{"id":"https://openalex.org/W4391547488","doi":"https://doi.org/10.1109/tc.2024.3362060","title":"Optimizing CNN Computation Using RISC-V Custom Instruction Sets for Edge Platforms","display_name":"Optimizing CNN Computation Using RISC-V Custom Instruction Sets for Edge Platforms","publication_year":2024,"publication_date":"2024-02-05","ids":{"openalex":"https://openalex.org/W4391547488","doi":"https://doi.org/10.1109/tc.2024.3362060"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2024.3362060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2024.3362060","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","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/A5101951183","display_name":"Shihang Wang","orcid":"https://orcid.org/0000-0002-5753-6450"},"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":"Shihang Wang","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5753-6450","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","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":["Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9349-2718","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437324","display_name":"Zhiyuan Xu","orcid":"https://orcid.org/0009-0001-9039-7528"},"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":"Zhiyuan Xu","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0001-9039-7528","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, 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":["Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0004-6562-9536","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, 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":["Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0007-4376-3373","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, 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":["Department of Electrical and Computer Engineering, The University of British Columbia, Vancouver, BC, Canada"],"raw_orcid":"https://orcid.org/0000-0002-2644-2873","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"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":["Institute of Nanoscience and Applications (INA) and the Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-4359-3550","affiliations":[{"raw_affiliation_string":"Institute of Nanoscience and Applications (INA) and the Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":29.1202,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.99525386,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"73","issue":"5","first_page":"1371","last_page":"1384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.73089998960495,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.73089998960495,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.6937000155448914,"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":0.7301530838012695},{"id":"https://openalex.org/keywords/reduced-instruction-set-computing","display_name":"Reduced instruction set computing","score":0.6252785921096802},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5703420639038086},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5551267266273499},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.5158130526542664},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4936131238937378},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39162564277648926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2011180818080902}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7301530838012695},{"id":"https://openalex.org/C126298526","wikidata":"https://www.wikidata.org/wiki/Q189376","display_name":"Reduced instruction set computing","level":3,"score":0.6252785921096802},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5703420639038086},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5551267266273499},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.5158130526542664},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4936131238937378},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39162564277648926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2011180818080902}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2024.3362060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2024.3362060","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"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":25,"referenced_works":["https://openalex.org/W1005811612","https://openalex.org/W1686810756","https://openalex.org/W2048266589","https://openalex.org/W2094756095","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2557409653","https://openalex.org/W2618530766","https://openalex.org/W2800985424","https://openalex.org/W2903636812","https://openalex.org/W2943055749","https://openalex.org/W2963340555","https://openalex.org/W2978396128","https://openalex.org/W3005924570","https://openalex.org/W3016085798","https://openalex.org/W3016309475","https://openalex.org/W3034392153","https://openalex.org/W3034714449","https://openalex.org/W3193946904","https://openalex.org/W3193967165","https://openalex.org/W3211431797","https://openalex.org/W4246193833","https://openalex.org/W4253012315","https://openalex.org/W6637373629","https://openalex.org/W6640442106"],"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/W2128502296","https://openalex.org/W2993622674","https://openalex.org/W1833044483","https://openalex.org/W4382053335","https://openalex.org/W2036206036"],"abstract_inverted_index":{"Benefit":[0],"from":[1,73,84],"the":[2,34,52,61,66,78,100,104,111,130,179,192,202],"custom":[3,28,91,131,155],"instruction":[4,25,46],"extension":[5],"capabilities,":[6],"RISC-V":[7,22,145],"architecture":[8],"can":[9,31,48,70,93,107,121,133,189],"be":[10,71,94,108,122,134],"optimized":[11,170],"for":[12],"many":[13],"domain-specific":[14],"applications.":[15],"In":[16],"this":[17],"paper,":[18],"we":[19],"propose":[20],"seven":[21],"SIMD":[23],"(single":[24],"multiple":[26],"data)":[27],"instructions":[29,92,132],"that":[30,178],"significantly":[32],"optimize":[33],"convolution,":[35],"activation":[36],"and":[37,77,113,136,160,166,184,199,210],"pool":[38],"operations":[39],"in":[40,96,127],"CNN":[41],"inference":[42,180],"computation.":[43],"More":[44],"specifically,":[45],"CONV23":[47],"greatly":[49,190],"speed":[50],"up":[51],"operation":[53],"ofF(2":[54],"\u00d7":[55,58],"2,":[56],"3":[57],"3).":[59],"With":[60],"adoption":[62],"of":[63,68,181,207],"Winograd":[64],"algorithm,":[65],"number":[67],"multiplications":[69],"reduced":[72,83],"36":[74],"to":[75,86,152],"16,":[76],"execution":[79,193],"time":[80],"is":[81,148],"also":[82,169],"140":[85],"21":[87],"clock":[88],"cycles.":[89],"These":[90],"executed":[95],"batch":[97],"mode":[98],"within":[99],"acceleration":[101],"module":[102],"where":[103],"immediate":[105],"data":[106],"reused,":[109],"so":[110],"latency":[112,194],"energy":[114,204],"overhead":[115],"associated":[116],"with":[117,139,201],"excess":[118],"memory":[119],"accesses":[120],"eliminated.":[123],"Using":[124],"inline":[125],"assembler":[126],"C":[128,140],"language,":[129],"called":[135,163],"compiled":[137],"together":[138],"source":[141],"code.":[142],"A":[143],"revised":[144],"processor,":[146],"RI5CY-Accel":[147,173,188],"constructed":[149],"on":[150,172,187],"FPGA":[151],"accommodate":[153],"these":[154],"instructions.":[156],"Revised":[157],"LeNet-5,":[158],"VGG16":[159],"ResNet18":[161],"model;":[162],"LeNet-Accel,":[164,182],"VGG16-Accel":[165,183],"ResNet18-Accel":[167,185],"are":[168],"based":[171,186],"architecture.":[174],"Benchmark":[175],"experiments":[176],"demonstrated":[177],"reduce":[191],"by":[195],"over":[196],"76.6%,":[197],"88.8%":[198],"87.1%,":[200],"total":[203],"consumption":[205],"saving":[206],"74.8%,":[208],"87.8%":[209],"85.1%":[211],"respectively.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}