{"id":"https://openalex.org/W4320490426","doi":"https://doi.org/10.1007/s11227-023-05088-4","title":"Efficient and portable Winograd convolutions for multi-core processors","display_name":"Efficient and portable Winograd convolutions for multi-core processors","publication_year":2023,"publication_date":"2023-02-12","ids":{"openalex":"https://openalex.org/W4320490426","doi":"https://doi.org/10.1007/s11227-023-05088-4"},"language":"en","primary_location":{"id":"doi:10.1007/s11227-023-05088-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-023-05088-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-023-05088-4.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11227-023-05088-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054862021","display_name":"Manuel F. Dolz","orcid":"https://orcid.org/0000-0001-9466-3398"},"institutions":[{"id":"https://openalex.org/I10902133","display_name":"Universitat Jaume I","ror":"https://ror.org/02ws1xc11","country_code":"ES","type":"education","lineage":["https://openalex.org/I10902133"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Manuel F. Dolz","raw_affiliation_strings":["Universitat Jaume I, Castell\u00f3 de la Plana, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Jaume I, Castell\u00f3 de la Plana, Spain","institution_ids":["https://openalex.org/I10902133"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018719028","display_name":"H\u00e8ctor Mart\u00ednez","orcid":"https://orcid.org/0000-0001-5891-4479"},"institutions":[{"id":"https://openalex.org/I53110688","display_name":"University of C\u00f3rdoba","ror":"https://ror.org/05yc77b46","country_code":"ES","type":"education","lineage":["https://openalex.org/I53110688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"H\u00e9ctor Mart\u00ednez","raw_affiliation_strings":["Universidad de C\u00f3rdoba, C\u00f3rdoba, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad de C\u00f3rdoba, C\u00f3rdoba, Spain","institution_ids":["https://openalex.org/I53110688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033947083","display_name":"Adri\u00e1n Castell\u00f3","orcid":"https://orcid.org/0000-0002-8576-8451"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Adri\u00e1n Castell\u00f3","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040153798","display_name":"Pedro Alonso","orcid":"https://orcid.org/0000-0002-6882-6592"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pedro Alonso-Jord\u00e1","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012806004","display_name":"Enrique S. Quintana\u2013Ort\u0301\u0131","orcid":"https://orcid.org/0000-0002-5454-165X"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Enrique S. Quintana-Ort\u00ed","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054862021"],"corresponding_institution_ids":["https://openalex.org/I10902133"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":2.1205,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85947607,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"79","issue":"10","first_page":"10589","last_page":"10610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9965999722480774,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9202876687049866},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.8297621607780457},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.7902174592018127},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7243438959121704},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6365660429000854},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5874317288398743},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.5079889893531799},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4622494876384735},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.44815927743911743},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22338631749153137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1117216944694519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9202876687049866},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.8297621607780457},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.7902174592018127},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7243438959121704},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6365660429000854},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5874317288398743},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.5079889893531799},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4622494876384735},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.44815927743911743},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22338631749153137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1117216944694519},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s11227-023-05088-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-023-05088-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-023-05088-4.