{"id":"https://openalex.org/W4417166181","doi":"https://doi.org/10.1145/3742872.3757073","title":"RISC-TAE: Instruction Set Extension for Transformer Model Acceleration","display_name":"RISC-TAE: Instruction Set Extension for Transformer Model Acceleration","publication_year":2025,"publication_date":"2025-09-28","ids":{"openalex":"https://openalex.org/W4417166181","doi":"https://doi.org/10.1145/3742872.3757073"},"language":null,"primary_location":{"id":"doi:10.1145/3742872.3757073","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3742872.3757073","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3742872.3757073","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Compilers, Architecture, and Synthesis for Embedded Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3742872.3757073","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5105939406","display_name":"Fei Liu","orcid":"https://orcid.org/0009-0004-0886-8696"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fei Liu","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103858181","display_name":"Yanping Shao","orcid":"https://orcid.org/0009-0004-8039-6689"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanping Shao","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005924574","display_name":"Zhouquan Liu","orcid":"https://orcid.org/0009-0009-5338-139X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhouquan Liu","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101985792","display_name":"Jing Zhang","orcid":"https://orcid.org/0009-0002-7087-2528"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053514899","display_name":"Junbo Tie","orcid":"https://orcid.org/0000-0002-8989-8931"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junbo Tie","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101178638","display_name":"Mingche Lai","orcid":"https://orcid.org/0009-0003-5681-0010"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingche Lai","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389329","display_name":"Gang Chen","orcid":"https://orcid.org/0000-0003-4234-1359"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Chen","raw_affiliation_strings":["Sun Yat-sen University, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069512300","display_name":"Libo Huang","orcid":"https://orcid.org/0000-0002-8307-6742"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libo Huang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5105939406"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42998748,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.5482000112533569,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.5482000112533569,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.11129999905824661,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.09229999780654907,"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/dataflow","display_name":"Dataflow","score":0.6169000267982483},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5931000113487244},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5820000171661377},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.46470001339912415},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.37880000472068787},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.33570000529289246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7181000113487244},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.6169000267982483},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5931000113487244},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5820000171661377},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.37599998712539673},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.33239999413490295},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3248000144958496},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.30889999866485596},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.28299999237060547},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C17321440","wikidata":"https://www.wikidata.org/wiki/Q184909","display_name":"Flyback transformer","level":4,"score":0.2680000066757202},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.259799987077713},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3742872.3757073","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3742872.3757073","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3742872.3757073","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Compilers, Architecture, and Synthesis for Embedded Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3742872.3757073","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3742872.3757073","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3742872.3757073","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Compilers, Architecture, and Synthesis for Embedded Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1023919524","display_name":null,"funder_award_id":", Grant","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4459438753","display_name":null,"funder_award_id":"62272475","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G881319392","display_name":null,"funder_award_id":"62102433","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417166181.pdf","grobid_xml":"https://content.openalex.org/works/W4417166181.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2936567838","https://openalex.org/W4386453603"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"RISC-TAE(Transformer":[3],"Acceleration":[4],"Engine),":[5],"a":[6,80],"RISC-V":[7,39],"instruction":[8],"set":[9],"extension":[10],"with":[11,33],"microarchitectural":[12],"co-design,":[13],"to":[14],"meet":[15],"the":[16],"performance":[17],"and":[18,46,59,66],"energy-efficiency":[19],"requirements":[20],"of":[21],"Transformer":[22,85],"models":[23],"in":[24,50],"edge":[25,84],"scenes.The":[26],"design":[27],"integrates":[28],"operator-specialized":[29],"computing":[30],"units":[31],"(GEMM/Softmax/GELU)":[32],"hardware-managed":[34],"dataflow":[35],"orchestration":[36],"through":[37],"custom":[38],"instructions,":[40],"effectively":[41],"resolving":[42],"energy":[43],"efficiency":[44],"bottlenecks":[45],"memory":[47],"access":[48],"fragmentation":[49],"existing":[51],"solutions.":[52],"Experiments":[53],"demonstrate":[54],"that":[55],"RISC-TAE":[56],"achieves":[57],"23.35\u00d7":[58],"8.01\u00d7":[60],"speedups":[61],"over":[62],"scalar":[63],"processor":[64,68],"CVA6":[65],"vector":[67],"ARA":[69],"respectively":[70],"for":[71,83],"BERT":[72],"inference,":[73],"while":[74],"outperforming":[75],"RISC-VTF":[76],"by":[77],"1.4\u00d7,":[78],"providing":[79],"scalable":[81],"solution":[82],"deployment.":[86]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-09T00:00:00"}
