{"id":"https://openalex.org/W3110773471","doi":"https://doi.org/10.1145/3400302.3415697","title":"Optimizing stochastic computing for low latency inference of convolutional neural networks","display_name":"Optimizing stochastic computing for low latency inference of convolutional neural networks","publication_year":2020,"publication_date":"2020-11-02","ids":{"openalex":"https://openalex.org/W3110773471","doi":"https://doi.org/10.1145/3400302.3415697","mag":"3110773471"},"language":"en","primary_location":{"id":"doi:10.1145/3400302.3415697","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3400302.3415697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th International Conference on Computer-Aided Design","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/A5100438512","display_name":"Zhiyuan Chen","orcid":"https://orcid.org/0000-0002-4915-1593"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiyuan Chen","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068840674","display_name":"Yufei Ma","orcid":"https://orcid.org/0000-0002-2670-524X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Ma","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100696999","display_name":"Zhongfeng Wang","orcid":"https://orcid.org/0000-0002-7227-4786"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongfeng Wang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100438512"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.3084,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6251133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"200","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11321","display_name":"Error Correcting Code Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11321","display_name":"Error Correcting Code Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9979000091552734,"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"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9950000047683716,"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/stochastic-computing","display_name":"Stochastic computing","score":0.8601832389831543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8168536424636841},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.7233397960662842},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6628493070602417},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6235100626945496},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5869705080986023},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5579925179481506},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5369135737419128},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5257992148399353},{"id":"https://openalex.org/keywords/datapath","display_name":"Datapath","score":0.4518154263496399},{"id":"https://openalex.org/keywords/adder","display_name":"Adder","score":0.44650745391845703},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4434088468551636},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4271836578845978},{"id":"https://openalex.org/keywords/cmos","display_name":"CMOS","score":0.42705973982810974},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4103120267391205},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3982265889644623},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3174118399620056},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.3163298964500427},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.2724882662296295},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.1319778561592102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1238771378993988}],"concepts":[{"id":"https://openalex.org/C2780971903","wikidata":"https://www.wikidata.org/wiki/Q2933705","display_name":"Stochastic computing","level":3,"score":0.8601832389831543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8168536424636841},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.7233397960662842},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6628493070602417},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6235100626945496},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5869705080986023},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5579925179481506},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5369135737419128},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5257992148399353},{"id":"https://openalex.org/C2781198647","wikidata":"https://www.wikidata.org/wiki/Q1633673","display_name":"Datapath","level":2,"score":0.4518154263496399},{"id":"https://openalex.org/C164620267","wikidata":"https://www.wikidata.org/wiki/Q376953","display_name":"Adder","level":3,"score":0.44650745391845703},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4434088468551636},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4271836578845978},{"id":"https://openalex.org/C46362747","wikidata":"https://www.wikidata.org/wiki/Q173431","display_name":"CMOS","level":2,"score":0.42705973982810974},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4103120267391205},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3982265889644623},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3174118399620056},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.3163298964500427},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2724882662296295},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.1319778561592102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1238771378993988},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3400302.3415697","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3400302.3415697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th International Conference on Computer-Aided Design","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":20,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2003056114","https://openalex.org/W2051898848","https://openalex.org/W2108598243","https://openalex.org/W2117130368","https://openalex.org/W2219959730","https://openalex.org/W2285660444","https://openalex.org/W2294282016","https://openalex.org/W2402098947","https://openalex.org/W2533474659","https://openalex.org/W2614053718","https://openalex.org/W2625226188","https://openalex.org/W2795915628","https://openalex.org/W2802559652","https://openalex.org/W2809046730","https://openalex.org/W2908696560","https://openalex.org/W2912949188","https://openalex.org/W2944948997","https://openalex.org/W2944970523","https://openalex.org/W2963674932"],"related_works":["https://openalex.org/W2996717348","https://openalex.org/W1044727952","https://openalex.org/W1998118780","https://openalex.org/W4319431600","https://openalex.org/W2537803004","https://openalex.org/W1578907948","https://openalex.org/W2088062563","https://openalex.org/W3104287241","https://openalex.org/W2768509551","https://openalex.org/W3213934210"],"abstract_inverted_index":{"The":[0,176],"appealing":[1],"property":[2,126],"of":[3,70,90,100,110,127,151],"low":[4,6],"area,":[5],"power,":[7],"flexible":[8],"precision,":[9],"and":[10,105,118,161,186,204],"high":[11],"bit":[12,47,67,129],"error":[13],"tolerance":[14],"has":[15,74],"made":[16],"Stochastic":[17],"Computing":[18],"(SC)":[19],"a":[20,71],"promising":[21],"alternative":[22],"to":[23,38,56,62,77,113,136,157,209],"conventional":[24],"binary":[25],"arithmetic":[26],"for":[27],"many":[28],"computation":[29],"intensive":[30],"tasks,":[31],"e.g.,":[32],"convolutional":[33],"neural":[34],"networks":[35],"(CNNs).":[36],"However,":[37],"relieve":[39],"the":[40,66,80,87,98,106,125,138,145,148,165],"intrinsic":[41],"fluctuation":[42],"noise":[43],"in":[44,52],"SC,":[45],"long":[46],"stream":[48],"is":[49,131,184],"normally":[50],"required":[51],"SC-based":[53,152],"CNN":[54,111,178,213],"accelerators":[55],"achieve":[57],"satisfactory":[58],"accuracy,":[59],"which":[60,122,196],"leads":[61],"extortionate":[63],"latency.":[64],"Although":[65],"parallel":[68,149],"structure":[69],"SC":[72,101,174,211],"multiplier":[73],"been":[75],"proposed":[76,132,177],"reduce":[78,137],"latency,":[79],"resulting":[81],"extra":[82],"overhead":[83],"still":[84],"considerably":[85],"degrade":[86],"overall":[88,107,146],"efficiency":[89],"SC.":[91,115],"In":[92],"this":[93],"paper,":[94],"we":[95],"optimize":[96],"both":[97],"micro-architecture":[99],"multiply-and-accumulate":[102],"(MAC)":[103],"unit":[104],"acceleration":[108],"scheme":[109],"accelerator":[112,179],"favor":[114],"An":[116],"optimized":[117],"scalable":[119],"SC-MAC":[120,182],"unit,":[121],"fully":[123],"utilizes":[124],"low-discrepancy":[128],"stream,":[130],"with":[133,140,180],"adjustable":[134],"parameters":[135],"latency":[139],"minor":[141],"area":[142,206],"increase.":[143],"For":[144],"accelerator,":[147],"dimensions":[150],"MAC":[153],"array":[154,183],"are":[155],"extended":[156,181],"reuse":[158],"hardware":[159],"resources":[160],"improve":[162],"throughput,":[163],"since":[164],"judiciously":[166],"chosen":[167],"loop":[168],"unrolling":[169],"strategy":[170],"can":[171],"better":[172],"benefit":[173],"operations.":[175],"synthesized":[185],"demonstrated":[187],"using":[188],"TSMC":[189],"28nm":[190],"CMOS":[191],"on":[192],"several":[193],"representative":[194],"CNNs,":[195],"gains":[197],"2\u00d7":[198],"performance":[199],"speedup,":[200],"2.8\u00d7":[201],"energy":[202],"savings":[203],"15%":[205],"reduction":[207],"compared":[208],"state-of-the-art":[210],"based":[212],"accelerator.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}