{"id":"https://openalex.org/W4400224496","doi":"https://doi.org/10.1145/3649153.3649181","title":"RV-GEMM: Neural Network Inference Acceleration with Near-Memory GEMM Instructions on RISC-V","display_name":"RV-GEMM: Neural Network Inference Acceleration with Near-Memory GEMM Instructions on RISC-V","publication_year":2024,"publication_date":"2024-05-07","ids":{"openalex":"https://openalex.org/W4400224496","doi":"https://doi.org/10.1145/3649153.3649181"},"language":"en","primary_location":{"id":"doi:10.1145/3649153.3649181","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649153.3649181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM International Conference on Computing Frontiers","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/A5100663083","display_name":"Xingbo Wang","orcid":"https://orcid.org/0000-0001-9349-2718"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingbo Wang","raw_affiliation_strings":["Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9349-2718","affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705987","display_name":"Chenxi Feng","orcid":"https://orcid.org/0009-0007-4376-3373"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxi Feng","raw_affiliation_strings":["Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0007-4376-3373","affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032499618","display_name":"Bingzhen Chen","orcid":"https://orcid.org/0009-0004-6562-9536"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingzhen Chen","raw_affiliation_strings":["Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0004-6562-9536","affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341277","display_name":"Qi Wang","orcid":"https://orcid.org/0000-0002-2644-2873"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Qi Wang","raw_affiliation_strings":["The University of British Columbia, Vancouver, Canada"],"raw_orcid":"https://orcid.org/0000-0002-2644-2873","affiliations":[{"raw_affiliation_string":"The University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103194141","display_name":"Yucong Huang","orcid":"https://orcid.org/0000-0002-8499-4254"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yucong Huang","raw_affiliation_strings":["Hong Kong University of Science and Technology Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-8499-4254","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007760320","display_name":"Terry Tao Ye","orcid":"https://orcid.org/0000-0002-4359-3550"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Terry Tao Ye","raw_affiliation_strings":["Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-4359-3550","affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8749,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7393915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"302","last_page":"305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9970999956130981,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9970999956130981,"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/T10320","display_name":"Neural Networks and Applications","score":0.98089998960495,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9733999967575073,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8324670195579529},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.607181966304779},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5292959213256836},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5221548080444336},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48817354440689087},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3293841481208801},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3275609612464905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2631048858165741}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324670195579529},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.607181966304779},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5292959213256836},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5221548080444336},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48817354440689087},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3293841481208801},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3275609612464905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2631048858165741},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3649153.3649181","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649153.3649181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-142379","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-142379","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2557409653","https://openalex.org/W2963255460","https://openalex.org/W3005924570","https://openalex.org/W3016085798","https://openalex.org/W3024621361","https://openalex.org/W3208112639"],"related_works":["https://openalex.org/W2390829436","https://openalex.org/W1989791859","https://openalex.org/W2565094479","https://openalex.org/W602859758","https://openalex.org/W2006439817","https://openalex.org/W1971289376","https://openalex.org/W2379101322","https://openalex.org/W2055243143","https://openalex.org/W1992553864","https://openalex.org/W2776207444"],"abstract_inverted_index":{"General":[0],"Matrix":[1],"Multiply":[2],"(GEMM),":[3],"as":[4],"a":[5],"fundamental":[6],"operation":[7],"in":[8,15,79,96],"neural":[9],"network,":[10],"plays":[11],"an":[12],"important":[13],"role":[14],"artificial":[16],"intelligence":[17],"and":[18,42,50,83,122,134,146],"signal":[19],"processing":[20],"applications.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25,46],"proposed":[26],"three":[27,67],"SMID":[28],"RISC-V":[29,112],"custom":[30,69],"instructions":[31],"to":[32,60,109],"accelerate":[33],"GEMM":[34,57,68,115],"computations,":[35],"supporting":[36],"multiple":[37],"precisions":[38,118],"including":[39],"32-bit,":[40,120],"16-bit":[41,121],"8-bit":[43,123],"fixed.":[44],"Furthermore,":[45],"implemented":[47,84],"address":[48],"calculation":[49],"loop":[51],"control":[52],"units":[53],"along":[54,71],"with":[55,72,100],"the":[56,62,73,80,86,110,125],"acceleration":[58],"module":[59],"reduce":[61],"memory":[63],"access":[64],"overhead.":[65],"These":[66],"instructions,":[70],"near-memory":[74],"optimization":[75],"units,":[76],"were":[77],"incorporated":[78],"RV-GEMM":[81,126],"processor":[82,127],"on":[85],"FPGA":[87],"platform":[88],"for":[89,104,114],"speedup":[90,129],"evaluation.":[91],"It":[92],"was":[93],"also":[94,140],"compiled":[95],"Synopsys":[97],"Design":[98],"Compiler":[99],"CMOS":[101],"55nm":[102],"process":[103],"hardware":[105],"overhead":[106],"estimation.":[107],"Compared":[108],"baseline":[111],"processor,":[113],"computations":[116],"under":[117],"of":[119,131],"fixed,":[124],"achieved":[128],"ratios":[130],"15.8\u00d7,":[132],"28.7\u00d7":[133],"42.5\u00d7.":[135],"The":[136],"peak":[137],"energy":[138],"efficiency":[139],"reached":[141],"260":[142],"GOPS/W,":[143,148],"420":[144],"GOPS/W":[145],"609":[147],"respectively.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}