{"id":"https://openalex.org/W1922926746","doi":"https://doi.org/10.1007/s11227-015-1483-z","title":"Optimizing CUDA code by kernel fusion: application on BLAS","display_name":"Optimizing CUDA code by kernel fusion: application on BLAS","publication_year":2015,"publication_date":"2015-07-21","ids":{"openalex":"https://openalex.org/W1922926746","doi":"https://doi.org/10.1007/s11227-015-1483-z","mag":"1922926746"},"language":"en","primary_location":{"id":"doi:10.1007/s11227-015-1483-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11227-015-1483-z","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1305.1183","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ji\u0159\u00ed Filipovi\u010d","orcid":"https://orcid.org/0000-0002-5703-9673"},"institutions":[{"id":"https://openalex.org/I21449261","display_name":"Masaryk University","ror":"https://ror.org/02j46qs45","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21449261"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Ji\u0159\u00ed Filipovi\u010d","raw_affiliation_strings":["Faculty of Informatics, Masaryk University, Botanick\u00e1 68a, 602 00, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Masaryk University, Botanick\u00e1 68a, 602 00, Brno, Czech Republic","institution_ids":["https://openalex.org/I21449261"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mat\u00fa\u0161 Madzin","orcid":null},"institutions":[{"id":"https://openalex.org/I21449261","display_name":"Masaryk University","ror":"https://ror.org/02j46qs45","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21449261"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Mat\u00fa\u0161 Madzin","raw_affiliation_strings":["Faculty of Informatics, Masaryk University, Botanick\u00e1 68a, 602 00, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Masaryk University, Botanick\u00e1 68a, 602 00, Brno, Czech Republic","institution_ids":["https://openalex.org/I21449261"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jan Fousek","orcid":null},"institutions":[{"id":"https://openalex.org/I21449261","display_name":"Masaryk University","ror":"https://ror.org/02j46qs45","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21449261"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Fousek","raw_affiliation_strings":["Faculty of Informatics, Masaryk University, Botanick\u00e1 68a, 602 00, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Masaryk University, Botanick\u00e1 68a, 602 00, Brno, Czech Republic","institution_ids":["https://openalex.org/I21449261"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lud\u011bk Matyska","orcid":null},"institutions":[{"id":"https://openalex.org/I21449261","display_name":"Masaryk University","ror":"https://ror.org/02j46qs45","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21449261"]},{"id":"https://openalex.org/I4210155092","display_name":"Czech Academy of Sciences, Institute of Computer Science","ror":"https://ror.org/0496n6574","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210155092"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lud\u011bk Matyska","raw_affiliation_strings":["Institute of Computer Science, Masaryk University, Botanick\u00e1 68a, 602 00, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Masaryk University, Botanick\u00e1 68a, 602 00, Brno, Czech Republic","institution_ids":["https://openalex.org/I21449261","https://openalex.org/I4210155092"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I21449261"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":3.6281,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.92719579,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"71","issue":"10","first_page":"3934","last_page":"3957"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9409999847412109,"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":0.9409999847412109,"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":0.011900000274181366,"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"}},{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.00839999970048666,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6661999821662903},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6642000079154968},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.652899980545044},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49570000171661377},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4693000018596649},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.454800009727478},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.3714999854564667},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.36730000376701355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9208999872207642},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7211999893188477},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6661999821662903},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6642000079154968},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.652899980545044},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49570000171661377},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4693000018596649},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.454800009727478},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3714999854564667},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.36730000376701355},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.265500009059906},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.2558000087738037}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11227-015-1483-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11227-015-1483-z","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1305.1183","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1305.1183","pdf_url":"https://arxiv.org/pdf/1305.1183","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1305.1183","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1305.1183","pdf_url":"https://arxiv.org/pdf/1305.1183","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3479813890","display_name":null,"funder_award_id":"CZ.1.07/2.3.00/30.0037","funder_id":"https://openalex.org/F4320321005","funder_display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy"},{"id":"https://openalex.org/G6210024077","display_name":null,"funder_award_id":"ED3.2.00/08.0144","funder_id":"https://openalex.org/F4320321005","funder_display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy"}],"funders":[{"id":"https://openalex.org/F4320321005","display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy","ror":"https://ror.org/037n8p820"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W22188748","https://openalex.org/W1973897068","https://openalex.org/W1981896890","https://openalex.org/W2001611463","https://openalex.org/W2023415862","https://openalex.org/W2028053408","https://openalex.org/W2048269379","https://openalex.org/W2050129046","https://openalex.org/W2134427337","https://openalex.org/W2138163628","https://openalex.org/W2149381887","https://openalex.org/W2153190325","https://openalex.org/W2164326463","https://openalex.org/W2169492033","https://openalex.org/W2180959024","https://openalex.org/W4231684867","https://openalex.org/W4237609491","https://openalex.org/W4250290707","https://openalex.org/W4252345548"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2016-06-24T00:00:00"}
