{"id":"https://openalex.org/W2160786443","doi":"https://doi.org/10.1109/ipdps.2009.5160988","title":"A cross-input adaptive framework for GPU program optimizations","display_name":"A cross-input adaptive framework for GPU program optimizations","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2160786443","doi":"https://doi.org/10.1109/ipdps.2009.5160988","mag":"2160786443"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2009.5160988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2009.5160988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Parallel & Distributed Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5061441276","display_name":"Yixun Liu","orcid":"https://orcid.org/0009-0005-3961-7977"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yixun Liu","raw_affiliation_strings":["Computer Science Department, College of William and Mary, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, College of William and Mary, USA","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049890668","display_name":"Eddy Z. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eddy Z. Zhang","raw_affiliation_strings":["Computer Science Department, College of William and Mary, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, College of William and Mary, USA","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624451","display_name":"Xipeng Shen","orcid":"https://orcid.org/0000-0003-3599-8010"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xipeng Shen","raw_affiliation_strings":["Computer Science Department, College of William and Mary, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, College of William and Mary, USA","institution_ids":["https://openalex.org/I16285277"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16285277"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":135,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8697896599769592},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7772054672241211},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6742124557495117},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6643827557563782},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.5904033184051514},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5855212807655334},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5417225360870361},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.4759666323661804},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.46453553438186646},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.4597369432449341},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4289618730545044},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.41207098960876465},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35427337884902954},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3482446074485779},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.2158530056476593},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.20769813656806946},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.14833009243011475},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1066426932811737}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8697896599769592},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7772054672241211},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6742124557495117},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6643827557563782},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.5904033184051514},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5855212807655334},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5417225360870361},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.4759666323661804},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.46453553438186646},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.4597369432449341},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4289618730545044},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.41207098960876465},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35427337884902954},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3482446074485779},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.2158530056476593},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.20769813656806946},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.14833009243011475},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1066426932811737},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2009.5160988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2009.5160988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Parallel & Distributed Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.550000011920929,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1517684295","https://openalex.org/W1964031104","https://openalex.org/W1972209410","https://openalex.org/W1991591392","https://openalex.org/W1992851788","https://openalex.org/W2019708326","https://openalex.org/W2028124543","https://openalex.org/W2028499920","https://openalex.org/W2044280736","https://openalex.org/W2083056254","https://openalex.org/W2084475036","https://openalex.org/W2102182691","https://openalex.org/W2114927422","https://openalex.org/W2116210226","https://openalex.org/W2117228145","https://openalex.org/W2130289795","https://openalex.org/W2135144788","https://openalex.org/W2136952590","https://openalex.org/W2145018926","https://openalex.org/W2153492376","https://openalex.org/W2159591447","https://openalex.org/W2293286976","https://openalex.org/W3048716914","https://openalex.org/W3138798301","https://openalex.org/W3145767355","https://openalex.org/W4243796884"],"related_works":["https://openalex.org/W2151046618","https://openalex.org/W1972148443","https://openalex.org/W1969233021","https://openalex.org/W2167646277","https://openalex.org/W2063573318","https://openalex.org/W2388314963","https://openalex.org/W3158047141","https://openalex.org/W1656096860","https://openalex.org/W2027443981","https://openalex.org/W151175334"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2,64,77],"seen":[3],"a":[4,39,103,162,176],"trend":[5],"in":[6,97,173,183],"using":[7],"graphic":[8],"processing":[9],"units":[10],"(GPU)":[11],"as":[12,175],"accelerators":[13],"for":[14,119,151,157],"general-purpose":[15],"computing.":[16],"The":[17,165],"inexpensive,":[18],"single-chip,":[19],"massively":[20],"parallel":[21],"architecture":[22],"of":[23,29,38,55,105,131,170],"GPU":[24,41,58,163,184],"has":[25,87],"evidentially":[26],"brought":[27],"factors":[28],"speedup":[30],"to":[31,46,66,70,112,114,122,142,161,178],"many":[32],"numerical":[33],"applications.":[34],"However,":[35],"the":[36,47,72,85,95,110,132,144,154,168,171,180],"development":[37],"high-quality":[40],"application":[42],"is":[43,117],"challenging,":[44],"due":[45],"large":[48],"optimization":[49,86,138],"space":[50],"and":[51],"complex":[52],"unpredictable":[53],"effects":[54],"optimizations":[56],"on":[57,127],"program":[59,115],"performance.":[60],"Recently,":[61],"several":[62],"studies":[63,76],"attempted":[65],"use":[67],"empirical":[68],"search":[69],"help":[71],"optimization.":[73],"Although":[74],"those":[75],"shown":[78],"promising":[79],"results,":[80],"one":[81],"important":[82,118],"factor\u2014program":[83],"inputs\u2014in":[84],"remained":[88],"unexplored.":[89],"In":[90,129],"this":[91,98],"work,":[92],"we":[93,107,134],"initiate":[94],"exploration":[96],"new":[99],"dimension.":[100],"By":[101],"conducting":[102],"series":[104],"measurement,":[106],"find":[108],"that":[109],"ability":[111],"adapt":[113],"inputs":[116],"some":[120],"applications":[121],"achieve":[123],"their":[124],"best":[125],"performance":[126],"GPU.":[128],"light":[130],"findings,":[133],"develop":[135],"an":[136,158],"input-adaptive":[137],"framework,":[139],"namely":[140],"G-ADAPT,":[141],"address":[143],"influence":[145],"by":[146],"constructing":[147],"cross-input":[148],"predictive":[149],"models":[150],"automatically":[152],"predicting":[153],"(near-)optimal":[155],"configurations":[156],"arbitrary":[159],"input":[160],"program.":[164],"results":[166],"demonstrate":[167],"promise":[169],"framework":[172],"serving":[174],"tool":[177],"alleviate":[179],"productivity":[181],"bottleneck":[182],"programming.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":21},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":23}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}