{"id":"https://openalex.org/W3016169946","doi":"https://doi.org/10.1109/dac18072.2020.9218656","title":"Bit-Parallel Vector Composability for Neural Acceleration","display_name":"Bit-Parallel Vector Composability for Neural Acceleration","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3016169946","doi":"https://doi.org/10.1109/dac18072.2020.9218656","mag":"3016169946"},"language":"en","primary_location":{"id":"doi:10.1109/dac18072.2020.9218656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18072.2020.9218656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.05333","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082499242","display_name":"Soroush Ghodrati","orcid":"https://orcid.org/0000-0001-5514-8027"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I4210108710","display_name":"Advanced Coherent Technologies (United States)","ror":"https://ror.org/01zf6g661","country_code":"US","type":"company","lineage":["https://openalex.org/I4210108710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soroush Ghodrati","raw_affiliation_strings":["University of California,Alternative Computing Technologies (ACT) Lab,San Diego","University of California\u2014San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Alternative Computing Technologies (ACT) Lab,San Diego","institution_ids":["https://openalex.org/I4210108710"]},{"raw_affiliation_string":"University of California\u2014San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082318034","display_name":"Hardik Sharma","orcid":"https://orcid.org/0000-0003-0028-013X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hardik Sharma","raw_affiliation_strings":["Bigstream, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bigstream, Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035427716","display_name":"Cliff Young","orcid":"https://orcid.org/0000-0003-2172-1651"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cliff Young","raw_affiliation_strings":["Google Inc","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037648751","display_name":"Nam Sung Kim","orcid":"https://orcid.org/0000-0002-0442-5634"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nam Sung Kim","raw_affiliation_strings":["University of Illinois Urbana-Champaign","***University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084514143","display_name":"Hadi Esmaeilzadeh","orcid":"https://orcid.org/0000-0002-8548-1039"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I4210108710","display_name":"Advanced Coherent Technologies (United States)","ror":"https://ror.org/01zf6g661","country_code":"US","type":"company","lineage":["https://openalex.org/I4210108710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hadi Esmaeilzadeh","raw_affiliation_strings":["University of California,Alternative Computing Technologies (ACT) Lab,San Diego","University of California\u2014San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Alternative Computing Technologies (ACT) Lab,San Diego","institution_ids":["https://openalex.org/I4210108710"]},{"raw_affiliation_string":"University of California\u2014San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/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"}},"topics":[{"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":0.9997000098228455,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9995999932289124,"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/operand","display_name":"Operand","score":0.9170840978622437},{"id":"https://openalex.org/keywords/composability","display_name":"Composability","score":0.7922213673591614},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7784867286682129},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6272479891777039},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.5279138088226318},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4447658956050873},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4162519872188568},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.3477553427219391},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2769413888454437},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.19061923027038574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14272862672805786}],"concepts":[{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.9170840978622437},{"id":"https://openalex.org/C2778814252","wikidata":"https://www.wikidata.org/wiki/Q5156715","display_name":"Composability","level":2,"score":0.7922213673591614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7784867286682129},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6272479891777039},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.5279138088226318},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4447658956050873},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4162519872188568},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.3477553427219391},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2769413888454437},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.19061923027038574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14272862672805786}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/dac18072.2020.9218656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18072.2020.9218656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.05333","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.05333","pdf_url":"https://arxiv.org/pdf/2004.05333","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2004.05333","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.05333","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3016169946","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.05333","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.05333","pdf_url":"https://arxiv.org/pdf/2004.05333","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6200000047683716}],"awards":[{"id":"https://openalex.org/G1072749480","display_name":null,"funder_award_id":"FA9550-17","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G1084401270","display_name":"EAGER: