{"id":"https://openalex.org/W4311486595","doi":"https://doi.org/10.1007/s11227-022-05003-3","title":"Micro-kernels for portable and efficient matrix multiplication in deep learning","display_name":"Micro-kernels for portable and efficient matrix multiplication in deep learning","publication_year":2022,"publication_date":"2022-12-14","ids":{"openalex":"https://openalex.org/W4311486595","doi":"https://doi.org/10.1007/s11227-022-05003-3"},"language":"en","primary_location":{"id":"doi:10.1007/s11227-022-05003-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-022-05003-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-022-05003-3.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/s11227-022-05003-3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004018864","display_name":"Guillermo Alaejos","orcid":"https://orcid.org/0000-0001-5909-3094"},"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":"Guillermo Alaejos","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Val\u00e8ncia, Val\u00e8ncia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Val\u00e8ncia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"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":true,"raw_author_name":"Adri\u00e1n Castell\u00f3","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Val\u00e8ncia, Val\u00e8ncia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Val\u00e8ncia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"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/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, Val\u00e8ncia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Val\u00e8ncia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075880248","display_name":"Francisco D. Igual","orcid":"https://orcid.org/0000-0003-4480-9517"},"institutions":[{"id":"https://openalex.org/I121748325","display_name":"Universidad Complutense de Madrid","ror":"https://ror.org/02p0gd045","country_code":"ES","type":"education","lineage":["https://openalex.org/I121748325"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Francisco D. Igual","raw_affiliation_strings":["Universidad Complutense de Madrid, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Complutense de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I121748325"]}]},{"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, Val\u00e8ncia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Val\u00e8ncia, Spain","institution_ids":["https://openalex.org/I60053951"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033947083"],"corresponding_institution_ids":["https://openalex.org/I60053951"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":3.4809,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.9353157,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"79","issue":"7","first_page":"8124","last_page":"8147"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9983000159263611,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/simd","display_name":"SIMD","score":0.9340616464614868},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8810644149780273},{"id":"https://openalex.org/keywords/intrinsics","display_name":"Intrinsics","score":0.8300503492355347},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7629462480545044},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5979726910591125},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5728853940963745},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5464417934417725},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.4857204556465149},{"id":"https://openalex.org/keywords/single-precision-floating-point-format","display_name":"Single-precision floating-point format","score":0.4130232334136963},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.176744282245636}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.9340616464614868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8810644149780273},{"id":"https://openalex.org/C2908650547","wikidata":"https://www.wikidata.org/wiki/Q20999234","display_name":"Intrinsics","level":2,"score":0.8300503492355347},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7629462480545044},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5979726910591125},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5728853940963745},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5464417934417725},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.4857204556465149},{"id":"https://openalex.org/C133095886","wikidata":"https://www.wikidata.org/wiki/Q1307173","display_name":"Single-precision floating-point format","level":3,"score":0.4130232334136963},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.176744282245636},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11227-022-05003-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-022-05003-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-022-05003-3.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:10251/199584","is_oa":true,"landing_page_url":"http://hdl.handle.net/10251/199584","pdf_url":"https://riunet.upv.es/bitstream/10251/199584/1/Alaejos-LopezCastelloMartinez%20-%20Micro-kernels%20for%20portable%20and%20efficient%20matrix%20multiplication%20in....pdf","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-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"}],"best_oa_location":{"id":"doi:10.1007/s11227-022-05003-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-022-05003-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-022-05003-3.