{"id":"https://openalex.org/W2604690062","doi":"https://doi.org/10.3233/978-1-61499-484-8-195","title":"Auto-Tuning for GPGPU Applications Using Performance and Energy Model","display_name":"Auto-Tuning for GPGPU Applications Using Performance and Energy Model","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2604690062","doi":"https://doi.org/10.3233/978-1-61499-484-8-195","mag":"2604690062"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-484-8-195","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-484-8-195","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","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/A5101768797","display_name":"Chih-Sheng Lin","orcid":"https://orcid.org/0000-0001-7055-8374"},"institutions":[{"id":"https://openalex.org/I142066694","display_name":"ITRI International","ror":"https://ror.org/04wwsbd59","country_code":"US","type":"facility","lineage":["https://openalex.org/I142066694"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lin Chih-Sheng","raw_affiliation_strings":["ITRI International, San Jose, United States"],"affiliations":[{"raw_affiliation_string":"ITRI International, San Jose, United States","institution_ids":["https://openalex.org/I142066694"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035222402","display_name":"Shih-Meng Teng","orcid":null},"institutions":[{"id":"https://openalex.org/I148099254","display_name":"National Chung Cheng University","ror":"https://ror.org/0028v3876","country_code":"TW","type":"education","lineage":["https://openalex.org/I148099254"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Teng Shih-Meng","raw_affiliation_strings":["National Chung Cheng University, Minxiong, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Chung Cheng University, Minxiong, Taiwan","institution_ids":["https://openalex.org/I148099254"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050423310","display_name":"Pao\u2010Ann Hsiung","orcid":"https://orcid.org/0000-0002-3639-1467"},"institutions":[{"id":"https://openalex.org/I148099254","display_name":"National Chung Cheng University","ror":"https://ror.org/0028v3876","country_code":"TW","type":"education","lineage":["https://openalex.org/I148099254"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsiung Pao-Ann","raw_affiliation_strings":["National Chung Cheng University, Minxiong, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Chung Cheng University, Minxiong, Taiwan","institution_ids":["https://openalex.org/I148099254"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101768797"],"corresponding_institution_ids":["https://openalex.org/I142066694"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36427851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.992900013923645,"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":0.992900013923645,"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":0.9786999821662903,"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":0.95660001039505,"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/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.7222573757171631},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6494062542915344},{"id":"https://openalex.org/keywords/auto-tuning","display_name":"Auto tuning","score":0.4858248233795166},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.42293959856033325},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.1561935842037201},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07954230904579163},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.05087551474571228}],"concepts":[{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.7222573757171631},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6494062542915344},{"id":"https://openalex.org/C2986422732","wikidata":"https://www.wikidata.org/wiki/Q753025","display_name":"Auto tuning","level":4,"score":0.4858248233795166},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42293959856033325},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.1561935842037201},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07954230904579163},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.05087551474571228},{"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/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.0},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/978-1-61499-484-8-195","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-484-8-195","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8999999761581421,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2505380084","https://openalex.org/W2390279801","https://openalex.org/W4400333498","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W1980160788"],"abstract_inverted_index":{"The":[0,77],"general-purpose":[1],"graphic":[2],"processing":[3],"unit":[4],"(GPGPU)":[5],"is":[6,49,122,128],"a":[7,47,52,66,110,133,137],"popular":[8],"accelerator":[9],"for":[10,65,80,100,114,130,136,167,184],"general":[11],"applications":[12,19,102],"such":[13],"as":[14,42,147],"scientific":[15],"computing":[16,29],"because":[17],"the":[18,24,37,43,88,104,145,148,155,161,174,178,182,188,194,204,207],"are":[20,84],"massively":[21],"parallel":[22,28],"and":[23,62,106,117,151,169,172,193],"significant":[25],"power":[26,75,107,118],"of":[27,40,91,120,163,176,190,196],"inheriting":[30],"from":[31],"GPUs.":[32],"However,":[33],"distributing":[34],"workload":[35],"among":[36],"large":[38],"number":[39],"cores":[41],"execution":[44],"configuration":[45,135,198],"in":[46,199],"GPGPU":[48,101],"currently":[50],"still":[51],"manual":[53],"trial-and-error":[54],"process.":[55],"Programmers":[56],"try":[57],"out":[58],"manually":[59],"some":[60],"configurations":[61],"might":[63],"settle":[64],"sub-optimal":[67],"one":[68],"leading":[69],"to":[70],"poor":[71],"performance":[72,105,116,168],"and/or":[73],"high":[74],"consumption.":[76],"state-of-the-art":[78],"methods":[79],"addressing":[81],"this":[82,141],"issue":[83],"mainly":[85],"based":[86],"on":[87],"heavy":[89],"profiling":[90],"computation":[92],"kernels.":[93],"This":[94],"paper":[95],"presents":[96],"an":[97,125],"auto-tuning":[98,126,179],"approach":[99,113],"with":[103,181],"models.":[108],"First,":[109],"model-based":[111],"analytic":[112],"estimating":[115],"consumption":[119],"kernels":[121],"proposed.":[123],"Second,":[124],"framework":[127],"proposed":[129,165,201],"automatically":[131],"obtaining":[132],"near-optimal":[134],"kernel":[138],"computation.":[139],"In":[140],"work,":[142],"we":[143],"formulate":[144],"problem":[146],"constraint":[149],"optimization":[150,156],"solve":[152],"it":[153],"using":[154],"algorithms.":[157],"Experimental":[158],"results":[159],"show":[160,203],"fidelity":[162],"our":[164,200],"models":[166,183],"energy":[170],"consumption,":[171],"prove":[173],"rationality":[175],"adopting":[177],"method":[180,202],"minimizing":[185],"overhead.":[186],"Further,":[187],"efficiency":[189],"tuning":[191],"procedure":[192],"quality":[195],"outcome":[197],"superiorities":[205],"over":[206],"previous":[208],"methods.":[209]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2017-04-14T00:00:00"}