Language and Architecture Design for Approximation at Different Granularities","funder_award_id":"1553192","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G2225644610","display_name":null,"funder_award_id":"HR0011-18-C-0020","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G260750634","display_name":null,"funder_award_id":"FA9550-17-1","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G4790131527","display_name":null,"funder_award_id":"FA8650-20-2-7009","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5323327668","display_name":"CSR: Medium: Collaborative Research: Scale-Out Near-Data Acceleration of Machine Learning","funder_award_id":"1703812","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5452581202","display_name":null,"funder_award_id":"FA9550-17-1-0274","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5809100787","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G6064698370","display_name":null,"funder_award_id":"R01EB028350","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8289759875","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"},{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3016169946.pdf","grobid_xml":"https://content.openalex.org/works/W3016169946.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2133834148","https://openalex.org/W2285660444","https://openalex.org/W2442974303","https://openalex.org/W2508602506","https://openalex.org/W2516141709","https://openalex.org/W2518281301","https://openalex.org/W2524428287","https://openalex.org/W2563587242","https://openalex.org/W2606722458","https://openalex.org/W2625457103","https://openalex.org/W2719597717","https://openalex.org/W2751477244","https://openalex.org/W2761132374","https://openalex.org/W2786771851","https://openalex.org/W2794141774","https://openalex.org/W2909365574","https://openalex.org/W2949870694","https://openalex.org/W2963367920"],"related_works":["https://openalex.org/W3091813304","https://openalex.org/W2581189719","https://openalex.org/W1974531365","https://openalex.org/W2896415993","https://openalex.org/W1531251462","https://openalex.org/W2049142403","https://openalex.org/W2884836535","https://openalex.org/W1536960396","https://openalex.org/W2077569042","https://openalex.org/W2472255304","https://openalex.org/W2262429236","https://openalex.org/W2775543260","https://openalex.org/W2155772026","https://openalex.org/W2359058895","https://openalex.org/W2298144119","https://openalex.org/W2788825194","https://openalex.org/W2135717971","https://openalex.org/W1505735619","https://openalex.org/W3171483929","https://openalex.org/W2015443653"],"abstract_inverted_index":{"Conventional":[0],"neural":[1,80,164],"accelerators":[2],"rely":[3],"on":[4],"isolated":[5],"self-sufficient":[6],"functional":[7],"units":[8,87],"that":[9,171],"perform":[10],"an":[11,19],"atomic":[12],"operation":[13],"while":[14],"communicating":[15],"the":[16,28,37,40,61,68,74,95,105,112,154,159,186,249],"results":[17,41],"through":[18],"operand":[20],"delivery-aggregation":[21],"logic.":[22],"Each":[23],"single":[24],"unit":[25,53],"processes":[26],"all":[27,36],"bits":[29,38,93],"of":[30,39,60,70,85,94,120,139,162,175,217],"their":[31],"operands":[32,113],"atomically":[33],"and":[34,66,114,123,134,151,193,207,212,214,235,265],"produce":[35],"in":[42,78,268],"isolation.":[43],"This":[44,143],"paper":[45],"explores":[46],"a":[47,58,129,167,173,218],"different":[48],"design":[49,144,200,204,225,246],"style,":[50],"where":[51],"each":[52],"is":[54,108,166,172],"only":[55,109],"responsible":[56],"for":[57],"slice":[59],"bit-level":[62,71],"operations":[63,115],"to":[64,91,132,232,237,248],"interleave":[65],"combine":[67],"benefits":[69,261],"parallelism":[72,77,147,150],"with":[73,206,213],"abundant":[75],"data-level":[76,149],"deep":[79,195],"networks.":[81],"A":[82],"dynamic":[83],"collection":[84,174],"these":[86,223],"cooperate":[88],"at":[89,185],"runtime":[90],"generate":[92],"results,":[96],"collectively.":[97],"Such":[98],"cooperation":[99],"requires":[100],"extracting":[101],"new":[102,137],"grouping":[103],"between":[104,263],"bits,":[106],"which":[107,179,255],"possible":[110],"if":[111],"are":[116,180],"vectorizable.":[117],"The":[118,260],"abundance":[119],"Data-Level":[121],"Parallelism":[122],"mostly":[124],"repeated":[125],"execution":[126],"patterns,":[127],"provides":[128],"unique":[130],"opportunity":[131],"define":[133],"leverage":[135],"this":[136,199],"dimension":[138],"Bit-Parallel":[140,227],"Vector":[141,169,177,228],"Composability.":[142],"intersperses":[145],"bit":[146,187],"within":[148],"dynamically":[152,181],"interweaves":[153],"two":[155],"together.":[156],"As":[157],"such,":[158],"building":[160],"block":[161],"our":[163,245],"accelerator":[165],"Composable":[168],"Unit":[170],"Narrower-Bitwidth":[176],"Engines,":[178],"composed":[182],"or":[183],"decomposed":[184],"granularity.":[188],"Using":[189],"six":[190],"diverse":[191],"CNN":[192],"LSTM":[194],"networks,":[196],"we":[197],"evaluate":[198],"style":[201,247],"across":[202],"four":[203,224],"points:":[205],"without":[208,215],"algorithmic":[209],"bitwidth":[210],"heterogeneity":[211],"availability":[216],"high-bandwidth":[219],"off-chip":[220],"memory.":[221],"Across":[222],"points,":[226],"Composability":[229],"brings":[230],"(1.4\u00d7":[231],"3.5\u00d7)":[233],"speedup":[234],"(1.1\u00d7":[236],"2.7\u00d7)":[238],"energy":[239],"reduction.":[240],"We":[241],"also":[242,256],"comprehensively":[243],"compare":[244],"Nvidia's":[250],"RTX":[251],"2080":[252],"TI":[253],"GPU,":[254],"supports":[257],"INT-4":[258],"execution.":[259],"range":[262],"28.0\u00d7":[264],"33.7\u00d7":[266],"improvement":[267],"Performance-per-Watt.":[269]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}