{"id":"https://openalex.org/W2625468380","doi":"https://doi.org/10.1145/3061639.3062187","title":"A Fast and Power Efficient Architecture to Parallelize LSTM based RNN for Cognitive Intelligence Applications","display_name":"A Fast and Power Efficient Architecture to Parallelize LSTM based RNN for Cognitive Intelligence Applications","publication_year":2017,"publication_date":"2017-06-13","ids":{"openalex":"https://openalex.org/W2625468380","doi":"https://doi.org/10.1145/3061639.3062187","mag":"2625468380"},"language":"en","primary_location":{"id":"doi:10.1145/3061639.3062187","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3061639.3062187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual Design Automation Conference 2017","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/A5086894201","display_name":"Peng Ouyang","orcid":null},"institutions":[{"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"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peng Ouyang","raw_affiliation_strings":["Institute of Microelectronics, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054524841","display_name":"Shouyi Yin","orcid":"https://orcid.org/0000-0003-2309-572X"},"institutions":[{"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"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouyi Yin","raw_affiliation_strings":["Institute of Microelectronics, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I4210119392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036023084","display_name":"Shaojun Wei","orcid":"https://orcid.org/0000-0001-5117-7920"},"institutions":[{"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"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojun Wei","raw_affiliation_strings":["Institute of Microelectronics, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I4210119392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5086894201"],"corresponding_institution_ids":["https://openalex.org/I4210119392","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.2303,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.86605145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.866323709487915},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7910689115524292},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.532060444355011},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5179871320724487},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.441878080368042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42986100912094116},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.42353859543800354},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3534833490848541},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2283385992050171},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22225934267044067}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.866323709487915},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7910689115524292},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.532060444355011},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5179871320724487},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.441878080368042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42986100912094116},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42353859543800354},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3534833490848541},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2283385992050171},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22225934267044067},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3061639.3062187","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3061639.3062187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual Design Automation Conference 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W855255571","https://openalex.org/W1492347181","https://openalex.org/W1947481528","https://openalex.org/W1951742130","https://openalex.org/W2102113734","https://openalex.org/W2130942839","https://openalex.org/W2177436562","https://openalex.org/W2559655401","https://openalex.org/W2962735857","https://openalex.org/W2963211739"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W3034302643","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W2964335273","https://openalex.org/W1889624880","https://openalex.org/W2229372569"],"abstract_inverted_index":{"Long":[0],"Short-Term":[1],"Memory":[2],"(LSTM)":[3],"based":[4,68],"Recurrent":[5],"Neural":[6],"Networks":[7],"(RNNs)":[8],"are":[9],"promising":[10],"for":[11],"cognitive":[12],"intelligence":[13],"applications":[14],"like":[15,39],"speech":[16,103],"recognition,":[17],"image":[18,101],"caption":[19],"and":[20,43,52,76,87,105,120,124,132],"nature":[21],"language":[22,106],"processing,":[23],"etc.":[24],"However,":[25],"the":[26,74],"cascade":[27],"dependent":[28],"structure":[29],"in":[30],"RNN":[31],"with":[32,138],"huge":[33,92],"amount":[34,93],"of":[35,100],"power":[36,54,125],"inefficient":[37],"operations":[38,94],"multiplication,":[40],"memory":[41],"accessing":[42],"nonlinear":[44],"transformation,":[45],"could":[46],"not":[47],"guarantee":[48],"high":[49],"computing":[50,113],"speed":[51,114],"low":[53],"consumption.":[55],"In":[56],"this":[57,82,110],"work,":[58],"by":[59,115,127],"exploiting":[60],"semantic":[61,66],"correlation,":[62],"we":[63],"propose":[64],"a":[65,84],"correlation":[67],"data":[69],"pre-fetch":[70],"method":[71],"to":[72],"break":[73],"dependency":[75],"achieve":[77],"parallel":[78,86],"processing.":[79],"Based":[80],"on":[81,98],"method,":[83],"full":[85],"pipeline":[88],"architecture":[89],"that":[90],"tackles":[91],"is":[95],"designed.":[96],"Experiments":[97],"benchmarks":[99],"caption,":[102],"recognition":[104],"processing":[107],"show":[108],"that,":[109],"work":[111],"improves":[112],"5.1":[116],"times,":[117,122,129,134],"44.9":[118],"times":[119,131],"1.53":[121],"respectively,":[123,135],"efficiency":[126],"1885.7":[128],"4061.5":[130],"127.5":[133],"when":[136],"compared":[137],"state-of-the-art":[139],"works.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}