{"id":"https://openalex.org/W3120016685","doi":"https://doi.org/10.1145/3434402","title":"On the Anatomy of Predictive Models for Accelerating GPU Convolution Kernels and Beyond","display_name":"On the Anatomy of Predictive Models for Accelerating GPU Convolution Kernels and Beyond","publication_year":2021,"publication_date":"2021-01-07","ids":{"openalex":"https://openalex.org/W3120016685","doi":"https://doi.org/10.1145/3434402","mag":"3120016685"},"language":"en","primary_location":{"id":"doi:10.1145/3434402","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3434402","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3434402","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3434402","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059786958","display_name":"Paolo Sylos Labini","orcid":"https://orcid.org/0000-0002-7950-4396"},"institutions":[{"id":"https://openalex.org/I171543936","display_name":"Free University of Bozen-Bolzano","ror":"https://ror.org/012ajp527","country_code":"IT","type":"education","lineage":["https://openalex.org/I171543936"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Paolo Sylos Labini","raw_affiliation_strings":["Free University of Bozen-Bolzano, Bozen-Bolzano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Free University of Bozen-Bolzano, Bozen-Bolzano, Italy","institution_ids":["https://openalex.org/I171543936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002434813","display_name":"Marco Cianfriglia","orcid":"https://orcid.org/0000-0002-6775-7804"},"institutions":[{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Cianfriglia","raw_affiliation_strings":["National Research Council of Italy, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Research Council of Italy, Italy","institution_ids":["https://openalex.org/I4210155236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032252970","display_name":"Damiano Perri","orcid":"https://orcid.org/0000-0001-6815-6659"},"institutions":[{"id":"https://openalex.org/I27483092","display_name":"University of Perugia","ror":"https://ror.org/00x27da85","country_code":"IT","type":"education","lineage":["https://openalex.org/I27483092"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Damiano Perri","raw_affiliation_strings":["University of Perugia, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Perugia, Italy","institution_ids":["https://openalex.org/I27483092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058074271","display_name":"Osvaldo Gervasi","orcid":"https://orcid.org/0000-0003-4327-520X"},"institutions":[{"id":"https://openalex.org/I27483092","display_name":"University of Perugia","ror":"https://ror.org/00x27da85","country_code":"IT","type":"education","lineage":["https://openalex.org/I27483092"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Osvaldo Gervasi","raw_affiliation_strings":["University of Perugia, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Perugia, Italy","institution_ids":["https://openalex.org/I27483092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083325184","display_name":"Grigori Fursin","orcid":"https://orcid.org/0000-0001-7719-1624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grigori Fursin","raw_affiliation_strings":["ctuning Foundation, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ctuning Foundation, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081953467","display_name":"Anton Lokhmotov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anton Lokhmotov","raw_affiliation_strings":["Dividiti, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dividiti, United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071007301","display_name":"Cedric Nugteren","orcid":null},"institutions":[{"id":"https://openalex.org/I2905213637","display_name":"TomTom (Netherlands)","ror":"https://ror.org/04as6y835","country_code":"NL","type":"company","lineage":["https://openalex.org/I2905213637"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Cedric Nugteren","raw_affiliation_strings":["TomTom, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TomTom, Netherlands","institution_ids":["https://openalex.org/I2905213637"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051748763","display_name":"Bruno Carpentieri","orcid":"https://orcid.org/0000-0002-0516-0033"},"institutions":[{"id":"https://openalex.org/I171543936","display_name":"Free University of Bozen-Bolzano","ror":"https://ror.org/012ajp527","country_code":"IT","type":"education","lineage":["https://openalex.org/I171543936"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Bruno Carpentieri","raw_affiliation_strings":["Free University of Bozen-Bolzano,Bozen-Bolzano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Free University of Bozen-Bolzano,Bozen-Bolzano, Italy","institution_ids":["https://openalex.org/I171543936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038940357","display_name":"Fabiana Zollo","orcid":"https://orcid.org/0000-0002-0833-5388"},"institutions":[{"id":"https://openalex.org/I149461666","display_name":"Ca' Foscari University of Venice","ror":"https://ror.org/04yzxz566","country_code":"IT","type":"education","lineage":["https://openalex.org/I149461666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabiana Zollo","raw_affiliation_strings":["Ca\u2019 Foscari University of Venice, Italy","Ca' Foscari University of Venice, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ca\u2019 Foscari University of Venice, Italy","institution_ids":["https://openalex.org/I149461666"]},{"raw_affiliation_string":"Ca' Foscari University of Venice, Italy","institution_ids":["https://openalex.org/I149461666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011440366","display_name":"Flavio