{"id":"https://openalex.org/W3197704349","doi":"https://doi.org/10.1109/socc49529.2020.9524784","title":"A Configurable FPGA Accelerator of Bi-LSTM Inference with Structured Sparsity","display_name":"A Configurable FPGA Accelerator of Bi-LSTM Inference with Structured Sparsity","publication_year":2020,"publication_date":"2020-09-08","ids":{"openalex":"https://openalex.org/W3197704349","doi":"https://doi.org/10.1109/socc49529.2020.9524784","mag":"3197704349"},"language":"en","primary_location":{"id":"doi:10.1109/socc49529.2020.9524784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/socc49529.2020.9524784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 33rd International System-on-Chip Conference (SOCC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5081601767","display_name":"Shouliang Guo","orcid":null},"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":"Shouliang Guo","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,Nanjing,China","School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066888122","display_name":"Chao Fang","orcid":"https://orcid.org/0000-0003-3430-1189"},"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":"Chao Fang","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,Nanjing,China","School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019940239","display_name":"Jun Lin","orcid":"https://orcid.org/0000-0003-2760-4333"},"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":"Jun Lin","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,Nanjing,China","School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, 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,School of Electronic Science and Engineering,Nanjing,China","School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.6762,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66279416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"174","last_page":"179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9902999997138977,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9879000186920166,"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":0.8386595249176025},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7873520255088806},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7138546705245972},{"id":"https://openalex.org/keywords/stratix","display_name":"Stratix","score":0.6404085755348206},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.49492162466049194},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.48545652627944946},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47367244958877563},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.47236210107803345},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4371016025543213},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3746753931045532},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.37414488196372986},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3709948658943176},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3584824502468109},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20572251081466675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19672459363937378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8386595249176025},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7873520255088806},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7138546705245972},{"id":"https://openalex.org/C2776277307","wikidata":"https://www.wikidata.org/wiki/Q22074755","display_name":"Stratix","level":3,"score":0.6404085755348206},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.49492162466049194},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.48545652627944946},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47367244958877563},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.47236210107803345},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4371016025543213},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3746753931045532},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.37414488196372986},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3709948658943176},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3584824502468109},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20572251081466675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19672459363937378},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/socc49529.2020.9524784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/socc49529.2020.9524784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 33rd International System-on-Chip Conference (SOCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8899999856948853}],"awards":[{"id":"https://openalex.org/G4988504959","display_name":null,"funder_award_id":"61604068","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1635512741","https://openalex.org/W1940872118","https://openalex.org/W2005708641","https://openalex.org/W2064675550","https://openalex.org/W2193413348","https://openalex.org/W2525778437","https://openalex.org/W2730834423","https://openalex.org/W2940345045","https://openalex.org/W2962820060","https://openalex.org/W2964307104","https://openalex.org/W4298580827","https://openalex.org/W6687566353","https://openalex.org/W6727690538","https://openalex.org/W6748409065"],"related_works":["https://openalex.org/W4322616423","https://openalex.org/W3196579076","https://openalex.org/W1509211761","https://openalex.org/W2518118925","https://openalex.org/W4365398249","https://openalex.org/W2391299576","https://openalex.org/W4296563896","https://openalex.org/W4378806073","https://openalex.org/W4286233754","https://openalex.org/W3147787617"],"abstract_inverted_index":{"To":[0],"deploy":[1],"Bi-directional":[2],"Long":[3],"Short-Term":[4],"Memory":[5],"(Bi-LSTM)":[6],"on":[7,44,84,98,114,125,138,145],"resource-constrained":[8],"embedded":[9],"devices,":[10],"this":[11],"work":[12],"presents":[13],"a":[14,23,31,36,65],"configurable":[15],"FPGA-based":[16],"Bi-LSTM":[17,25,68,85,117],"accelerator":[18,60,109,132],"enabling":[19],"structured":[20,37,66,115],"compression.":[21],"Firstly,":[22],"dense":[24],"model":[26,69],"is":[27,48,61,77],"thoroughly":[28],"slimed":[29],"by":[30,51],"hybrid":[32],"quantization":[33],"scheme":[34],"and":[35,93,127,135,141],"top-k":[38],"pruning.":[39],"Secondly,":[40],"the":[41,52,58,72,99,107,123,129],"energy":[42,146],"consumption":[43],"external":[45],"memory":[46],"access":[47],"significantly":[49],"reduced":[50],"proposed":[53,59,108],"row-reuse":[54],"computing":[55],"pattern.":[56],"Finally,":[57],"capable":[62],"of":[63,95],"handling":[64],"sparse":[67,116],"benefitting":[70],"from":[71],"algorithm-hardware":[73],"co-design":[74],"workflow.":[75],"It":[76],"also":[78],"flexible":[79],"to":[80],"perform":[81],"inference":[82],"tasks":[83],"models":[86],"with":[87,122],"any":[88],"feature":[89],"dimension,":[90],"sequence":[91],"length,":[92],"number":[94],"layers.":[96],"Implemented":[97],"Intel":[100],"Cyclone":[101],"V":[102],"SXC5":[103],"SoC":[104],"FPGA":[105,131],"platform,":[106],"can":[110],"achieve":[111],"189.69":[112],"GOPs":[113],"networks":[118],"without":[119],"batching.":[120],"Compared":[121],"implementations":[124],"CPU":[126],"GPU,":[128],"low-cost":[130],"achieves":[133],"43.5x":[134],"6.3x":[136],"speedup":[137],"latency,":[139],"520.9x":[140],"46.5":[142],"x":[143],"improvement":[144],"efficiency,":[147],"respectively.":[148]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}