{"id":"https://openalex.org/W4379794547","doi":"https://doi.org/10.1109/access.2023.3283312","title":"Analysis and Optimization of Direct Convolution Execution on Multi-Core Processors","display_name":"Analysis and Optimization of Direct Convolution Execution on Multi-Core Processors","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4379794547","doi":"https://doi.org/10.1109/access.2023.3283312"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3283312","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3283312","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10144741.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10144741.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004350640","display_name":"Mirco Mannino","orcid":"https://orcid.org/0000-0003-1660-3984"},"institutions":[{"id":"https://openalex.org/I102064193","display_name":"University of Siena","ror":"https://ror.org/01tevnk56","country_code":"IT","type":"education","lineage":["https://openalex.org/I102064193"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mirco Mannino","raw_affiliation_strings":["Department of Information Engineering and Mathematics, University of Siena, Siena, Italy"],"raw_orcid":"https://orcid.org/0000-0003-1660-3984","affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Mathematics, University of Siena, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021283515","display_name":"Biagio Peccerillo","orcid":"https://orcid.org/0000-0002-4998-0092"},"institutions":[{"id":"https://openalex.org/I102064193","display_name":"University of Siena","ror":"https://ror.org/01tevnk56","country_code":"IT","type":"education","lineage":["https://openalex.org/I102064193"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Biagio Peccerillo","raw_affiliation_strings":["Department of Information Engineering and Mathematics, University of Siena, Siena, Italy"],"raw_orcid":"https://orcid.org/0000-0002-4998-0092","affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Mathematics, University of Siena, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001351683","display_name":"Andrea Mondelli","orcid":"https://orcid.org/0000-0002-4740-7081"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Andrea Mondelli","raw_affiliation_strings":["Huawei Technologies Company Ltd., Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Company Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047011963","display_name":"Sandro Bartolini","orcid":"https://orcid.org/0000-0002-7975-3632"},"institutions":[{"id":"https://openalex.org/I102064193","display_name":"University of Siena","ror":"https://ror.org/01tevnk56","country_code":"IT","type":"education","lineage":["https://openalex.org/I102064193"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sandro Bartolini","raw_affiliation_strings":["Department of Information Engineering and Mathematics, University of Siena, Siena, Italy"],"raw_orcid":"https://orcid.org/0000-0002-7975-3632","affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Mathematics, University of Siena, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.2212,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51782042,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"11","issue":null,"first_page":"57514","last_page":"57528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9988999962806702,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8545924425125122},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6116880178451538},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5902206897735596},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.562680184841156},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44999444484710693},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.4419458210468292},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.43926432728767395},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4350992441177368},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4293246865272522},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.41198480129241943},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32212311029434204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31903356313705444},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2647329866886139},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16813889145851135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8545924425125122},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6116880178451538},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5902206897735596},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.562680184841156},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44999444484710693},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.4419458210468292},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.43926432728767395},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4350992441177368},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4293246865272522},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.41198480129241943},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32212311029434204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31903356313705444},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2647329866886139},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16813889145851135},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2023.3283312","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3283312","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10144741.