{"id":"https://openalex.org/W4387350719","doi":"https://doi.org/10.1109/tpds.2023.3322037","title":"Design and Implementation of Deep Learning 2D Convolutions on Modern CPUs","display_name":"Design and Implementation of Deep Learning 2D Convolutions on Modern CPUs","publication_year":2023,"publication_date":"2023-10-04","ids":{"openalex":"https://openalex.org/W4387350719","doi":"https://doi.org/10.1109/tpds.2023.3322037"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2023.3322037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3322037","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed 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/A5090157400","display_name":"Vasilios Kelefouras","orcid":"https://orcid.org/0000-0001-9591-913X"},"institutions":[{"id":"https://openalex.org/I897542642","display_name":"University of Plymouth","ror":"https://ror.org/008n7pv89","country_code":"GB","type":"education","lineage":["https://openalex.org/I897542642"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vasilios Kelefouras","raw_affiliation_strings":["Department of Computing, Plymouth University, Plymouth, U.K"],"raw_orcid":"https://orcid.org/0000-0001-9591-913X","affiliations":[{"raw_affiliation_string":"Department of Computing, Plymouth University, Plymouth, U.K","institution_ids":["https://openalex.org/I897542642"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074371053","display_name":"\u0393\u03b5\u03ce\u03c1\u03b3\u03b9\u03bf\u03c2 \u039a\u03b5\u03c1\u03b1\u03bc\u03af\u03b4\u03b1\u03c2","orcid":"https://orcid.org/0000-0003-0460-6061"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]},{"id":"https://openalex.org/I897542642","display_name":"University of Plymouth","ror":"https://ror.org/008n7pv89","country_code":"GB","type":"education","lineage":["https://openalex.org/I897542642"]}],"countries":["GB","GR"],"is_corresponding":false,"raw_author_name":"Georgios Keramidas","raw_affiliation_strings":["Department of Computer Engineering &#x0026; Informatics, Aristoteleio Panepistemio Thessalonikes, Thessaloniki, Greece","Computing, Plymouth University, Plymouth, U.K"],"raw_orcid":"https://orcid.org/0000-0003-0460-6061","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering &#x0026; Informatics, Aristoteleio Panepistemio Thessalonikes, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]},{"raw_affiliation_string":"Computing, Plymouth University, Plymouth, U.K","institution_ids":["https://openalex.org/I897542642"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6382,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.70434876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"34","issue":"12","first_page":"3104","last_page":"3116"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980999827384949,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9966999888420105,"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":0.7595345377922058},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6193073987960815},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6100596785545349},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5992481112480164},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.5695919990539551},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5277624130249023},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5110026597976685},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3408195674419403},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2830126881599426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2827685475349426},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22768744826316833},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.14078161120414734}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7595345377922058},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6193073987960815},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6100596785545349},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5992481112480164},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.5695919990539551},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5277624130249023},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5110026597976685},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3408195674419403},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2830126881599426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2827685475349426},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22768744826316833},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.14078161120414734}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpds.2023.3322037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3322037","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:pearl.plymouth.ac.uk:10026.1/21352","is_oa":false,"landing_page_url":"https://pearl.plymouth.ac.uk/handle/10026.1/21352","pdf_url":null,"source":{"id":"https://openalex.org/S4306402507","display_name":"PEARL (University of Plymouth)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I897542642","host_organization_name":"University of Plymouth","host_organization_lineage":["https://openalex.org/I897542642"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2069881969","https://openalex.org/W2766839578","https://openalex.org/W2786374423","https://openalex.org/W2804032941","https://openalex.org/W2804777790","https://openalex.org/W2806891462","https://openalex.org/W2919636550","https://openalex.org/W2951894856","https://openalex.org/W2952110101","https://openalex.org/W2952713184","https://openalex.org/W2954580493","https://openalex.org/W3046739674","https://openalex.org/W3057502114","https://openalex.org/W3096395190","https://openalex.org/W3123054690","https://openalex.org/W3152882955","https://openalex.org/W3156745629","https://openalex.org/W3173462777","https://openalex.org/W4206990365","https://openalex.org/W4226207184","https://openalex.org/W4280547204","https://openalex.org/W4281296111","https://openalex.org/W4283654473","https://openalex.org/W4288079690","https://openalex.org/W4308596141","https://openalex.org/W6729837857","https://openalex.org/W6745499037","https://openalex.org/W6751349269","https://openalex.org/W6752390237","https://openalex.org/W6765129128","https://openalex.org/W6779728309","https://openalex.org/W6839545381","https://openalex.org/W6846469293"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W2778498407","https://openalex.org/W3157543420"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"a":[3,95],"new":[4],"method":[5],"is":[6,51,78,100],"provided":[7],"for":[8,108,125,136],"accelerating":[9],"the":[10,23,31,39,72,75,110,149,153],"execution":[11],"of":[12,74,152],"convolution":[13,32,133,150],"layers":[14,33,151],"in":[15,94],"Deep":[16],"Neural":[17],"Networks.":[18],"This":[19,99],"research":[20],"work":[21,50,66],"provides":[22],"theoretical":[24],"background":[25],"to":[26,57,162],"efficiently":[27],"design":[28],"and":[29,45,53,91,128,135,139],"implement":[30],"on":[34,38,120],"x86/x64":[35],"CPUs,":[36],"based":[37],"target":[40],"layer":[41],"parameters,":[42],"quantization":[43],"level":[44],"hardware":[46],"architecture.":[47],"The":[48,64,144],"proposed":[49,65],"general":[52],"can":[54],"be":[55],"applied":[56,119],"other":[58],"processor":[59],"families":[60],"too,":[61],"e.g.,":[62],"Arm.":[63],"achieves":[67],"high":[68],"speedup":[69],"values":[70],"over":[71],"state":[73],"art,":[76],"which":[77],"Intel":[79,122],"oneDNN":[80],"library,":[81],"by":[82,102],"applying":[83],"compiler":[84],"optimizations,":[85],"such":[86],"as":[87],"vectorization,":[88],"register":[89],"blocking":[90],"loop":[92],"tiling,":[93],"more":[96],"efficient":[97],"way.":[98],"achieved":[101],"developing":[103],"an":[104],"analytical":[105],"modelling":[106],"approach":[107],"finding":[109],"optimization":[111],"parameters.":[112],"A":[113],"thorough":[114],"experimental":[115,145],"evaluation":[116],"has":[117],"been":[118],"two":[121],"CPU":[123],"platforms,":[124],"DenseNet-121,":[126],"ResNet-50":[127],"SqueezeNet":[129],"(including":[130],"112":[131],"different":[132],"layers),":[134],"both":[137],"FP32":[138],"int8":[140],"input/output":[141],"tensors":[142],"(quantization).":[143],"results":[146],"show":[147],"that":[148],"aforementioned":[154],"models":[155],"are":[156],"executed":[157],"from":[158],"<inline-formula><tex-math":[159,163],"notation=\"LaTeX\">$x1.1$</tex-math></inline-formula>":[160],"up":[161],"notation=\"LaTeX\">$x7.2$</tex-math></inline-formula>":[164],"times":[165],"faster.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}