{"id":"https://openalex.org/W2344642201","doi":"https://doi.org/10.1145/2916026.2916031","title":"Adaptive GPU Array Layout Auto-Tuning","display_name":"Adaptive GPU Array Layout Auto-Tuning","publication_year":2016,"publication_date":"2016-05-27","ids":{"openalex":"https://openalex.org/W2344642201","doi":"https://doi.org/10.1145/2916026.2916031","mag":"2344642201"},"language":"en","primary_location":{"id":"doi:10.1145/2916026.2916031","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2916026.2916031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Workshop on Software Engineering Methods for Parallel and High Performance Applications","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/A5110023001","display_name":"Nicolas Weber","orcid":"https://orcid.org/0000-0003-0032-9511"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Nicolas Weber","raw_affiliation_strings":["TU Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066521879","display_name":"Michael Goesele","orcid":"https://orcid.org/0000-0002-0944-0980"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Goesele","raw_affiliation_strings":["TU Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110023001"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":1.5767,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81436901,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"28"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980000257492065,"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":0.9954000115394592,"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":0.869139552116394},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6717862486839294},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5829793810844421},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.5415388345718384},{"id":"https://openalex.org/keywords/titan","display_name":"Titan (rocket family)","score":0.5082356333732605},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5082077980041504},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.45006975531578064},{"id":"https://openalex.org/keywords/auto-tuning","display_name":"Auto tuning","score":0.4465317130088806},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.43879061937332153},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4351353347301483},{"id":"https://openalex.org/keywords/performance-tuning","display_name":"Performance tuning","score":0.4330573081970215},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4210744798183441},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10541260242462158}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.869139552116394},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6717862486839294},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5829793810844421},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5415388345718384},{"id":"https://openalex.org/C50805821","wikidata":"https://www.wikidata.org/wiki/Q1136670","display_name":"Titan (rocket family)","level":2,"score":0.5082356333732605},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5082077980041504},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.45006975531578064},{"id":"https://openalex.org/C2986422732","wikidata":"https://www.wikidata.org/wiki/Q753025","display_name":"Auto tuning","level":4,"score":0.4465317130088806},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43879061937332153},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4351353347301483},{"id":"https://openalex.org/C2777138346","wikidata":"https://www.wikidata.org/wiki/Q1714153","display_name":"Performance tuning","level":2,"score":0.4330573081970215},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4210744798183441},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10541260242462158},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"score":0.0},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2916026.2916031","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2916026.2916031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Workshop on Software Engineering Methods for Parallel and High Performance Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:82600","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/82600/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W172770979","https://openalex.org/W1971367716","https://openalex.org/W1988307172","https://openalex.org/W2016618963","https://openalex.org/W2033088400","https://openalex.org/W2039727401","https://openalex.org/W2058328063","https://openalex.org/W2080592089","https://openalex.org/W2091599698","https://openalex.org/W2100218206","https://openalex.org/W2125833438","https://openalex.org/W2141389982","https://openalex.org/W2160786443","https://openalex.org/W2162404488","https://openalex.org/W2168559597","https://openalex.org/W2260757707","https://openalex.org/W2272866099","https://openalex.org/W2504987011"],"related_works":["https://openalex.org/W2408545863","https://openalex.org/W643179351","https://openalex.org/W2740469715","https://openalex.org/W2905265805","https://openalex.org/W2162805293","https://openalex.org/W2149446117","https://openalex.org/W4382052962","https://openalex.org/W2045128810","https://openalex.org/W3164683393","https://openalex.org/W2612334572"],"abstract_inverted_index":{"Optimal":[0],"performance":[1,73,86],"is":[2,142,160],"an":[3,30,38,96,118],"important":[4],"goal":[5],"in":[6,44,102,113,165],"compute":[7],"intensive":[8],"applications.":[9,46,131],"For":[10],"GPU":[11],"applications,":[12],"this":[13,134],"requires":[14,112],"a":[15,137,166],"lot":[16],"of":[17,74,99,122,172],"experience":[18],"and":[19,24,51,68,150],"knowledge":[20],"about":[21],"the":[22,25,49,100],"algorithms":[23],"underlying":[26],"hardware,":[27],"making":[28],"them":[29],"ideal":[31],"target":[32],"for":[33,117,129],"auto-tuning":[34],"approaches.":[35],"We":[36,60,78,94,132],"present":[37],"auto-tuner":[39],"which":[40,124],"optimizes":[41],"array":[42,63],"layouts":[43,64],"CUDA":[45],"Depending":[47],"on":[48],"data":[50,81,116],"program":[52],"parameters,":[53],"kernels":[54],"can":[55],"have":[56],"varying":[57],"optimal":[58,156],"configurations.":[59],"thus":[61],"adjust":[62],"adaptively":[65],"at":[66],"runtime":[67],"achieve":[69],"or":[70,91],"even":[71],"exceed":[72],"hand":[75,178],"optimized":[76,179],"code.":[77,180],"automatically":[79],"detect":[80],"characteristics":[82],"to":[83,104,144,153,162,174,177],"identify":[84],"different":[85],"scenarios":[87,123],"without":[88],"user":[89],"input":[90],"additional":[92],"programming.":[93],"perform":[95],"empirical":[97],"analysis":[98],"application":[101],"order":[103],"construct":[105],"our":[106],"decision":[107],"models.":[108],"Our":[109,158],"adaptive":[110],"optimization":[111],"principle":[114],"profiling":[115],"extremely":[119],"high":[120],"number":[121],"cannot":[125],"be":[126],"exhaustively":[127],"evaluated":[128],"complex":[130],"solve":[133],"by":[135],"extending":[136],"previously":[138],"published":[139],"method":[140,159],"that":[141],"able":[143,161],"efficiently":[145],"profile":[146],"single":[147],"kernel":[148],"calls":[149],"enhance":[151],"it":[152],"find":[154],"application-wide":[155],"solutions.":[157],"optimize":[163],"applications":[164],"few":[167],"minutes,":[168],"reaching":[169],"speed":[170],"ups":[171],"up":[173],"20%":[175],"compared":[176]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-02-26T08:16:20.718346","created_date":"2025-10-10T00:00:00"}