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":[],"awards":[{"id":"https://openalex.org/G1622782223","display_name":null,"funder_award_id":"MCIN/AEI/10","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"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/G1889187437","display_name":null,"funder_award_id":"FJC2019-039222-I","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G1923596760","display_name":null,"funder_award_id":"PID2020-113656RB-C22","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\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/G2309143163","display_name":null,"funder_award_id":"RTI2018-093684-B-I00","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G2312845444","display_name":null,"funder_award_id":"PID2021-126576NB-I00","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G2359364823","display_name":null,"funder_award_id":"MCIN/AEI/10.13039/501100011033","funder_id":"https://openalex.org/F4320323868","funder_display_name":"Barcelona Supercomputing Center"},{"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/G2545389795","display_name":null,"funder_award_id":"MCIN/AEI/10.13039/501100011033","funder_id":"https://openalex.org/F4320319605","funder_display_name":"Consejer\u00eda de Transformaci\u00f3n Econ\u00f3mica, Industria, Conocimiento y Universidades"},{"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/G3219925899","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/G3855998773","display_name":null,"funder_award_id":"S2018/TCS-4423","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G4045093968","display_name":null,"funder_award_id":"MCIN/AEI/10.13039/501100011033","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G410571670","display_name":null,"funder_award_id":"10.13039/501100011033","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G4337095679","display_name":null,"funder_award_id":"PR65/19-22445","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G451917667","display_name":null,"funder_award_id":"13039/501100011033","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"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/G5421083681","display_name":null,"funder_award_id":"MCIN/ AEI/10.13039/501100011033","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G5539308778","display_name":null,"funder_award_id":"AEI/10.13039/501100011033","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G5967599077","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"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/G6298273575","display_name":null,"funder_award_id":"RTI2018","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G6756106972","display_name":null,"funder_award_id":"MCIN/AEI/10","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G6946262214","display_name":null,"funder_award_id":"PID2020-113656RB-C22","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/G7434936867","display_name":null,"funder_award_id":"PID2021","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/G7657615468","display_name":null,"funder_award_id":"RTI2018-093684-B-I00","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G822310507","display_name":null,"funder_award_id":"S2018/TCS-4423","funder_id":"https://openalex.org/F4320313831","funder_display_name":"Comunidad de Madrid"},{"id":"https://openalex.org/G8716935391","display_name":null,"funder_award_id":"MCIN/AEI/10.13039/501100011033","funder_id":"https://openalex.org/F4320326754","funder_display_name":"Junta de Andaluc\u00eda"}],"funders":[{"id":"https://openalex.org/F4320313831","display_name":"Comunidad de Madrid","ror":null},{"id":"https://openalex.org/F4320319605","display_name":"Consejer\u00eda de Transformaci\u00f3n Econ\u00f3mica, Industria, Conocimiento y Universidades","ror":null},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"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/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4311486595.pdf","grobid_xml":"https://content.openalex.org/works/W4311486595.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1546569454","https://openalex.org/W1983157164","https://openalex.org/W1984212674","https://openalex.org/W2002257715","https://openalex.org/W2002555321","https://openalex.org/W2043275593","https://openalex.org/W2073061372","https://openalex.org/W2194775991","https://openalex.org/W2252007067","https://openalex.org/W4224278821","https://openalex.org/W4281687509"],"related_works":["https://openalex.org/W4289638474","https://openalex.org/W2069504277","https://openalex.org/W4401454459","https://openalex.org/W2293666837","https://openalex.org/W2067411013","https://openalex.org/W1977434943","https://openalex.org/W4226248541","https://openalex.org/W4302004660","https://openalex.org/W2550374317","https://openalex.org/W2588463123"],"abstract_inverted_index":{"Abstract":[0],"We":[1],"provide":[2],"a":[3,13,73,136],"practical":[4],"demonstration":[5],"that":[6,84],"it":[7],"is":[8],"possible":[9],"to":[10,34,47],"systematically":[11],"generate":[12],"variety":[14],"of":[15,65,91,108],"high-performance":[16],"micro-kernels":[17,111],"for":[18,61,112,129],"the":[19,49,62,106,109],"general":[20],"matrix":[21],"multiplication":[22],"(":[23],"gemm":[24,66,92],")":[25],"via":[26],"generic":[27,42],"templates":[28,43],"which":[29],"can":[30],"be":[31],"easily":[32],"customized":[33],"different":[35],"processor":[36,133,139,148],"architectures":[37],"and":[38,121,142],"micro-kernel":[39],"dimensions.":[40],"These":[41],"employ":[44],"vector":[45],"intrinsics":[46],"exploit":[48],"SIMD":[50],"(single":[51],"instruction,":[52],"multiple":[53],"data)":[54],"units":[55],"in":[56,69,93],"current":[57,94],"general-purpose":[58],"processors":[59],"and,":[60],"particular":[63],"type":[64],"problems":[67],"encountered":[68],"deep":[70],"learning,":[71],"deliver":[72],"floating-point":[74],"throughput":[75],"rate":[76],"on":[77,143],"par":[78],"with":[79,86],"or":[80],"even":[81],"higher":[82],"than":[83],"obtained":[85],"conventional,":[87],"carefully":[88],"tuned":[89],"implementations":[90],"linear":[95],"algebra":[96],"libraries":[97],"(e.g.,":[98],"BLIS,":[99],"AMD":[100,145],"AOCL,":[101],"ARMPL).":[102],"Our":[103],"work":[104],"exposes":[105],"structure":[107],"template-based":[110],"ARM":[113,117],"Neon":[114],"(128-bit":[115],"SIMD),":[116,125],"SVE":[118],"(variable-length":[119],"SIMD)":[120],"Intel":[122],"AVX512":[123],"(512-bit":[124],"showing":[126],"considerable":[127],"performance":[128],"an":[130,144],"NVIDIA":[131],"Carmel":[132],"(ARM":[134,140],"Neon),":[135],"Fujitsu":[137],"A64FX":[138],"SVE)":[141],"EPYC":[146],"7282":[147],"(256-bit":[149],"SIMD).":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}
