{"id":"https://openalex.org/W4226207184","doi":"https://doi.org/10.1109/tpds.2022.3171471","title":"Design and Implementation of 2D Convolution on x86/x64 Processors","display_name":"Design and Implementation of 2D Convolution on x86/x64 Processors","publication_year":2022,"publication_date":"2022-04-29","ids":{"openalex":"https://openalex.org/W4226207184","doi":"https://doi.org/10.1109/tpds.2022.3171471"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2022.3171471","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3171471","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/9790018/09765671.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/71/9790018/09765671.pdf","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":["School of Engineering, Computing and Mathematics, University of Plymouth, Plymouth, U.K"],"raw_orcid":"https://orcid.org/0000-0001-9591-913X","affiliations":[{"raw_affiliation_string":"School of Engineering, Computing and Mathematics, University of Plymouth, 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"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Georgios Keramidas","raw_affiliation_strings":["School of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece"],"raw_orcid":"https://orcid.org/0000-0003-0460-6061","affiliations":[{"raw_affiliation_string":"School of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2724,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.8034815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"33","issue":"12","first_page":"3800","last_page":"3815"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9944000244140625,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9937999844551086,"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/speedup","display_name":"Speedup","score":0.8040040731430054},{"id":"https://openalex.org/keywords/intrinsics","display_name":"Intrinsics","score":0.7106320261955261},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.6338209509849548},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.6213557720184326},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5867286920547485},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5836601853370667},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5308341383934021},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5009124279022217},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.45589402318000793},{"id":"https://openalex.org/keywords/mmx","display_name":"MMX","score":0.45145002007484436},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4513598084449768},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.32292765378952026},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3177013695240021},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.2480071783065796},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11846458911895752},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.11771795153617859},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.0948914885520935}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8040040731430054},{"id":"https://openalex.org/C2908650547","wikidata":"https://www.wikidata.org/wiki/Q20999234","display_name":"Intrinsics","level":2,"score":0.7106320261955261},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.6338209509849548},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.6213557720184326},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5867286920547485},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5836601853370667},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5308341383934021},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5009124279022217},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.45589402318000793},{"id":"https://openalex.org/C85918911","wikidata":"https://www.wikidata.org/wiki/Q904336","display_name":"MMX","level":2,"score":0.45145002007484436},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4513598084449768},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.32292765378952026},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3177013695240021},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.2480071783065796},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11846458911895752},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.11771795153617859},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0948914885520935},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpds.2022.3171471","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3171471","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/9790018/09765671.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:10026.1/19129","is_oa":false,"landing_page_url":"http://hdl.handle.net/10026.1/19129","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":{"id":"doi:10.1109/tpds.2022.3171471","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3171471","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/9790018/09765671.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4226207184.pdf","grobid_xml":"https://content.openalex.org/works/W4226207184.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1575935080","https://openalex.org/W1999129135","https://openalex.org/W2063455145","https://openalex.org/W2069881969","https://openalex.org/W2107307723","https://openalex.org/W2114929171","https://openalex.org/W2786374423","https://openalex.org/W2788818070","https://openalex.org/W2789602589","https://openalex.org/W2804777790","https://openalex.org/W2884721730","https://openalex.org/W2907172645","https://openalex.org/W2919636550","https://openalex.org/W2951894856","https://openalex.org/W2952110101","https://openalex.org/W2952713184","https://openalex.org/W2954580493","https://openalex.org/W2978452617","https://openalex.org/W3036423057","https://openalex.org/W3046739674","https://openalex.org/W3048263222","https://openalex.org/W3057502114","https://openalex.org/W3117440043","https://openalex.org/W3152882955","https://openalex.org/W4234143480","https://openalex.org/W4238973935","https://openalex.org/W6729837857","https://openalex.org/W6752390237","https://openalex.org/W6758002897","https://openalex.org/W6765129128"],"related_works":["https://openalex.org/W1563340050","https://openalex.org/W602477477","https://openalex.org/W4708796","https://openalex.org/W1480874568","https://openalex.org/W2129537883","https://openalex.org/W2164226499","https://openalex.org/W4236526691","https://openalex.org/W2003690377","https://openalex.org/W2365914194","https://openalex.org/W4312862090"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3],"new":[4],"method":[5,72,134,161],"for":[6],"accelerating":[7],"the":[8,28,31,40,46,92,112,131,152],"2D":[9],"direct":[10,156],"Convolution":[11],"operation":[12],"on":[13,76],"x86/x64":[14],"processors":[15],"is":[16,53,57,162],"presented.":[17],"It":[18,102],"includes":[19],"efficient":[20],"vectorization":[21],"by":[22,82],"using":[23,35,83,136],"SIMD":[24],"intrinsics,":[25],"bit-twiddling":[26],"optimizations,":[27],"optimization":[29],"of":[30,45],"division":[32],"operation,":[33],"multi-threading":[34],"OpenMP,":[36],"register":[37],"blocking":[38],"and":[39,59,91,118,143,170],"shortest":[41],"possible":[42],"bit-width":[43],"value":[44],"intermediate":[47],"results.":[48],"The":[49,70,159],"proposed":[50,71,160],"method,":[51],"which":[52],"provided":[54],"as":[55,164],"open-source,":[56],"general":[58],"can":[60],"be":[61],"applied":[62],"to":[63,107,125,147],"other":[64],"processor":[65],"families":[66],"too,":[67],"e.g.,":[68],"Arm.":[69],"has":[73],"been":[74],"evaluated":[75],"two":[77],"different":[78,85],"multi-core":[79],"Intel":[80,113,137,154],"CPUs,":[81],"twenty":[84],"image":[86],"sizes,":[87],"8-bit":[88],"integer":[89],"computations":[90],"most":[93],"commonly":[94],"used":[95],"kernel":[96],"sizes":[97],"(3x3,":[98],"5x5,":[99],"7x7,":[100],"9x9).":[101],"achieves":[103,166],"from":[104,121,144],"<inline-formula><tex-math":[105,108,122,126,145,148],"notation=\"LaTeX\">$2.8\\times$</tex-math></inline-formula>":[106],"notation=\"LaTeX\">$40\\times$</tex-math></inline-formula>":[109],"speedup":[110,129,150],"over":[111,130,151],"IPP":[114],"library":[115],"(OpenCV":[116],"GaussianBlur":[117],"Filter2D":[119],"routines),":[120],"notation=\"LaTeX\">$105":[123],"\\times$</tex-math></inline-formula>":[124,128],"notation=\"LaTeX\">$400":[127],"gemm-based":[132],"convolution":[133,157],"(by":[135],"MKL":[138,155],"int8":[139],"matrix":[140],"multiplication":[141],"routine),":[142],"notation=\"LaTeX\">$8.5\\times$</tex-math></inline-formula>":[146],"notation=\"LaTeX\">$618\\times$</tex-math></inline-formula>":[149],"vslsConvExec":[153],"routine.":[158],"superior":[163],"it":[165],"far":[167],"fewer":[168],"arithmetical":[169],"load/store":[171],"instructions.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}