{"id":"https://openalex.org/W2106938618","doi":"https://doi.org/10.1145/2716282.2716292","title":"Effects of source-code optimizations on GPU performance and energy consumption","display_name":"Effects of source-code optimizations on GPU performance and energy consumption","publication_year":2015,"publication_date":"2015-02-03","ids":{"openalex":"https://openalex.org/W2106938618","doi":"https://doi.org/10.1145/2716282.2716292","mag":"2106938618"},"language":"en","primary_location":{"id":"doi:10.1145/2716282.2716292","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2716282.2716292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop on General Purpose Processing using GPUs","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/A5038030080","display_name":"Jared Coplin","orcid":null},"institutions":[{"id":"https://openalex.org/I13511017","display_name":"Texas State University","ror":"https://ror.org/05h9q1g27","country_code":"US","type":"education","lineage":["https://openalex.org/I13511017"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jared Coplin","raw_affiliation_strings":["Texas State University, USA","Texas State University, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Texas State University, USA","institution_ids":["https://openalex.org/I13511017"]},{"raw_affiliation_string":"Texas State University, USA#TAB#","institution_ids":["https://openalex.org/I13511017"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103125276","display_name":"Martin Burtscher","orcid":"https://orcid.org/0000-0001-7717-3354"},"institutions":[{"id":"https://openalex.org/I13511017","display_name":"Texas State University","ror":"https://ror.org/05h9q1g27","country_code":"US","type":"education","lineage":["https://openalex.org/I13511017"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Burtscher","raw_affiliation_strings":["Texas State University, USA","Texas State University, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Texas State University, USA","institution_ids":["https://openalex.org/I13511017"]},{"raw_affiliation_string":"Texas State University, USA#TAB#","institution_ids":["https://openalex.org/I13511017"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5038030080"],"corresponding_institution_ids":["https://openalex.org/I13511017"],"apc_list":null,"apc_paid":null,"fwci":2.6382,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.89888611,"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":"48","last_page":"58"},"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.8026312589645386},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7395070791244507},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7066370248794556},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6204075813293457},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.6184091567993164},{"id":"https://openalex.org/keywords/power-consumption","display_name":"Power consumption","score":0.5383497476577759},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5292111039161682},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.46728262305259705},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.45421114563941956},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4446064531803131},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.42116236686706543},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13057148456573486},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.07969611883163452},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06527632474899292},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.062393248081207275}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8026312589645386},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7395070791244507},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7066370248794556},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6204075813293457},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.6184091567993164},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.5383497476577759},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5292111039161682},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.46728262305259705},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.45421114563941956},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4446064531803131},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.42116236686706543},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13057148456573486},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.07969611883163452},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06527632474899292},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.062393248081207275},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2716282.2716292","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2716282.2716292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop on General Purpose Processing using GPUs","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G4794074179","display_name":null,"funder_award_id":"1141022","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320310830","display_name":"Texas State University","ror":"https://ror.org/009ey6w22"},{"id":"https://openalex.org/F4320327553","display_name":"International Max Planck Research School for Advanced Methods in Process and Systems Engineering","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1968430163","https://openalex.org/W1976052065","https://openalex.org/W1980489165","https://openalex.org/W2005375205","https://openalex.org/W2033637296","https://openalex.org/W2036186127","https://openalex.org/W2043083835","https://openalex.org/W2054224993","https://openalex.org/W2068306188","https://openalex.org/W2091913208","https://openalex.org/W2100619764","https://openalex.org/W2101595571","https://openalex.org/W2125588078","https://openalex.org/W2135120170","https://openalex.org/W2141101244","https://openalex.org/W2150198609","https://openalex.org/W2155373773","https://openalex.org/W2614178556","https://openalex.org/W4240739471"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W2062253548","https://openalex.org/W4225414539","https://openalex.org/W2094832839","https://openalex.org/W4289522463","https://openalex.org/W1977763331","https://openalex.org/W2076165488","https://openalex.org/W4385574943"],"abstract_inverted_index":{"This":[0,78],"paper":[1,79],"studies":[2],"the":[3,9,52,56,102,107,121],"effects":[4],"of":[5,16,25,59,105,117,126,135],"source-code":[6],"optimizations":[7,42,82,99,118],"on":[8,63],"performance,":[10,91],"power":[11,57,108],"draw,":[12],"and":[13,33,55,73,75,92,115,123],"energy":[14,85,124],"consumption":[15,58,125],"a":[17,29,34,127,133],"modern":[18],"compute":[19],"GPU.":[20],"We":[21,50],"evaluate":[22],"128":[23],"versions":[24],"two":[26,70],"n-body":[27],"codes:":[28],"compute-bound":[30],"regular":[31],"implementation":[32],"memory-bound":[35],"irregular":[36],"implementation.":[37],"Both":[38],"programs":[39],"include":[40],"six":[41],"that":[43,113],"can":[44,119],"be":[45],"individually":[46],"enabled":[47],"or":[48],"disabled.":[49],"measured":[51],"active":[53],"runtime":[54],"each":[60],"code":[61],"version":[62],"three":[64],"inputs,":[65],"various":[66],"GPU":[67,128],"clock":[68],"frequencies,":[69],"arithmetic":[71],"precisions,":[72],"with":[74],"without":[76],"ECC.":[77],"investigates":[80],"which":[81,87,93],"primarily":[83],"improve":[84],"efficiency,":[86],"ones":[88,94],"mainly":[89],"boost":[90],"help":[95],"both":[96],"aspects.":[97],"Some":[98],"also":[100],"have":[101],"added":[103],"benefit":[104],"reducing":[106],"draw.":[109],"Our":[110],"analysis":[111],"shows":[112],"individual":[114],"combinations":[116],"alter":[120],"performance":[122],"kernel":[129],"by":[130],"up":[131],"to":[132],"factor":[134],"five.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}