{"id":"https://openalex.org/W4412652998","doi":"https://doi.org/10.1145/3756322","title":"Optimizing Sparse Matrix Convolution on RISC-V Core: Custom Instructions for Embedded System","display_name":"Optimizing Sparse Matrix Convolution on RISC-V Core: Custom Instructions for Embedded System","publication_year":2025,"publication_date":"2025-07-26","ids":{"openalex":"https://openalex.org/W4412652998","doi":"https://doi.org/10.1145/3756322"},"language":"en","primary_location":{"id":"doi:10.1145/3756322","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3756322","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-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/A5012678245","display_name":"Huachen Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huachen Zhang","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University"],"raw_orcid":"https://orcid.org/0009-0005-1364-0976","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101122041","display_name":"Jianyang Ding","orcid":"https://orcid.org/0009-0005-9902-9755"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyang Ding","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University"],"raw_orcid":"https://orcid.org/0009-0005-9902-9755","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111296495","display_name":"Bowen Jiang","orcid":"https://orcid.org/0009-0003-8171-9008"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Jiang","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University"],"raw_orcid":"https://orcid.org/0009-0003-8171-9008","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109373616","display_name":"Tsung-Che Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianshuo Lu","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University"],"raw_orcid":"https://orcid.org/0009-0005-9301-4130","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Xu","orcid":"https://orcid.org/0009-0002-0281-9506"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xu","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University"],"raw_orcid":"https://orcid.org/0009-0002-0281-9506","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024443501","display_name":"Zhilei Chai","orcid":"https://orcid.org/0000-0003-3822-1653"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhilei Chai","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University"],"raw_orcid":"https://orcid.org/0000-0003-3822-1653","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University","institution_ids":["https://openalex.org/I111599522"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I111599522"],"apc_list":null,"apc_paid":null,"fwci":3.1718,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9143002,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"24","issue":"6","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9987000226974487,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9987000226974487,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9983999729156494,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980000257492065,"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":0.6647694110870361},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5336874723434448},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.511158287525177},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4811312258243561},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.45722997188568115},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4422544538974762},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.33335041999816895},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3303828239440918},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32436060905456543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16535711288452148},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.10839155316352844},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08470335602760315}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6647694110870361},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5336874723434448},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.511158287525177},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4811312258243561},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.45722997188568115},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4422544538974762},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.33335041999816895},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3303828239440918},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32436060905456543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16535711288452148},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.10839155316352844},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08470335602760315},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3756322","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3756322","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2232809325","display_name":null,"funder_award_id":"JUSRP202501072","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2097117768","https://openalex.org/W2194775991","https://openalex.org/W2442974303","https://openalex.org/W2489529491","https://openalex.org/W2618530766","https://openalex.org/W2883283076","https://openalex.org/W2883542588","https://openalex.org/W2889339831","https://openalex.org/W2963319203","https://openalex.org/W2963594949","https://openalex.org/W2996874060","https://openalex.org/W3016085798","https://openalex.org/W3091969046","https://openalex.org/W3104849992","https://openalex.org/W3155922894","https://openalex.org/W3199137126","https://openalex.org/W3203242999","https://openalex.org/W4225905866","https://openalex.org/W4246492177","https://openalex.org/W4281662450","https://openalex.org/W4297044268","https://openalex.org/W4391547488","https://openalex.org/W4391746431","https://openalex.org/W4400811641","https://openalex.org/W4404587340","https://openalex.org/W4405440253","https://openalex.org/W4409917212","https://openalex.org/W4410810511"],"related_works":["https://openalex.org/W3158538495","https://openalex.org/W2045815042","https://openalex.org/W2092226129","https://openalex.org/W2913619905","https://openalex.org/W4387838477","https://openalex.org/W3125758369","https://openalex.org/W2375898439","https://openalex.org/W2069382761","https://openalex.org/W4321636545","https://openalex.org/W2023476765"],"abstract_inverted_index":{"With":[0],"the":[1,81,112,155,188],"increasing":[2],"demand":[3],"for":[4],"deep":[5],"neural":[6],"network":[7,229],"(DNN)":[8],"inference":[9,230],"tasks":[10],"on":[11,17,32,50,195,206],"embedded":[12,19],"platforms,":[13],"deploying":[14],"compute-intensive":[15],"DNNs":[16,178],"resource-constrained":[18],"platforms":[20,34],"faces":[21,36],"challenges.":[22],"While":[23],"sparsification":[24],"technology":[25],"offers":[26],"a":[27,43,86,99,207,220],"potential":[28],"solution,":[29],"its":[30,200],"implementation":[31],"edge":[33,61],"still":[35],"difficulties.":[37],"In":[38,73],"this":[39,65],"article,":[40],"we":[41,67],"propose":[42],"novel":[44],"sparse":[45,79,93,117],"convolution":[46,180],"acceleration":[47],"processor":[48,83],"based":[49,205],"RISC-V":[51],"architecture,":[52],"and":[53,101,199,236],"design":[54],"specialized":[55],"custom":[56,151],"instructions":[57],"to":[58,75,105,145,183],"enable":[59],"efficient":[60,131],"DNN":[62],"inference.":[63],"To":[64,120],"end,":[66],"mainly":[68],"address":[69],"three":[70],"technical":[71],"issues.":[72],"response":[74],"numerical":[76],"characteristics":[77],"of":[78,190,224],"convolution,":[80],"designed":[82,128],"can":[84,169,218],"implement":[85],"hardware-friendly":[87],"architecture":[88],"that":[89,134,166,215],"transforms":[90],"convolutions":[91],"into":[92],"matrix":[94,118],"multiplication.":[95],"Additionally,":[96],"it":[97],"employs":[98],"column-major":[100],"element-level":[102],"parallel":[103],"strategy":[104],"optimize":[106],"load":[107],"imbalance":[108],"issues":[109],"present":[110],"in":[111,154,227],"Gustavson":[113],"algorithm,":[114],"thereby":[115],"enhancing":[116],"computations.":[119],"further":[121],"improve":[122],"computational":[123,234],"efficiency,":[124],"our":[125,148,167,191,216],"work":[126,149,168,192,217],"is":[127,193,202],"by":[129],"incorporating":[130],"execution":[132,137,171],"units":[133],"reduce":[135,170],"instruction":[136,152,185],"overheads":[138],"while":[139],"minimizing":[140],"memory":[141],"access":[142],"frequency.":[143],"Compared":[144],"traditional":[146],"accelerators,":[147],"supports":[150],"formats":[153],"C":[156],"programming":[157],"language,":[158],"offering":[159],"superior":[160],"flexibility.":[161],"Extensive":[162],"experimental":[163],"results":[164,213],"indicate":[165],"time":[172],"over":[173],"70%":[174],"when":[175],"running":[176],"most":[177,228],"with":[179],"operations":[181],"compared":[182],"conventional":[184],"sets.":[186],"Moreover,":[187],"functionality":[189],"validated":[194],"an":[196],"FPGA":[197],"platform,":[198],"performance":[201,235],"comprehensively":[203],"evaluated":[204],"55":[208],"nm":[209],"CMOS":[210],"process.":[211],"The":[212],"show":[214],"achieve":[219],"peak":[221],"energy":[222,237],"efficiency":[223],"675":[225],"GOPS/W":[226],"tasks,":[231],"demonstrating":[232],"exceptional":[233],"efficiency.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}