{"id":"https://openalex.org/W4381149555","doi":"https://doi.org/10.1145/3605149","title":"Hierarchical Model Parallelism for Optimizing Inference on Many-core Processor via Decoupled 3D-CNN Structure","display_name":"Hierarchical Model Parallelism for Optimizing Inference on Many-core Processor via Decoupled 3D-CNN Structure","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4381149555","doi":"https://doi.org/10.1145/3605149"},"language":"en","primary_location":{"id":"doi:10.1145/3605149","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605149","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605149","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"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 Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3605149","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048148542","display_name":"Jiazhi Jiang","orcid":"https://orcid.org/0000-0002-1417-3012"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiazhi Jiang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0000-0002-1417-3012","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102016193","display_name":"Zijian Huang","orcid":"https://orcid.org/0009-0005-0280-2757"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijian Huang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0009-0005-0280-2757","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041534890","display_name":"Dan Huang","orcid":"https://orcid.org/0000-0001-5582-1031"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Huang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0000-0001-5582-1031","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024085713","display_name":"Jiangsu Du","orcid":"https://orcid.org/0000-0003-4707-9492"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangsu Du","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0000-0003-4707-9492","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069716714","display_name":"Lin Chen","orcid":"https://orcid.org/0000-0001-7943-3172"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0000-0001-7943-3172","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110993799","display_name":"Ziguan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziguan Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0000-0002-9318-5715","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101633465","display_name":"Yutong Lu","orcid":"https://orcid.org/0000-0001-5315-3375"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Lu","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0000-0001-5315-3375","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5048148542"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.2277,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.4955225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"20","issue":"3","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9954000115394592,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8937866687774658},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7236950397491455},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6140424013137817},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5938407182693481},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5331748127937317},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5220732092857361},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4885023832321167},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.430259108543396},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.41280660033226013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4005281627178192},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3229506015777588},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.1872895359992981},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.0950833261013031},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.08984872698783875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8937866687774658},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7236950397491455},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6140424013137817},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5938407182693481},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5331748127937317},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5220732092857361},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4885023832321167},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.430259108543396},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.41280660033226013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4005281627178192},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3229506015777588},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.1872895359992981},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0950833261013031},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.08984872698783875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3605149","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605149","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605149","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"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 Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3605149","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605149","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605149","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"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 Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G611074686","display_name":null,"funder_award_id":"2021YFB0301300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4381149555.pdf","grobid_xml":"https://content.openalex.org/works/W4381149555.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1952703253","https://openalex.org/W1976916015","https://openalex.org/W2068993993","https://openalex.org/W2163605009","https://openalex.org/W2172654076","https://openalex.org/W2475126267","https://openalex.org/W2886189612","https://openalex.org/W2908185957","https://openalex.org/W2969414999","https://openalex.org/W2971383048","https://openalex.org/W2972087877","https://openalex.org/W3044981912","https://openalex.org/W3083622693","https://openalex.org/W3108109508","https://openalex.org/W3113588636","https://openalex.org/W3129601694","https://openalex.org/W3154028478","https://openalex.org/W3202294838","https://openalex.org/W3203535024","https://openalex.org/W4205570975","https://openalex.org/W4232611972","https://openalex.org/W4236277626","https://openalex.org/W4241366218","https://openalex.org/W4286635279","https://openalex.org/W4301409763","https://openalex.org/W4302296459","https://openalex.org/W4312641748","https://openalex.org/W4320067900","https://openalex.org/W6637151318"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W2055243143","https://openalex.org/W2128523353","https://openalex.org/W2291648581","https://openalex.org/W2473478803","https://openalex.org/W2185482126","https://openalex.org/W4241547419","https://openalex.org/W2729363167","https://openalex.org/W2294763967","https://openalex.org/W2060611139"],"abstract_inverted_index":{"The":[0],"tremendous":[1],"success":[2],"of":[3,15,113,138,147,180],"convolutional":[4],"neural":[5],"network":[6],"(CNN)":[7],"has":[8],"made":[9],"it":[10,204,227],"ubiquitous":[11],"in":[12,56,77,193],"many":[13,78],"fields":[14],"human":[16],"endeavor.":[17],"Many":[18],"applications":[19],"such":[20,40,131],"as":[21,41,132],"biomedical":[22],"analysis":[23,27],"and":[24,115,136,167,184],"scientific":[25],"data":[26],"involve":[28],"analyzing":[29],"volumetric":[30],"data.":[31],"This":[32],"spawns":[33],"huge":[34],"demand":[35],"for":[36,73,89,151],"3D-CNN.":[37,152],"Although":[38],"accelerators":[39],"GPU":[42],"may":[43,52],"provide":[44],"higher":[45],"throughput":[46],"on":[47,93,117,122,201,214,224,238],"deep":[48,74],"learning":[49,75],"applications,":[50],"they":[51],"not":[53],"be":[54],"available":[55],"all":[57],"scenarios.":[58,79],"CPU,":[59],"especially":[60],"many-core":[61,97,119,149,216,240],"CPU":[62,98,150],"with":[63,159,189],"non-uniform":[64],"memory":[65,114],"access":[66],"(NUMA)":[67],"architecture,":[68],"remains":[69],"an":[70],"attractive":[71],"choice":[72],"inference":[76,87,109,157,199,222],"In":[80],"this":[81],"article,":[82],"we":[83],"propose":[84],"a":[85,190],"distributed":[86],"solution":[88,158,175,200,223],"3D-CNN":[90,108,182,198,221],"that":[91,173],"targets":[92],"the":[94,123,145,178,181,230],"emerging":[95],"ARM":[96,118,148,215,239],"platform.":[99],"A":[100],"hierarchical":[101,124],"partition":[102,126],"approach":[103],"is":[104],"claimed":[105],"to":[106,143,212,236],"accelerate":[107],"by":[110,210,234],"exploiting":[111],"characteristics":[112],"cache":[116],"CPU.":[120],"Based":[121],"model":[125],"approach,":[127],"other":[128],"optimization":[129,137],"techniques":[130],"NUMA-aware":[133],"thread":[134],"scheduling":[135],"3D-img2row":[139],"convolution":[140],"are":[141],"designed":[142],"exploit":[144],"potential":[146],"We":[153],"evaluate":[154],"our":[155,174,197,220],"proposed":[156],"several":[160],"classic":[161],"3D-CNNs:":[162],"C3D,":[163],"3D-resnet34,":[164],"3D-resnet50,":[165],"3D-vgg11,":[166],"P3D.":[168],"Our":[169],"experimental":[170],"results":[171],"show":[172],"can":[176,205,228],"boost":[177],"performance":[179],"inference,":[183],"achieve":[185],"much":[186],"better":[187],"scalability,":[188],"negligible":[191],"fluctuation":[192],"accuracy.":[194],"When":[195,218],"employing":[196,219],"ACL":[202,208],"libraries,":[203,226],"outperform":[206,229],"naive":[207,231],"implementations":[209,233],"11\u00d7":[211],"50\u00d7":[213],"processor.":[217,241],"NCNN":[225,232],"5.2\u00d7":[235],"14.2\u00d7":[237]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}