Vella","orcid":"https://orcid.org/0000-0002-5676-9228"},"institutions":[{"id":"https://openalex.org/I171543936","display_name":"Free University of Bozen-Bolzano","ror":"https://ror.org/012ajp527","country_code":"IT","type":"education","lineage":["https://openalex.org/I171543936"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Flavio Vella","raw_affiliation_strings":["Free University of Bozen-Bolzano, Bozen-Bolzano, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5676-9228","affiliations":[{"raw_affiliation_string":"Free University of Bozen-Bolzano, Bozen-Bolzano, Italy","institution_ids":["https://openalex.org/I171543936"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5059786958"],"corresponding_institution_ids":["https://openalex.org/I171543936"],"apc_list":null,"apc_paid":null,"fwci":2.8291,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.90295876,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"18","issue":"1","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987999796867371,"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":0.9987999796867371,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9952999949455261,"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":0.8885674476623535},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.7277168035507202},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6502200365066528},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5813743472099304},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5480936765670776},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5058655142784119},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.47189199924468994},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.45602932572364807},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.44288450479507446},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.41995781660079956},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3958478569984436},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.37420451641082764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3115706443786621},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14781507849693298},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14093098044395447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8885674476623535},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.7277168035507202},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6502200365066528},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5813743472099304},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5480936765670776},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5058655142784119},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.47189199924468994},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.45602932572364807},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.44288450479507446},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.41995781660079956},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3958478569984436},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.37420451641082764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3115706443786621},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14781507849693298},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14093098044395447},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3434402","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3434402","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3434402","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},{"id":"pmh:oai:alma.39UBZ_INST:11251743840001241","is_oa":true,"landing_page_url":"https://dl.acm.org/doi/10.1145/3434402","pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:flore.unifi.it:2158/1293233","is_oa":true,"landing_page_url":"https://hdl.handle.net/2158/1293233","pdf_url":null,"source":{"id":"https://openalex.org/S4306402033","display_name":"Florence Research (University of Florence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45084792","host_organization_name":"University of Florence","host_organization_lineage":["https://openalex.org/I45084792"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:iris.unitn.it:11572/332635","is_oa":false,"landing_page_url":"http://hdl.handle.net/11572/332635","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:iris.unive.it:10278/3734983","is_oa":false,"landing_page_url":"http://hdl.handle.net/10278/3734983","pdf_url":null,"source":{"id":"https://openalex.org/S4306402336","display_name":"ARCA (Universit\u00e0 Ca' Foscari Venezia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149461666","host_organization_name":"Ca' Foscari University of Venice","host_organization_lineage":["https://openalex.org/I149461666"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1145/3434402","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3434402","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3434402","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5102386346","display_name":null,"funder_award_id":"H2020-ICT-2015","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G6343567564","display_name":null,"funder_award_id":"INdAM-GNCS Project 2020","funder_id":"https://openalex.org/F4320334079","funder_display_name":"Gruppo Nazionale per il Calcolo Scientifico"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320311030","display_name":"Istituto Nazionale di Alta Matematica \"Francesco Severi\"","ror":"https://ror.org/01vx64p53"},{"id":"https://openalex.org/F4320325400","display_name":"Libera Universit\u00e0 di Bolzano","ror":"https://ror.org/012ajp527"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334079","display_name":"Gruppo Nazionale per il Calcolo