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},{"id":"pmh:oai:riunet.upv.es:10251/211502","is_oa":true,"landing_page_url":"http://hdl.handle.net/10251/211502","pdf_url":"https://riunet.upv.es/bitstreams/e51ea5ab-0605-4722-8b6c-bb4cbf86a407/download","source":{"id":"https://openalex.org/S4306400639","display_name":"RiuNet (Universitat Polit\u00e8cnica de Val\u00e8ncia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60053951","host_organization_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","host_organization_lineage":["https://openalex.org/I60053951"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:repositori.uji.es:10234/202584","is_oa":true,"landing_page_url":"http://hdl.handle.net/10234/202584","pdf_url":null,"source":{"id":"https://openalex.org/S4306400303","display_name":"Repositori UJI (Universitat Jaume I)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I10902133","host_organization_name":"Universitat Jaume I","host_organization_lineage":["https://openalex.org/I10902133"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s11227-023-05088-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-023-05088-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-023-05088-4.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1422035950","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320321864","funder_display_name":"Generalitat Valenciana"},{"id":"https://openalex.org/G1643949827","display_name":null,"funder_award_id":"AEI/10.13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G2262748287","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G2512800253","display_name":null,"funder_award_id":"FJC2019-039222-I","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G2736087390","display_name":null,"funder_award_id":"CDEIGENT/2018/014","funder_id":"https://openalex.org/F4320335711","funder_display_name":"Conselleria d'Educaci\u00f3, Investigaci\u00f3, Cultura i Esport"},{"id":"https://openalex.org/G300979063","display_name":null,"funder_award_id":"10.13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G3114316098","display_name":null,"funder_award_id":"MCIN/ AEI/10.13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G5080475149","display_name":null,"funder_award_id":"10.13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G62216336","display_name":null,"funder_award_id":"FJC2019-039222","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7084143925","display_name":null,"funder_award_id":"AEI/10","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7266728691","display_name":null,"funder_award_id":"13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7535663061","display_name":null,"funder_award_id":"AEI/10.","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G8417408325","display_name":null,"funder_award_id":"POSTDOC_21_00025","funder_id":"https://openalex.org/F4320326754","funder_display_name":"Junta de Andaluc\u00eda"}],"funders":[{"id":"https://openalex.org/F4320321864","display_name":"Generalitat Valenciana","ror":"https://ror.org/0097mvx21"},{"id":"https://openalex.org/F4320322926","display_name":"Universitat Jaume I","ror":"https://ror.org/02ws1xc11"},{"id":"https://openalex.org/F4320323868","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96"},{"id":"https://openalex.org/F4320326754","display_name":"Junta de Andaluc\u00eda","ror":"https://ror.org/01jem9c82"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null},{"id":"https://openalex.org/F4320335711","display_name":"Conselleria d'Educaci\u00f3, Investigaci\u00f3, Cultura i Esport","ror":"https://ror.org/01w104f98"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4320490426.pdf"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1487564550","https://openalex.org/W2172654076","https://openalex.org/W2604319603","https://openalex.org/W2892341857","https://openalex.org/W2950649068","https://openalex.org/W2951894856","https://openalex.org/W3057502114","https://openalex.org/W3098382995","https://openalex.org/W3129254793","https://openalex.org/W3174716098","https://openalex.org/W4224287974","https://openalex.org/W4280563761","https://openalex.org/W4281687509"],"related_works":["https://openalex.org/W2120385681","https://openalex.org/W2022113063","https://openalex.org/W2739740241","https://openalex.org/W1974923383","https://openalex.org/W2748015092","https://openalex.org/W2085105049","https://openalex.org/W2475524688","https://openalex.org/W2952876933","https://openalex.org/W2056079253","https://openalex.org/W2929736795"],"abstract_inverted_index":{"Abstract":[0],"We":[1],"take":[2],"a":[3,77,110],"step":[4],"forward":[5],"towards":[6],"developing":[7],"high-performance":[8],"codes":[9],"for":[10,24],"the":[11,16,32,35,40,53,73,80,103,119],"convolution":[12],"operator,":[13],"based":[14],"on":[15,86],"Winograd":[17],"algorithm,":[18],"that":[19,102,113],"are":[20],"easy":[21],"to":[22,51,65],"customise":[23],"general-purpose":[25],"processor":[26],"architectures.":[27],"In":[28],"our":[29,83],"approach,":[30],"augmenting":[31],"portability":[33],"of":[34,42,57,75,79],"solution":[36,112],"is":[37,105,114],"achieved":[38],"via":[39],"introduction":[41],"vector":[43],"instructions":[44],"from":[45],"Intel":[46,91],"SSE/AVX2/AVX512":[47],"and":[48,97,107],"ARM":[49,94],"NEON/SVE":[50],"exploit":[52,66],"single-instruction":[54],"multiple-data":[55],"capabilities":[56],"current":[58],"processors":[59],"as":[60,62],"well":[61],"OpenMP":[63],"pragmas":[64],"multi-threaded":[67],"parallelism.":[68],"While":[69],"this":[70],"comes":[71],"at":[72],"cost":[74],"sacrificing":[76],"fraction":[78],"computational":[81],"performance,":[82],"experimental":[84],"results":[85],"three":[87],"distinct":[88],"processors,":[89,100],"with":[90,118],"Xeon":[92],"Skylake,":[93],"Cortex":[95],"A57":[96],"Fujitsu":[98],"A64FX":[99],"show":[101],"impact":[104],"affordable":[106],"still":[108],"renders":[109],"Winograd-based":[111],"competitive":[115],"when":[116],"compared":[117],"lowering":[120],"gemm":[121],"-based":[122],"convolution.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2023-02-14T00:00:00"}
