{"id":"https://openalex.org/W4403918469","doi":"https://doi.org/10.1109/access.2024.3488033","title":"Auto Batching Scheme for Optimizing LSTM Inference on FPGA Platforms","display_name":"Auto Batching Scheme for Optimizing LSTM Inference on FPGA Platforms","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403918469","doi":"https://doi.org/10.1109/access.2024.3488033"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3488033","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3488033","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3488033","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110111705","display_name":"Byoung Jin Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byoung Jin Kim","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0009-8228-5655","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084016800","display_name":"Eui-Young Chung","orcid":"https://orcid.org/0000-0003-2013-8763"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eui-Young Chung","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-2013-8763","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.1856,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51723899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"12","issue":null,"first_page":"159380","last_page":"159394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14276","display_name":"Power Systems and Technologies","score":0.11620000004768372,"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/T14276","display_name":"Power Systems and Technologies","score":0.11620000004768372,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.10029999911785126,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T12810","display_name":"Real-time simulation and control systems","score":0.09350000321865082,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.8148404359817505},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7799696922302246},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.7662075757980347},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7357339859008789},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3915168046951294},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2807925343513489},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07506269216537476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148404359817505},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7799696922302246},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.7662075757980347},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7357339859008789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3915168046951294},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2807925343513489},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07506269216537476},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3488033","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3488033","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b183cd915e424c9d8b354318380c98e0","is_oa":true,"landing_page_url":"https://doaj.org/article/b183cd915e424c9d8b354318380c98e0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 159380-159394 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3488033","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3488033","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5052186987","display_name":null,"funder_award_id":"20019956","funder_id":"https://openalex.org/F4320330746","funder_display_name":"Korea Semiconductor Research Consortium"},{"id":"https://openalex.org/G5096367102","display_name":null,"funder_award_id":"1415181094","funder_id":"https://openalex.org/F4320321681","funder_display_name":"Ministry of Trade, Industry and Energy"}],"funders":[{"id":"https://openalex.org/F4320321681","display_name":"Ministry of Trade, Industry and Energy","ror":"https://ror.org/008nkqk13"},{"id":"https://openalex.org/F4320330746","display_name":"Korea Semiconductor Research Consortium","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1689711448","https://openalex.org/W2588448445","https://openalex.org/W2757698722","https://openalex.org/W2788838111","https://openalex.org/W2962760690","https://openalex.org/W2963679555","https://openalex.org/W2970716438","https://openalex.org/W2971507840","https://openalex.org/W2984242728","https://openalex.org/W3034833480","https://openalex.org/W3048034223","https://openalex.org/W3114397406","https://openalex.org/W3150182863","https://openalex.org/W3154451338","https://openalex.org/W3158444059","https://openalex.org/W3161782335","https://openalex.org/W3174954176","https://openalex.org/W3187677606","https://openalex.org/W4200157451","https://openalex.org/W4206796315","https://openalex.org/W4207032740","https://openalex.org/W4213420788","https://openalex.org/W4226023758","https://openalex.org/W4280577395","https://openalex.org/W4280624308","https://openalex.org/W4285144065","https://openalex.org/W4285741594","https://openalex.org/W4300865759","https://openalex.org/W4312686336","https://openalex.org/W4313172518","https://openalex.org/W4362714362","https://openalex.org/W4377009115","https://openalex.org/W4388145607","https://openalex.org/W4389352378","https://openalex.org/W4392945499"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2111241003","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2355315220","https://openalex.org/W4200391368","https://openalex.org/W2210979487"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"innovative":[4],"auto":[5,119],"batching":[6,24,59,64,76,120,131],"scheme":[7,121,148],"designed":[8],"to":[9,37,46,124,165],"optimize":[10],"Long":[11],"Short-Term":[12],"Memory":[13],"(LSTM)":[14],"inference":[15],"on":[16],"Field-Programmable":[17],"Gate":[18],"Array":[19],"(FPGA)":[20],"platforms.":[21],"Existing":[22],"block":[23,58,63,75,130],"methods":[25],"face":[26],"challenges":[27],"with":[28,60,138],"LSTM":[29],"models":[30],"that":[31,79],"have":[32],"large":[33],"hidden":[34],"sizes":[35],"due":[36],"insufficient":[38],"on-chip":[39,82,89,140],"memory,":[40],"which":[41],"impedes":[42],"prefetching":[43],"and":[44,49,104,112,157],"leads":[45],"repeated":[47],"evictions":[48],"reloads,":[50],"significantly":[51],"reducing":[52],"processing":[53],"utilization.":[54],"Our":[55,118],"approach":[56],"extends":[57],"weight":[61],"stationary":[62],"(WSBB),":[65],"allowing":[66],"computation":[67],"without":[68],"stalls":[69],"regardless":[70],"of":[71,114,146],"prefetch":[72],"availability.Additionally,":[73],"bypass-enabled":[74],"(BEBB)":[77],"ensures":[78],"even":[80,137],"when":[81],"memory":[83,94],"is":[84],"insufficient,":[85],"it":[86],"prevents":[87],"contamination":[88],"while":[90,132],"fully":[91],"leveraging":[92],"off-chip":[93],"bandwidth.":[95],"Experimental":[96],"results":[97],"from":[98],"both":[99],"synthetic":[100],"benchmarks":[101],"(Deepbench":[102],"suite)":[103],"real-world":[105],"applications":[106],"(RNN-T)":[107],"validate":[108],"the":[109,115,143,155,166],"superior":[110],"performance":[111],"efficiency":[113,162],"proposed":[116],"method.":[117],"demonstrates":[122],"up":[123],"3.7":[125],"times":[126,152,159],"speedup":[127,153],"over":[128,154],"previous":[129],"maintaining":[133],"high":[134],"computational":[135],"efficiency,":[136],"limited":[139],"memory.":[141],"Furthermore,":[142],"FPGA-based":[144],"implementation":[145],"our":[147],"achieves":[149],"a":[150],"5":[151],"CPU":[156],"4.3":[158],"higher":[160],"energy":[161],"(GFLOP/s/W)":[163],"compared":[164],"GPU.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}