,":[168],"results":[170],"speedup":[173],"range":[174],"from":[175],"3.7x":[176],"57.3x":[178],"comparing":[179],"CPU-based":[181],"system":[182],"execution":[185],"end-to-end":[188],"model":[190],"inferences.":[191]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}