{"id":"https://openalex.org/W4401308326","doi":"https://doi.org/10.1145/3675018.3675029","title":"Convex: A RISC-V Instruction Set Extension Scheme for Accelerating Convolution Operations on MCUs","display_name":"Convex: A RISC-V Instruction Set Extension Scheme for Accelerating Convolution Operations on MCUs","publication_year":2024,"publication_date":"2024-06-07","ids":{"openalex":"https://openalex.org/W4401308326","doi":"https://doi.org/10.1145/3675018.3675029"},"language":"en","primary_location":{"id":"doi:10.1145/3675018.3675029","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3675018.3675029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 8th International Conference on High Performance Compilation, Computing and Communications","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/A5102706859","display_name":"Heming Liu","orcid":"https://orcid.org/0009-0005-9823-4554"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Heming Liu","raw_affiliation_strings":["School of Integrated Circuits, Guangdong University of Technology, China"],"raw_orcid":"https://orcid.org/0009-0005-9823-4554","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Guangdong University of Technology, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022175129","display_name":"Xian Lin","orcid":"https://orcid.org/0000-0002-5780-5948"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Lin","raw_affiliation_strings":["School of Integrated Circuits, Guangdong University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-5780-5948","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Guangdong University of Technology, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090873606","display_name":"Xin Zheng","orcid":"https://orcid.org/0000-0003-4931-9664"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zheng","raw_affiliation_strings":["School of Integrated Circuits, Guangdong University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0003-4931-9664","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Guangdong University of Technology, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050076555","display_name":"Shuting Cai","orcid":"https://orcid.org/0000-0002-2842-6439"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuting Cai","raw_affiliation_strings":["School of Integrated Circuits, Guangdong University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-2842-6439","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Guangdong University of Technology, China","institution_ids":["https://openalex.org/I139024713"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102706859"],"corresponding_institution_ids":["https://openalex.org/I139024713"],"apc_list":null,"apc_paid":null,"fwci":1.4231,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.81642813,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"133","last_page":"138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9955999851226807,"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":0.9955999851226807,"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":0.9929999709129333,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/extension","display_name":"Extension (predicate logic)","score":0.6727670431137085},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6395716071128845},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.6029940843582153},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5598068833351135},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.5417545437812805},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.5290319323539734},{"id":"https://openalex.org/keywords/reduced-instruction-set-computing","display_name":"Reduced instruction set computing","score":0.5195046663284302},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48877832293510437},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3615003526210785},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.337246835231781},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28809142112731934},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19763115048408508},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15236571431159973},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.0667448341846466}],"concepts":[{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.6727670431137085},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6395716071128845},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.6029940843582153},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5598068833351135},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.5417545437812805},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.5290319323539734},{"id":"https://openalex.org/C126298526","wikidata":"https://www.wikidata.org/wiki/Q189376","display_name":"Reduced instruction set computing","level":3,"score":0.5195046663284302},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48877832293510437},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3615003526210785},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.337246835231781},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28809142112731934},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19763115048408508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15236571431159973},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0667448341846466},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3675018.3675029","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3675018.3675029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 8th International Conference on High Performance Compilation, Computing and Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W3007729836","https://openalex.org/W3019985649","https://openalex.org/W3036554530","https://openalex.org/W3109391100","https://openalex.org/W3123928534","https://openalex.org/W3172744943","https://openalex.org/W3193967165","https://openalex.org/W3203828254"],"related_works":["https://openalex.org/W2538644970","https://openalex.org/W4376881175","https://openalex.org/W4310584696","https://openalex.org/W4385730960","https://openalex.org/W4237840813","https://openalex.org/W4364295250","https://openalex.org/W2128502296","https://openalex.org/W2993622674","https://openalex.org/W1833044483","https://openalex.org/W4382053335"],"abstract_inverted_index":{"In":[0],"the":[1,31,80,96,102,104,119],"era":[2],"of":[3,14,35,83],"Artificial":[4],"Intelligence":[5],"(AI),":[6],"edge":[7],"computing":[8],"gains":[9],"widespread":[10],"application":[11],"through":[12],"Internet":[13],"Things":[15],"(IoT)":[16],"devices,":[17],"which":[18],"leverage":[19],"microcontrollers":[20,40],"(MCUs)":[21],"to":[22,78,101],"provide":[23],"computational":[24],"power.":[25],"It":[26],"is":[27],"beneficial":[28],"for":[29,45],"overcoming":[30],"high":[32],"latency":[33],"limitations":[34],"cloud":[36],"computing.":[37],"However,":[38],"cost-constrained":[39],"require":[41],"more":[42],"efficient":[43],"support":[44,50],"convolutional":[46,120],"operations,":[47],"including":[48],"hardware":[49],"such":[51],"as":[52],"instruction":[53,62,92],"set":[54,63],"extensions.":[55],"This":[56],"paper":[57],"proposes":[58],"a":[59,107,114],"high-performance":[60],"RISC-V":[61,91],"extension":[64,93],"scheme":[65,94],"that":[66],"utilizes":[67],"bit":[68],"concatenation":[69],"extension,":[70],"weight":[71],"storage":[72],"optimization,":[73],"and":[74,113],"activation":[75],"values":[76],"reuse":[77],"enhance":[79],"inference":[81,111],"speed":[82,112],"Convolutional":[84],"Neural":[85],"Networks":[86],"(CNNs).":[87],"We":[88],"integrate":[89],"this":[90],"into":[95],"E203":[97],"(E203-Convex)":[98],"processor.":[99],"Compared":[100],"E203,":[103],"E203-Convex":[105],"achieves":[106],"23.5x":[108],"improvement":[109,116],"in":[110,118],"107.2x":[115],"specifically":[117],"layer.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
