{"id":"https://openalex.org/W4381389666","doi":"https://doi.org/10.1145/3589236.3589241","title":"GPU Auto-tuning Framework for Optimal Performance and Power Consumption","display_name":"GPU Auto-tuning Framework for Optimal Performance and Power Consumption","publication_year":2023,"publication_date":"2023-02-25","ids":{"openalex":"https://openalex.org/W4381389666","doi":"https://doi.org/10.1145/3589236.3589241"},"language":"en","primary_location":{"id":"doi:10.1145/3589236.3589241","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589236.3589241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Workshop on General Purpose Processing Using GPU","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/A5013629148","display_name":"Sunbal Cheema","orcid":"https://orcid.org/0009-0000-1437-479X"},"institutions":[{"id":"https://openalex.org/I530967","display_name":"Toronto Metropolitan University","ror":"https://ror.org/05g13zd79","country_code":"CA","type":"education","lineage":["https://openalex.org/I530967"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Sunbal Cheema","raw_affiliation_strings":["Electrical, Computer and Biomedical Engineering, Toronto Metropolitan (formerly Ryerson) University, Canada"],"raw_orcid":"https://orcid.org/0009-0000-1437-479X","affiliations":[{"raw_affiliation_string":"Electrical, Computer and Biomedical Engineering, Toronto Metropolitan (formerly Ryerson) University, Canada","institution_ids":["https://openalex.org/I530967"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030236479","display_name":"Gul N. Khan","orcid":"https://orcid.org/0000-0003-3169-5952"},"institutions":[{"id":"https://openalex.org/I530967","display_name":"Toronto Metropolitan University","ror":"https://ror.org/05g13zd79","country_code":"CA","type":"education","lineage":["https://openalex.org/I530967"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gul Khan","raw_affiliation_strings":["Electrical, Computer and Biomedical Engineering, Toronto Metropolitan (formerly Ryerson) University, Canada"],"raw_orcid":"https://orcid.org/0000-0003-3169-5952","affiliations":[{"raw_affiliation_string":"Electrical, Computer and Biomedical Engineering, Toronto Metropolitan (formerly Ryerson) University, Canada","institution_ids":["https://openalex.org/I530967"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013629148"],"corresponding_institution_ids":["https://openalex.org/I530967"],"apc_list":null,"apc_paid":null,"fwci":0.2992,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.48262725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987000226974487,"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":0.9987000226974487,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9947999715805054,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9908000230789185,"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/loop-unrolling","display_name":"Loop unrolling","score":0.872398853302002},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8483253121376038},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6703606843948364},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6355670690536499},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.6163183450698853},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5026087760925293},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4795222580432892},{"id":"https://openalex.org/keywords/tuner","display_name":"Tuner","score":0.44624537229537964},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.4407332241535187},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.4158777892589569},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4155368208885193},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30499985814094543},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.19398817420005798},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.1449303925037384}],"concepts":[{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.872398853302002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8483253121376038},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6703606843948364},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6355670690536499},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.6163183450698853},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5026087760925293},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4795222580432892},{"id":"https://openalex.org/C9819579","wikidata":"https://www.wikidata.org/wiki/Q1544018","display_name":"Tuner","level":3,"score":0.44624537229537964},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4407332241535187},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.4158777892589569},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4155368208885193},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30499985814094543},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.19398817420005798},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.1449303925037384},{"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/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589236.3589241","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589236.3589241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Workshop on General Purpose Processing Using GPU","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.9100000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1978969737","https://openalex.org/W1989562524","https://openalex.org/W2036109172","https://openalex.org/W2051277525","https://openalex.org/W2072407403","https://openalex.org/W2100218206","https://openalex.org/W2126105956","https://openalex.org/W2263518470","https://openalex.org/W2522820499","https://openalex.org/W2807679627","https://openalex.org/W2891113010","https://openalex.org/W3008278996","https://openalex.org/W4231452985","https://openalex.org/W4236496807","https://openalex.org/W4243741180"],"related_works":["https://openalex.org/W4290057712","https://openalex.org/W2168846948","https://openalex.org/W2559413996","https://openalex.org/W2559844932","https://openalex.org/W2185884583","https://openalex.org/W2549354931","https://openalex.org/W2104659803","https://openalex.org/W2066192516","https://openalex.org/W2164503864","https://openalex.org/W1836544786"],"abstract_inverted_index":{"An":[0],"auto-tuning":[1],"framework":[2,66],"for":[3,8,69,85],"GPU":[4,15,53],"devices":[5],"is":[6,67],"presented":[7],"tuning":[9,55],"application":[10,86],"kernels":[11],"of":[12,28,39,130],"OpenCL.":[13],"The":[14,50,64,109,125],"tuner":[16],"employs":[17],"multi-objective":[18],"optimization":[19],"methodology":[20,51],"to":[21],"improve":[22],"the":[23,128],"performance":[24,58],"and":[25,43,59,92,104,120,132],"power":[26,82,119],"consumption":[27,61],"applications.":[29],"It":[30,73],"efficiently":[31],"explores":[32],"a":[33,75],"user":[34],"defined":[35],"solution":[36],"space":[37],"comprising":[38],"possible":[40],"tunable":[41],"algorithmic":[42,95],"hardware":[44,81],"counter":[45],"variations":[46,96],"through":[47,89],"code":[48,54,87,90,114],"transformations.":[49],"targets":[52],"situations":[56],"where":[57],"energy":[60],"are":[62,107],"critical.":[63],"proposed":[65],"evaluated":[68],"2D":[70],"convolution":[71],"kernels.":[72],"utilizes":[74],"non-dominated":[76],"sorting":[77],"Genetic":[78],"Algorithm":[79],"with":[80],"sensor":[83],"data":[84],"transformation":[88],"rewrite":[91],"validation.":[93],"Various":[94],"such":[97],"as":[98],"loop":[99],"unrolling,":[100],"caching,":[101],"workgroup":[102],"size":[103],"memory":[105],"utilization":[106],"applied.":[108],"final":[110],"pareto":[111],"optimal":[112],"configurations":[113],"utilized":[115],"around":[116],"30%":[117],"less":[118],"4%":[121],"faster":[122],"execution":[123],"time.":[124],"analysis":[126],"shows":[127],"convergence":[129],"optimization,":[131],"45%":[133],"improvement":[134],"in":[135],"standard":[136],"deviation.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}