{"id":"https://openalex.org/W2768520977","doi":"https://doi.org/10.1145/3152821.3152877","title":"Autotuning of OpenCL Kernels with Global Optimizations","display_name":"Autotuning of OpenCL Kernels with Global Optimizations","publication_year":2017,"publication_date":"2017-09-09","ids":{"openalex":"https://openalex.org/W2768520977","doi":"https://doi.org/10.1145/3152821.3152877","mag":"2768520977"},"language":"en","primary_location":{"id":"doi:10.1145/3152821.3152877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3152821.3152877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on AutotuniNg and aDaptivity AppRoaches for Energy efficient HPC Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089216324","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"]},{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]}],"countries":["AT","CZ"],"is_corresponding":true,"raw_author_name":"Ji\u0159\u00ed Filipovi\u010d","raw_affiliation_strings":["Masaryk University, University of Vienna"],"affiliations":[{"raw_affiliation_string":"Masaryk University, University of Vienna","institution_ids":["https://openalex.org/I21449261","https://openalex.org/I129774422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022500174","display_name":"Filip Petrovi\u0107","orcid":"https://orcid.org/0009-0003-6474-9205"},"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":"Filip Petrovi\u010d","raw_affiliation_strings":["Masaryk University"],"affiliations":[{"raw_affiliation_string":"Masaryk University","institution_ids":["https://openalex.org/I21449261"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065806871","display_name":"Siegfried Benkner","orcid":"https://orcid.org/0000-0002-6520-2047"},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Siegfried Benkner","raw_affiliation_strings":["University of Vienna"],"affiliations":[{"raw_affiliation_string":"University of Vienna","institution_ids":["https://openalex.org/I129774422"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5089216324"],"corresponding_institution_ids":["https://openalex.org/I129774422","https://openalex.org/I21449261"],"apc_list":null,"apc_paid":null,"fwci":0.9013,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.757233,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.8830670118331909},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.828764796257019},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.7655667066574097},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5682001113891602},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5577391982078552},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.5510608553886414},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.45862194895744324},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2806926369667053},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.16358187794685364},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16111144423484802},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.13816002011299133}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8830670118331909},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.828764796257019},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.7655667066574097},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5682001113891602},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5577391982078552},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.5510608553886414},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.45862194895744324},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2806926369667053},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.16358187794685364},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16111144423484802},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.13816002011299133},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3152821.3152877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3152821.3152877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on AutotuniNg and aDaptivity AppRoaches for Energy efficient HPC Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1488731993","https://openalex.org/W1790519466","https://openalex.org/W1863336885","https://openalex.org/W1922926746","https://openalex.org/W1978362304","https://openalex.org/W2059745360","https://openalex.org/W2062368747","https://openalex.org/W2102182691","https://openalex.org/W2128120785","https://openalex.org/W2132117096","https://openalex.org/W2135653967","https://openalex.org/W2140707050","https://openalex.org/W2152503947","https://openalex.org/W2157310776","https://openalex.org/W2159497832","https://openalex.org/W2170216784","https://openalex.org/W2261716154","https://openalex.org/W2265322554","https://openalex.org/W2294864096","https://openalex.org/W2525951357","https://openalex.org/W2616027267","https://openalex.org/W3103983137","https://openalex.org/W3105204543","https://openalex.org/W3123057955","https://openalex.org/W3136479147","https://openalex.org/W4231859022","https://openalex.org/W4250119831"],"related_works":["https://openalex.org/W1763971038","https://openalex.org/W2371501690","https://openalex.org/W2093143612","https://openalex.org/W3144161808","https://openalex.org/W2583394830","https://openalex.org/W2357498671","https://openalex.org/W4241263734","https://openalex.org/W4245302940","https://openalex.org/W1549901675","https://openalex.org/W2768520977"],"abstract_inverted_index":{"Autotuning":[0],"is":[1],"an":[2],"important":[3],"method":[4],"for":[5],"automatically":[6],"exploring":[7],"code":[8,14],"optimizations.":[9],"It":[10],"may":[11],"target":[12],"low-level":[13],"optimizations,":[15,29],"such":[16,30],"as":[17,25,27,31],"memory":[18,23,41],"blocking,":[19],"loop":[20],"unrolling":[21],"or":[22,45],"prefetching,":[24],"well":[26],"high-level":[28],"placement":[32],"of":[33],"computation":[34],"kernels":[35],"on":[36],"proper":[37],"hardware":[38],"devices,":[39],"optimizing":[40],"transfers":[42],"between":[43,46],"nodes":[44],"accelerators":[47],"and":[48],"main":[49],"memory.":[50]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}