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:usiena-air.unisi.it:11365/1234894","is_oa":true,"landing_page_url":"https://hdl.handle.net/11365/1234894","pdf_url":"https://hdl.handle.net/11365/1234894","source":{"id":"https://openalex.org/S4377196319","display_name":"Use Siena air (University of Siena)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102064193","host_organization_name":"University of Siena","host_organization_lineage":["https://openalex.org/I102064193"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:f70d874594ac4a1d8f71d34fb6d3d5c3","is_oa":true,"landing_page_url":"https://doaj.org/article/f70d874594ac4a1d8f71d34fb6d3d5c3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 57514-57528 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3283312","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3283312","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10144741.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322183","display_name":"Huawei Technologies","ror":"https://ror.org/00cmhce21"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4379794547.pdf","grobid_xml":"https://content.openalex.org/works/W4379794547.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1597968260","https://openalex.org/W1686810756","https://openalex.org/W1970456555","https://openalex.org/W2078224158","https://openalex.org/W2120615054","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2433451779","https://openalex.org/W2540279855","https://openalex.org/W2565630050","https://openalex.org/W2670151302","https://openalex.org/W2804777790","https://openalex.org/W2810819381","https://openalex.org/W2910121883","https://openalex.org/W2913146885","https://openalex.org/W2945146780","https://openalex.org/W2954580493","https://openalex.org/W2983655274","https://openalex.org/W2998600257","https://openalex.org/W3100321043","https://openalex.org/W3118616291","https://openalex.org/W3123054690","https://openalex.org/W3156745629","https://openalex.org/W3184382748","https://openalex.org/W3192477179","https://openalex.org/W4226207184","https://openalex.org/W4293100236","https://openalex.org/W4293149165","https://openalex.org/W4311543031","https://openalex.org/W6635694052","https://openalex.org/W6637373629","https://openalex.org/W6684191040","https://openalex.org/W6718152450","https://openalex.org/W6740373327","https://openalex.org/W6752390237","https://openalex.org/W6765129128","https://openalex.org/W6788369737"],"related_works":["https://openalex.org/W2762467749","https://openalex.org/W2979513934","https://openalex.org/W2351155539","https://openalex.org/W4312354936","https://openalex.org/W4386858688","https://openalex.org/W2982536526","https://openalex.org/W4380302312","https://openalex.org/W3008689640","https://openalex.org/W4385338604","https://openalex.org/W3081626085"],"abstract_inverted_index":{"Nowadays,":[0],"convolutional":[1,187],"neural":[2],"networks":[3,14],"are":[4,24,214],"among":[5],"the":[6,41,59,88,129,179,183,186,209],"most":[7,42],"widely":[8,43],"used":[9,44,169],"types":[10],"of":[11,40,50,77,106,164,185],"deep":[12],"learning":[13],"thanks":[15],"to":[16,27,30,46,84,170,178,200,203],"their":[17,32],"usefulness":[18],"in":[19,71,147,161,176,226],"many":[20,25],"application":[21],"domains.":[22],"There":[23],"efforts":[26],"find":[28],"methods":[29],"increase":[31,197],"training":[33],"and":[34,37,56,82,86,113,131,141,157,182],"inference":[35],"performance":[36,130,198],"efficiency.":[38],"One":[39],"technique":[45],"implement":[47],"convolution":[48,99,225],"consists":[49],"flattening":[51],"tensors":[52,89],"into":[53],"2D":[54],"matrices":[55],"carrying":[57],"out":[58],"operation":[60],"through":[61],"a":[62,104,162,173,193,204,227],"matrix-matrix":[63,223],"multiplication":[64],"routine,":[65],"which":[66],"has":[67],"highly":[68],"optimized":[69],"implementations":[70],"high-performance":[72,174],"libraries.":[73],"However,":[74],"this":[75,92,121],"kind":[76],"approach":[78],"uses":[79],"extra":[80,118],"time":[81],"memory":[83],"transform":[85],"store":[87],"involved.":[90],"For":[91],"reason,direct":[93],"convolutionis":[94],"becoming":[95],"increasingly":[96],"popular.":[97],"Direct":[98],"can":[100,167],"be":[101,168],"implemented":[102],"as":[103],"series":[105],"nested":[107],"loops":[108],"iterating":[109],"over":[110],"tensor":[111],"dimensions":[112],"it":[114],"does":[115],"not":[116],"require":[117],"memory.":[119],"In":[120],"work,":[122],"we":[123,196],"evaluate":[124],"on":[125],"various":[126],"multi-core":[127,228],"CPUs":[128],"scalability":[132],"effects":[133],"deriving":[134],"from":[135],"different":[136,145],"parallelization":[137],"strategies,":[138],"loop":[139],"organizations,":[140],"SIMD-vectorization":[142],"approaches":[143],"with":[144,149],"compilers":[146],"relation":[148],"architectural":[150],"aspects.":[151],"We":[152],"discuss":[153],"each":[154],"parameter":[155],"thoroughly":[156],"distill":[158],"our":[159,212],"findings":[160],"set":[163],"heuristics":[165],"that":[166],"quickly":[171],"achieve":[172],"implementation":[175,206],"accordance":[177],"underlying":[180],"hardware":[181],"characteristics":[184],"layer":[188],"at":[189],"hand.":[190],"By":[191],"adopting":[192],"per-layer":[194],"approach,":[195],"up":[199],"60-70%":[201],"compared":[202],"static":[205],"for":[207],"all":[208],"layers.":[210],"Moreover,":[211],"results":[213],"comparable,":[215],"or":[216],"even":[217],"better":[218],"(up":[219],"to$1.67\\times":[220],"$speedup)":[221],"than":[222],"multiplication-based":[224],"system.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}