{"id":"https://openalex.org/W2151142801","doi":"https://doi.org/10.1109/hpcsim.2011.5999886","title":"Understanding the impact of CUDA tuning techniques for Fermi","display_name":"Understanding the impact of CUDA tuning techniques for Fermi","publication_year":2011,"publication_date":"2011-07-01","ids":{"openalex":"https://openalex.org/W2151142801","doi":"https://doi.org/10.1109/hpcsim.2011.5999886","mag":"2151142801"},"language":"en","primary_location":{"id":"doi:10.1109/hpcsim.2011.5999886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2011.5999886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 International Conference on High Performance Computing &amp; Simulation","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1109/HPCSim.2011.5999886","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072874402","display_name":"Yuri Torres","orcid":"https://orcid.org/0000-0002-3037-3567"},"institutions":[{"id":"https://openalex.org/I108103353","display_name":"Universidad de Valladolid","ror":"https://ror.org/01fvbaw18","country_code":"ES","type":"education","lineage":["https://openalex.org/I108103353"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Yuri Torres","raw_affiliation_strings":["Departamento de Inform\u00e1tica, Universidad de Valladolid, Spain"],"affiliations":[{"raw_affiliation_string":"Departamento de Inform\u00e1tica, Universidad de Valladolid, Spain","institution_ids":["https://openalex.org/I108103353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025222271","display_name":"Arturo Gonz\u00e1lez-Escribano","orcid":"https://orcid.org/0000-0003-1309-9321"},"institutions":[{"id":"https://openalex.org/I108103353","display_name":"Universidad de Valladolid","ror":"https://ror.org/01fvbaw18","country_code":"ES","type":"education","lineage":["https://openalex.org/I108103353"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Arturo Gonzalez-Escribano","raw_affiliation_strings":["Departamento de Inform\u00e1tica, Universidad de Valladolid, Spain"],"affiliations":[{"raw_affiliation_string":"Departamento de Inform\u00e1tica, Universidad de Valladolid, Spain","institution_ids":["https://openalex.org/I108103353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043394187","display_name":"Diego R. Llanos","orcid":"https://orcid.org/0000-0001-6240-9109"},"institutions":[{"id":"https://openalex.org/I108103353","display_name":"Universidad de Valladolid","ror":"https://ror.org/01fvbaw18","country_code":"ES","type":"education","lineage":["https://openalex.org/I108103353"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Diego R. Llanos","raw_affiliation_strings":["Departamento de Inform\u00e1tica, Universidad de Valladolid, Spain"],"affiliations":[{"raw_affiliation_string":"Departamento de Inform\u00e1tica, Universidad de Valladolid, Spain","institution_ids":["https://openalex.org/I108103353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072874402"],"corresponding_institution_ids":["https://openalex.org/I108103353"],"apc_list":null,"apc_paid":null,"fwci":5.3922,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.96289818,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"631","last_page":"639"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9980000257492065,"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":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8955621719360352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8706076145172119},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7004841566085815},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6207188367843628},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5190625786781311},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.46299514174461365},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.45162904262542725},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4513055086135864},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.44422686100006104},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14765262603759766},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14387494325637817}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8955621719360352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8706076145172119},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7004841566085815},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6207188367843628},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5190625786781311},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.46299514174461365},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.45162904262542725},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4513055086135864},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.44422686100006104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14765262603759766},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14387494325637817},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/hpcsim.2011.5999886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2011.5999886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 International Conference on High Performance Computing &amp; Simulation","raw_type":"proceedings-article"},{"id":"pmh:oai:uvadoc.uva.es:10324/75305","is_oa":true,"landing_page_url":"https://doi.org/10.1109/HPCSim.2011.5999886","pdf_url":null,"source":{"id":"https://openalex.org/S4306401553","display_name":"UVaDOC UVaDOC University of Valladolid Documentary Repository (University of Valladolid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108103353","host_organization_name":"Universidad de Valladolid","host_organization_lineage":["https://openalex.org/I108103353"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.905.6550","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.905.6550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Arturo_Gonzalez-Escribano/publication/224255446_Understanding_the_impact_of_CUDA_tuning_techniques_for_Fermi/links/54609da00cf2c1a63bfe4070.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:uvadoc.uva.es:10324/75305","is_oa":true,"landing_page_url":"https://doi.org/10.1109/HPCSim.2011.5999886","pdf_url":null,"source":{"id":"https://openalex.org/S4306401553","display_name":"UVaDOC UVaDOC University of Valladolid Documentary Repository (University of Valladolid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108103353","host_organization_name":"Universidad de Valladolid","host_organization_lineage":["https://openalex.org/I108103353"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1762731526","https://openalex.org/W1992851788","https://openalex.org/W2098426571","https://openalex.org/W2099891946","https://openalex.org/W2100115659","https://openalex.org/W2104637563","https://openalex.org/W2110301098","https://openalex.org/W2142143431","https://openalex.org/W2398736067"],"related_works":["https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2018477250","https://openalex.org/W2769189194","https://openalex.org/W1537323515","https://openalex.org/W2353852602","https://openalex.org/W2120249721"],"abstract_inverted_index":{"While":[0],"the":[1,13,18,41,54,60,65,70,75,92,104,116,134,137,154],"correctness":[2],"of":[3,69,79,120,136],"an":[4,35,143],"NVIDIA":[5],"CUDA":[6,26],"program":[7],"is":[8,22],"easy":[9],"to":[10,16,84,147,152,158],"achieve,":[11],"exploiting":[12],"GPU":[14],"capabilities":[15],"obtain":[17],"best":[19,105],"performance":[20,106],"possible":[21],"a":[23,45],"task":[24],"for":[25,40],"experienced":[27],"programmers.":[28],"Typical":[29],"code":[30],"tuning":[31,148,162],"strategies,":[32],"like":[33],"choosing":[34],"appropriate":[36],"size":[37,76,117],"and":[38,64,77,118,127,157],"shape":[39],"thread":[42],"blocks,":[43],"programming":[44],"good":[46],"coalescing,":[47],"or":[48],"maximize":[49],"occupancy,":[50,122],"are":[51,56,81],"inter-dependent.":[52],"Moreover,":[53],"choices":[55],"also":[57],"dependent":[58],"on":[59],"underlying":[61],"architecture":[62,130],"details,":[63],"global-memory":[66],"access":[67,125],"pattern":[68],"designed":[71],"solution.":[72],"For":[73],"example,":[74],"shapes":[78,119],"threadblocks":[80],"usually":[82,102],"chosen":[83],"facilitate":[85],"encoding":[86],"(e.g.":[87],"square":[88],"shapes),":[89],"while":[90],"maximizing":[91],"multiprocessors'":[93],"occupancy.":[94],"How":[95],"ever,":[96],"this":[97,109],"simple":[98],"choice":[99],"does":[100],"not":[101],"provide":[103],"results.":[107],"In":[108],"paper":[110],"we":[111],"discuss":[112],"important":[113],"relations":[114],"between":[115],"threadblocks,":[121],"global":[123],"memory":[124],"patterns,":[126],"other":[128],"Fermi":[129],"features,":[131],"such":[132],"as":[133],"configuration":[135],"new":[138],"transparent":[139],"cache.":[140],"We":[141],"present":[142],"insight":[144],"based":[145],"approach":[146],"techniques,":[149],"providing":[150],"lines":[151],"understand":[153],"complex":[155],"relations,":[156],"easily":[159],"avoid":[160],"bad":[161],"settings.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
