{"id":"https://openalex.org/W4402572331","doi":"https://doi.org/10.1109/newcas58973.2024.10666304","title":"Efficient Inference of Transformers on Bare-Metal Devices with RISC-V Vector Processors","display_name":"Efficient Inference of Transformers on Bare-Metal Devices with RISC-V Vector Processors","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402572331","doi":"https://doi.org/10.1109/newcas58973.2024.10666304"},"language":"en","primary_location":{"id":"doi:10.1109/newcas58973.2024.10666304","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/newcas58973.2024.10666304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 22nd IEEE Interregional NEWCAS Conference (NEWCAS)","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/A5112627659","display_name":"Yi-Xuan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Xuan Huang","raw_affiliation_strings":["National Yang-Ming Chiao-Tung University,Department of Computer Science,Hsinchu,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang-Ming Chiao-Tung University,Department of Computer Science,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084633263","display_name":"Po\u2010Han Huang","orcid":"https://orcid.org/0000-0001-7243-0788"},"institutions":[{"id":"https://openalex.org/I4210148468","display_name":"Industrial Technology Research Institute","ror":"https://ror.org/05szzwt63","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I4210148468"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Po-Han Huang","raw_affiliation_strings":["Industrial Technology Research Institute,Electronic and Optoelectronic System Research Laboratories,Hsinchu,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Industrial Technology Research Institute,Electronic and Optoelectronic System Research Laboratories,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I4210148468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008813715","display_name":"Juin\u2010Ming Lu","orcid":"https://orcid.org/0000-0002-4219-1349"},"institutions":[{"id":"https://openalex.org/I4210148468","display_name":"Industrial Technology Research Institute","ror":"https://ror.org/05szzwt63","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I4210148468"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Juin-Ming Lu","raw_affiliation_strings":["Industrial Technology Research Institute,Electronic and Optoelectronic System Research Laboratories,Hsinchu,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Industrial Technology Research Institute,Electronic and Optoelectronic System Research Laboratories,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I4210148468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102077864","display_name":"Tay\u2013Jyi Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148468","display_name":"Industrial Technology Research Institute","ror":"https://ror.org/05szzwt63","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I4210148468"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tay-Jyi Lin","raw_affiliation_strings":["Industrial Technology Research Institute,Electronic and Optoelectronic System Research Laboratories,Hsinchu,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Industrial Technology Research Institute,Electronic and Optoelectronic System Research Laboratories,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I4210148468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056256074","display_name":"Tien-Fu Chen","orcid":"https://orcid.org/0000-0001-6925-893X"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tien-Fu Chen","raw_affiliation_strings":["National Yang-Ming Chiao-Tung University,Department of Computer Science,Hsinchu,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang-Ming Chiao-Tung University,Department of Computer Science,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12253969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"393","last_page":"397"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9631999731063843,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9631999731063843,"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/T12039","display_name":"Electron and X-Ray Spectroscopy Techniques","score":0.9559999704360962,"subfield":{"id":"https://openalex.org/subfields/2508","display_name":"Surfaces, Coatings and Films"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10558","display_name":"Advancements in Semiconductor Devices and Circuit Design","score":0.9549000263214111,"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/computer-science","display_name":"Computer science","score":0.5394369959831238},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5133318305015564},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.45160141587257385},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4332429766654968},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.25626140832901},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18171283602714539},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16335657238960266},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08767139911651611}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5394369959831238},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5133318305015564},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.45160141587257385},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4332429766654968},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.25626140832901},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18171283602714539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16335657238960266},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08767139911651611}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/newcas58973.2024.10666304","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/newcas58973.2024.10666304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 22nd IEEE Interregional NEWCAS Conference (NEWCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.46000000834465027,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W3034457371","https://openalex.org/W3178105557","https://openalex.org/W3193967165","https://openalex.org/W3211525823","https://openalex.org/W6751349269"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093"],"abstract_inverted_index":{"Most":[0],"neural":[1],"network":[2],"frameworks":[3,48],"have":[4],"only":[5],"limited":[6],"supports":[7],"for":[8,19,74],"bare-metal":[9],"devices,":[10],"where":[11,36,55],"specific":[12],"primitives":[13],"need":[14],"considering":[15],"and":[16,53,59],"hand":[17],"optimizations":[18],"such":[20],"devices":[21],"incur":[22],"a":[23,37],"substantial":[24],"development":[25],"cost.":[26],"This":[27],"paper":[28],"presents":[29],"an":[30,43],"efficient":[31],"workflow":[32],"using":[33,61],"PyTorch":[34],"Transformer,":[35],"RISC-V":[38],"device":[39],"is":[40],"used":[41],"as":[42],"example.":[44],"Models":[45],"from":[46],"different":[47],"can":[49],"be":[50],"efficiently":[51],"deployed":[52],"optimized,":[54],"bottlenecks":[56],"are":[57],"segmented":[58],"optimized":[60],"intricsic":[62],"instructions.":[63],"Moreever,":[64],"TVM":[65],"BYOC":[66],"(Bring":[67],"Your":[68],"Own":[69],"Codegen)":[70],"has":[71],"been":[72],"adopted":[73],"custom":[75],"optimizations.":[76]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