Scientifico","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3120016685.pdf","grobid_xml":"https://content.openalex.org/works/W3120016685.grobid-xml"},"referenced_works_count":90,"referenced_works":["https://openalex.org/W46659105","https://openalex.org/W207309682","https://openalex.org/W376280045","https://openalex.org/W1482680420","https://openalex.org/W1483717008","https://openalex.org/W1496508106","https://openalex.org/W1501386175","https://openalex.org/W1863336885","https://openalex.org/W1947869163","https://openalex.org/W1971367716","https://openalex.org/W1978642402","https://openalex.org/W1984222112","https://openalex.org/W2004683477","https://openalex.org/W2005232436","https://openalex.org/W2008183828","https://openalex.org/W2033088400","https://openalex.org/W2037854811","https://openalex.org/W2041316443","https://openalex.org/W2046526098","https://openalex.org/W2059745360","https://openalex.org/W2062368747","https://openalex.org/W2073061372","https://openalex.org/W2093843662","https://openalex.org/W2095727900","https://openalex.org/W2097117768","https://openalex.org/W2100218206","https://openalex.org/W2101234009","https://openalex.org/W2102667697","https://openalex.org/W2106057110","https://openalex.org/W2107911628","https://openalex.org/W2119821739","https://openalex.org/W2125283600","https://openalex.org/W2128539477","https://openalex.org/W2135653967","https://openalex.org/W2140190241","https://openalex.org/W2159287299","https://openalex.org/W2163605009","https://openalex.org/W2172654076","https://openalex.org/W2279098554","https://openalex.org/W2296138103","https://openalex.org/W2417359092","https://openalex.org/W2604546911","https://openalex.org/W2605739168","https://openalex.org/W2615663338","https://openalex.org/W2623418689","https://openalex.org/W2725201101","https://openalex.org/W2725757310","https://openalex.org/W2730364998","https://openalex.org/W2731053425","https://openalex.org/W2751387202","https://openalex.org/W2755088640","https://openalex.org/W2766213466","https://openalex.org/W2767319308","https://openalex.org/W2783614532","https://openalex.org/W2786320458","https://openalex.org/W2788264912","https://openalex.org/W2790691034","https://openalex.org/W2791258966","https://openalex.org/W2804032941","https://openalex.org/W2809021737","https://openalex.org/W2809619744","https://openalex.org/W2887327791","https://openalex.org/W2902243168","https://openalex.org/W2914926228","https://openalex.org/W2920893842","https://openalex.org/W2946494244","https://openalex.org/W2952598959","https://openalex.org/W2955064481","https://openalex.org/W2964301839","https://openalex.org/W3011121930","https://openalex.org/W3015089394","https://openalex.org/W3033509590","https://openalex.org/W3036692157","https://openalex.org/W3094420268","https://openalex.org/W3102753670","https://openalex.org/W3103983137","https://openalex.org/W3105204543","https://openalex.org/W3119880013","https://openalex.org/W3136479147","https://openalex.org/W4212774754","https://openalex.org/W4230289604","https://openalex.org/W4235600583","https://openalex.org/W4239510810","https://openalex.org/W4242726609","https://openalex.org/W4243261006","https://openalex.org/W4250027548","https://openalex.org/W4256300792","https://openalex.org/W4288115929","https://openalex.org/W4297957988","https://openalex.org/W4376272906"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W4245975140","https://openalex.org/W2532592438","https://openalex.org/W1977763331","https://openalex.org/W2103136046","https://openalex.org/W2022120297","https://openalex.org/W3193149001","https://openalex.org/W2004686618"],"abstract_inverted_index":{"Efficient":[0],"HPC":[1],"libraries":[2],"often":[3],"expose":[4],"multiple":[5],"tunable":[6],"parameters,":[7],"algorithmic":[8,23],"implementations,":[9],"or":[10,47],"a":[11],"combination":[12],"of":[13,34,67,98,110,121],"them,":[14],"to":[15,86,117,153,156],"provide":[16],"optimized":[17],"routines.":[18],"The":[19],"optimal":[20],"parameters":[21,43],"and":[22,69,83,91,101,107,158,167],"choices":[24],"may":[25],"depend":[26],"on":[27,127,137],"input":[28],"properties":[29],"such":[30,54],"as":[31,55,130,132],"the":[32,35,39,64,88,96,104,111,119,147],"shapes":[33],"matrices":[36],"involved":[37],"in":[38,72,146],"operation.":[40],"Traditionally,":[41],"these":[42],"are":[44],"manually":[45],"tuned":[46],"set":[48],"by":[49,162],"auto-tuners.":[50],"In":[51,74],"emerging":[52],"applications":[53,149],"deep":[56,124],"learning,":[57],"this":[58,75],"approach":[59],"is":[60],"not":[61],"effective":[62],"across":[63],"wide":[65],"range":[66],"inputs":[68],"architectures":[70,136],"used":[71],"practice.":[73],"work,":[76],"we":[77,94,102],"analyze":[78],"different":[79,139],"machine":[80],"learning":[81,125],"techniques":[82],"predictive":[84],"models":[85],"accelerate":[87],"convolution":[89],"operator":[90],"GEMM.":[92],"Moreover,":[93],"address":[95],"problem":[97],"dataset":[99],"generation,":[100],"study":[103],"performance,":[105],"accuracy,":[106],"generalization":[108],"ability":[109],"models.":[112,169],"Our":[113],"insights":[114],"allow":[115],"us":[116],"improve":[118],"performance":[120],"computationally":[122],"expensive":[123],"primitives":[126],"high-end":[128],"GPUs":[129],"well":[131],"low-power":[133],"embedded":[134],"GPU":[135],"three":[138],"libraries.":[140],"Experimental":[141],"results":[142],"show":[143],"significant":[144],"improvement":[145],"target":[148],"from":[150],"50%":[151],"up":[152],"300%":[154],"compared":[155],"auto-tuned":[157],"high-optimized":[159],"vendor-based":[160],"heuristics":[161],"using":[163],"simple":[164],"decision":[165],"tree-":[166],"MLP-based":[168]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-01-18T00:00:00"}