{"id":"https://openalex.org/W2001611463","doi":"https://doi.org/10.1145/2082156.2082183","title":"Automatic fusions of CUDA-GPU kernels for parallel map","display_name":"Automatic fusions of CUDA-GPU kernels for parallel map","publication_year":2011,"publication_date":"2011-12-19","ids":{"openalex":"https://openalex.org/W2001611463","doi":"https://doi.org/10.1145/2082156.2082183","mag":"2001611463"},"language":"en","primary_location":{"id":"doi:10.1145/2082156.2082183","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2082156.2082183","pdf_url":null,"source":{"id":"https://openalex.org/S4210193905","display_name":"ACM SIGARCH Computer Architecture News","issn_l":"0163-5964","issn":["0163-5964","1943-5851"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320740","host_organization_name":"ACM SIGARCH","host_organization_lineage":["https://openalex.org/P4310320740"],"host_organization_lineage_names":["ACM SIGARCH"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGARCH Computer Architecture News","raw_type":"journal-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/A5045662465","display_name":"Jan Fousek","orcid":"https://orcid.org/0000-0002-8371-2956"},"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":"Jan Fousek","raw_affiliation_strings":["Masaryk University"],"affiliations":[{"raw_affiliation_string":"Masaryk University","institution_ids":["https://openalex.org/I21449261"]}]},{"author_position":"middle","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"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ji\u0159i Filipovi\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/A5046013369","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":"Matu\u0161 Madzin","raw_affiliation_strings":["Masaryk University"],"affiliations":[{"raw_affiliation_string":"Masaryk University","institution_ids":["https://openalex.org/I21449261"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045662465"],"corresponding_institution_ids":["https://openalex.org/I21449261"],"apc_list":null,"apc_paid":null,"fwci":1.2593,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.80395151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"39","issue":"4","first_page":"98","last_page":"99"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8799376487731934},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8362104296684265},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8149635791778564},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7686485648155212},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5896843075752258},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5837322473526001},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5501280426979065},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.506562352180481},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4561639428138733},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.43343618512153625},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3572503626346588},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2421620488166809},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.14639073610305786},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.13467827439308167},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1305030882358551},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07452085614204407}],"concepts":[{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8799376487731934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8362104296684265},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8149635791778564},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7686485648155212},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5896843075752258},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5837322473526001},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5501280426979065},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.506562352180481},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4561639428138733},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.43343618512153625},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3572503626346588},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2421620488166809},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.14639073610305786},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.13467827439308167},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1305030882358551},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07452085614204407},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2082156.2082183","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2082156.2082183","pdf_url":null,"source":{"id":"https://openalex.org/S4210193905","display_name":"ACM SIGARCH Computer Architecture News","issn_l":"0163-5964","issn":["0163-5964","1943-5851"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320740","host_organization_name":"ACM SIGARCH","host_organization_lineage":["https://openalex.org/P4310320740"],"host_organization_lineage_names":["ACM SIGARCH"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGARCH Computer Architecture News","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W106575872","https://openalex.org/W1264773896","https://openalex.org/W1480958225","https://openalex.org/W2021261510","https://openalex.org/W2063186542","https://openalex.org/W2071430609","https://openalex.org/W2120919211","https://openalex.org/W2146995753","https://openalex.org/W2620412100"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"When":[0],"implementing":[1],"a":[2,63],"function":[3],"mapping":[4],"on":[5],"the":[6,30,69,75,81],"contemporary":[7],"GPU,":[8],"several":[9,37],"contradictory":[10],"performance":[11],"factors":[12],"affecting":[13],"distribution":[14],"of":[15,48,65,77],"computation":[16],"into":[17,52],"GPU":[18],"kernels":[19,43,55],"have":[20],"to":[21,28,33,45,56],"be":[22,34],"balanced.":[23],"A":[24],"decomposition-fusion":[25],"scheme":[26],"suggests":[27],"decompose":[29],"computational":[31],"problem":[32],"solved":[35],"by":[36,80],"simple":[38],"functions":[39,50],"implemented":[40],"as":[41,83,85],"standalone":[42],"and":[44,74],"fuse":[46],"some":[47],"these":[49],"later":[51],"more":[53],"complex":[54],"improve":[57],"memory":[58],"locality.":[59],"In":[60],"this":[61],"paper,":[62],"prototype":[64],"source-to-source":[66],"compiler":[67,82,86],"automating":[68],"fusion":[70],"phase":[71],"is":[72,88],"presented":[73],"impact":[76],"fusions":[78],"generated":[79],"well":[84],"efficiency":[87],"experimentally":[89],"evaluated.":[90]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}