{"id":"https://openalex.org/W2260757707","doi":"https://doi.org/10.1145/2832087.2832093","title":"Guided profiling for auto-tuning array layouts on GPUs","display_name":"Guided profiling for auto-tuning array layouts on GPUs","publication_year":2015,"publication_date":"2015-11-11","ids":{"openalex":"https://openalex.org/W2260757707","doi":"https://doi.org/10.1145/2832087.2832093","mag":"2260757707"},"language":"en","primary_location":{"id":"doi:10.1145/2832087.2832093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2832087.2832093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Workshop on Performance Modeling, Benchmarking, and Simulation of High Performance Computing 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/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"],"affiliations":[{"raw_affiliation_string":"TU Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031080031","display_name":"Sandra C. Amend","orcid":null},"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":"Sandra C. Amend","raw_affiliation_strings":["TU Darmstadt"],"affiliations":[{"raw_affiliation_string":"TU Darmstadt","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"],"affiliations":[{"raw_affiliation_string":"TU Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110023001"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.9352,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83096857,"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":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9979000091552734,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9979000091552734,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9955000281333923,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9944000244140625,"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/computer-science","display_name":"Computer science","score":0.841539204120636},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.7413595914840698},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6863942742347717},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.5906895399093628},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.558935284614563},{"id":"https://openalex.org/keywords/tuner","display_name":"Tuner","score":0.516969621181488},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4933415949344635},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4840211570262909},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4556903541088104},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4532630443572998},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.42667990922927856},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.41271114349365234},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.38880908489227295},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.33614057302474976},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13192442059516907},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09706717729568481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.841539204120636},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.7413595914840698},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6863942742347717},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5906895399093628},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.558935284614563},{"id":"https://openalex.org/C9819579","wikidata":"https://www.wikidata.org/wiki/Q1544018","display_name":"Tuner","level":3,"score":0.516969621181488},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4933415949344635},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4840211570262909},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4556903541088104},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4532630443572998},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.42667990922927856},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.41271114349365234},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.38880908489227295},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.33614057302474976},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13192442059516907},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09706717729568481},{"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/C74064498","wikidata":"https://www.wikidata.org/wiki/Q3396184","display_name":"Radio frequency","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2832087.2832093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2832087.2832093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Workshop on Performance Modeling, Benchmarking, and Simulation of High Performance Computing Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:78046","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/78046/","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1575955136","https://openalex.org/W1595159159","https://openalex.org/W1971367716","https://openalex.org/W1998556186","https://openalex.org/W2000873501","https://openalex.org/W2001258868","https://openalex.org/W2011159963","https://openalex.org/W2016618963","https://openalex.org/W2030961306","https://openalex.org/W2055312318","https://openalex.org/W2085118703","https://openalex.org/W2100218206","https://openalex.org/W2104329103","https://openalex.org/W2113643095","https://openalex.org/W2125517004","https://openalex.org/W2125833438","https://openalex.org/W2129232868","https://openalex.org/W2132147136","https://openalex.org/W2132598718","https://openalex.org/W2135653967","https://openalex.org/W2138163628","https://openalex.org/W2139935536","https://openalex.org/W2141389982","https://openalex.org/W2160786443","https://openalex.org/W2162404488","https://openalex.org/W2272866099","https://openalex.org/W2532040979","https://openalex.org/W3136479147","https://openalex.org/W3145506805","https://openalex.org/W6679559547","https://openalex.org/W7008759146"],"related_works":["https://openalex.org/W2056717482","https://openalex.org/W2769189194","https://openalex.org/W1537323515","https://openalex.org/W2017587301","https://openalex.org/W2353852602","https://openalex.org/W2120249721","https://openalex.org/W2030707850","https://openalex.org/W2170611190","https://openalex.org/W2566934642","https://openalex.org/W2548246577"],"abstract_inverted_index":{"Auto-tuning":[0],"for":[1,67,77,89],"Graphics":[2],"Processing":[3],"Units":[4],"(GPUs)":[5],"has":[6,52],"become":[7],"very":[8],"popular":[9],"in":[10,55,80,102],"recent":[11],"years.":[12],"It":[13],"removes":[14],"the":[15,42,49,65,74,127,132],"necessity":[16],"to":[17,40,63,141],"hand-tune":[18],"GPU":[19,58],"code":[20,66],"especially":[21],"when":[22],"a":[23,37,90,103,119,124],"new":[24,71],"hardware":[25],"architecture":[26],"is":[27,36,147],"released.":[28],"Our":[29,145],"auto-tuner":[30],"optimizes":[31],"memory":[32,50,78],"access":[33],"patterns.":[34],"This":[35,93],"key":[38],"aspect":[39],"exploit":[41],"full":[43],"performance":[44],"of":[45,69,87,96,126,138],"modern":[46],"GPUs.":[47],"As":[48],"hierarchy":[51],"historically":[53],"changed":[54],"nearly":[56],"every":[57],"generation,":[59],"it":[60],"was":[61],"necessary":[62],"reoptimize":[64],"all":[68],"these":[70],"architectures.":[72],"Unfortunately,":[73],"solution":[75],"space":[76],"optimizations":[79],"large":[81,153],"applications":[82],"can":[83],"easily":[84],"reach":[85],"millions":[86],"configurations":[88],"single":[91],"kernel.":[92],"vast":[94],"number":[95],"implementations":[97],"cannot":[98],"be":[99],"fully":[100],"evaluated":[101,151],"feasible":[104],"time.":[105],"In":[106],"this":[107],"paper":[108],"we":[109],"present":[110],"an":[111,142],"adaptive":[112],"profiling":[113,133],"algorithm":[114,146],"that":[115],"aims":[116],"at":[117,149],"finding":[118],"near":[120],"optimal":[121],"configuration":[122],"within":[123],"fraction":[125],"global":[128],"optimum,":[129],"while":[130],"reducing":[131],"time":[134],"by":[135],"several":[136],"orders":[137],"magnitude":[139],"compared":[140],"exhaustive":[143],"search.":[144],"aimed":[148],"and":[150],"on":[152],"real-world":[154],"applications.":[155]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}