{"id":"https://openalex.org/W4412610590","doi":"https://doi.org/10.1109/hpcc64274.2024.00024","title":"VCNN: A compiler of CNNs based on MLIR for multi-core vector accelerators","display_name":"VCNN: A compiler of CNNs based on MLIR for multi-core vector accelerators","publication_year":2024,"publication_date":"2024-12-13","ids":{"openalex":"https://openalex.org/W4412610590","doi":"https://doi.org/10.1109/hpcc64274.2024.00024"},"language":"en","primary_location":{"id":"doi:10.1109/hpcc64274.2024.00024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc64274.2024.00024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on High Performance Computing and Communications (HPCC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5032831534","display_name":"Xiaorong Chen","orcid":null},"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":"Xiaorong Chen","raw_affiliation_strings":["National University of Defense Technology,College of Computer,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354222","display_name":"Cheng Li","orcid":"https://orcid.org/0000-0001-5765-3561"},"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":"Cheng Li","raw_affiliation_strings":["National University of Defense Technology,College of Computer,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119057120","display_name":"Zhong Liu B","orcid":null},"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":"Zhong Liu B","raw_affiliation_strings":["National University of Defense Technology,College of Computer,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.2629,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.63348663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"102","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9327999949455261,"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":0.9327999949455261,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9114999771118164,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7815607786178589},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7247297167778015},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5318156480789185},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.47367292642593384},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4679614007472992}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7815607786178589},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7247297167778015},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5318156480789185},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47367292642593384},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4679614007472992},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcc64274.2024.00024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc64274.2024.00024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on High Performance Computing and Communications (HPCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2530876040","https://openalex.org/W2570343428","https://openalex.org/W2886472289","https://openalex.org/W2962821792","https://openalex.org/W3008102594","https://openalex.org/W3043619075","https://openalex.org/W3122286897","https://openalex.org/W4246166885","https://openalex.org/W4282590766","https://openalex.org/W4282974189","https://openalex.org/W4301361180","https://openalex.org/W4312060068","https://openalex.org/W4360995079","https://openalex.org/W4378807770","https://openalex.org/W4380085410","https://openalex.org/W4387845549","https://openalex.org/W4392667938","https://openalex.org/W4393118821","https://openalex.org/W4393186098","https://openalex.org/W6751349269"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4240253816","https://openalex.org/W3096456556","https://openalex.org/W1713081424","https://openalex.org/W2127315869","https://openalex.org/W1523769955","https://openalex.org/W2245390655","https://openalex.org/W4379536100"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Network":[2],"(CNN)":[3],"is":[4,113,142,269],"one":[5],"of":[6,10,36,45,76,87,97,166,174,202,207,216,226,241,246,255,260],"the":[7,33,54,74,83,107,162,170,183,187,193,198,224,263,279],"representative":[8],"algorithms":[9],"machine":[11],"learning":[12],"and":[13,28,100,185,210,229,249,251],"deep":[14],"learning.":[15],"Multi-core":[16,48,136],"vector":[17,40,120,130],"accelerators":[18],"are":[19,44,50,101],"becoming":[20],"increasingly":[21],"popular":[22],"due":[23],"to":[24,39,53,103,129,218,288],"their":[25],"high":[26],"performance":[27,225],"low":[29],"power":[30,253],"consumption.":[31],"In":[32,220],"previous":[34],"methods":[35,93],"deploying":[37],"CNNs":[38],"accelerators,":[41],"three":[42],"issues":[43],"concern.":[46],"(1)":[47,134],"tasks":[49],"divided":[51],"according":[52],"image":[55],"data":[56],"dimension,":[57],"which":[58],"has":[59,237],"limitations":[60],"in":[61,110],"low-latency":[62,146],"real-time":[63,147],"detection":[64,148],"application":[65,149],"scenarios.":[66,150],"(2)":[67,151],"Many":[68],"memory":[69,284,290],"optimization":[70],"strategies":[71],"only":[72,160],"consider":[73],"impact":[75],"tensor":[77,80],"size":[78,163],"or":[79,164],"life,":[81],"ignoring":[82],"inherent":[84,171],"computational":[85,172,239],"characteristics":[86,173],"operator":[88,175],"types.":[89,176],"(3)":[90,177],"Manual":[91],"mapping":[92],"require":[94],"a":[95,114,135,212,238,252,282],"lot":[96],"engineering":[98],"effort":[99],"prone":[102],"introducing":[104],"errors.":[105],"Therefore,":[106],"VCNN":[108,123,194,236,264,280],"proposed":[109],"this":[111],"paper":[112],"compiler":[115],"based":[116],"on":[117],"MLIR":[118],"for":[119,145],"accelerators.":[121,131],"The":[122,232],"can":[124,195],"automatically":[125],"map":[126],"CNN":[127],"models":[128],"It":[132,158],"includes":[133],"Parallel":[137],"Convolution":[138],"algorithm":[139],"(MPC)":[140],"that":[141,181,192,235,245,259,275],"more":[143,242,256],"suitable":[144],"An":[152],"Adaptive":[153],"Memory":[154],"Reuse":[155],"method":[156],"(AMR).":[157],"not":[159],"considers":[161],"lifetime":[165],"tensors":[167],"but":[168],"also":[169],"A":[178],"quantization":[179],"pass":[180],"quantizes":[182],"model":[184,266],"reshuffles":[186],"data.":[188],"Experimental":[189],"results":[190,233],"show":[191,234],"effectively":[196],"utilize":[197],"parallel":[199,213],"processing":[200],"capabilities":[201],"hardware":[203],"when":[204],"performing":[205],"convolutions":[206],"different":[208],"sizes,":[209],"achieve":[211],"computing":[214],"efficiency":[215,240,254],"up":[217],"95.75%.":[219],"addition,":[221],"we":[222],"evaluated":[223],"AlexNet,":[227],"VGG16,":[228],"Yolov5s":[230],"models.":[231],"than":[243,257],"2X+":[244],"TVM,":[247],"TensorRT,":[248],"OnnxRuntime,":[250],"7X+":[258],"them.":[261],"Additionally,":[262],"inference":[265],"using":[267,276],"Float16":[268],"twice":[270],"as":[271,274],"energy":[272],"efficient":[273],"Float32.":[277],"Furthermore,":[278],"achieves":[281],"higher":[283],"reuse":[285,291],"rate":[286],"compared":[287],"traditional":[289],"methods.":[292]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}