{"id":"https://openalex.org/W2019295203","doi":"https://doi.org/10.1109/ipdpsw.2013.220","title":"Analyzing Optimization Techniques for Power Efficiency on Heterogeneous Platforms","display_name":"Analyzing Optimization Techniques for Power Efficiency on Heterogeneous Platforms","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2019295203","doi":"https://doi.org/10.1109/ipdpsw.2013.220","mag":"2019295203"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw.2013.220","doi":"https://doi.org/10.1109/ipdpsw.2013.220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2013.220","pdf_url":null,"source":{"id":"https://openalex.org/S4393918253","display_name":"IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum","issn_l":"2164-7062","issn":["2164-7062"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum","raw_type":"proceedings-article"},"volume":null,"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/A5019687323","display_name":"Yash Ukidave","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yash Ukidave","raw_affiliation_strings":["Department of Electrical & Computer Engineering, Northeastern University, Boston, USA","Dept. of Electr. & Comput. Eng., Northeastern Univ., Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Northeastern Univ., Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061128237","display_name":"David R Kaeli","orcid":"https://orcid.org/0000-0002-5692-0151","observed_orcids":["https://orcid.org/0000-0002-5692-0151"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David R. Kaeli","raw_affiliation_strings":["Department of Electrical & Computer Engineering, Northeastern University, Boston, USA","Dept. of Electr. & Comput. Eng., Northeastern Univ., Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Northeastern Univ., Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":1.4265,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.80913851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"37","issue":null,"first_page":"1040","last_page":"1049"},"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":0.0,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/power-efficiency","display_name":"power efficiency","score":0.9459999799728394},{"id":"https://openalex.org/keywords/heterogeneous-computing","display_name":"heterogeneous computing","score":0.6679999828338623},{"id":"https://openalex.org/keywords/gpu-power-consumption","display_name":"GPU power consumption","score":0.7720000147819519},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"loop unrolling","score":0.7590000033378601},{"id":"https://openalex.org/keywords/loop-tiling","display_name":"loop tiling","score":0.9010000228881836},{"id":"https://openalex.org/keywords/source-code-optimization","display_name":"source code optimization","score":0.6729999780654907},{"id":"https://openalex.org/keywords/power-performance-trade-off","display_name":"power-performance tradeoff","score":0.8690000176429749},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"fast Fourier transform","score":0.8510000109672546},{"id":"https://openalex.org/keywords/opencl","display_name":"OpenCL","score":0.7670000195503235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.832312822341919},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.7254270315170288},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.61180579662323},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.6040764451026917},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5315316319465637},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.531130313873291},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5068755745887756},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4885443150997162},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.47702547907829285},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.44507232308387756},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.43697983026504517},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.42482417821884155},{"id":"https://openalex.org/C118993495","wikidata":"https://www.wikidata.org/wiki/Q5042828","display_name":"Electrical efficiency","level":3,"score":0.4219353497028351},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3364947736263275},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.32227182388305664},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.165042906999588},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.08849623799324036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdpsw.2013.220","doi":"https://doi.org/10.1109/ipdpsw.2013.220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2013.220","pdf_url":null,"source":{"id":"https://openalex.org/S4393918253","display_name":"IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum","issn_l":"2164-7062","issn":["2164-7062"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum","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":0.75}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1597508330","https://openalex.org/W1717365219","https://openalex.org/W1903794615","https://openalex.org/W1976534780","https://openalex.org/W1978969737","https://openalex.org/W1979527452","https://openalex.org/W1992851788","https://openalex.org/W2000335122","https://openalex.org/W2002555321","https://openalex.org/W2024874287","https://openalex.org/W2047532956","https://openalex.org/W2066804546","https://openalex.org/W2102182691","https://openalex.org/W2103742924","https://openalex.org/W2108600626","https://openalex.org/W2114927422","https://openalex.org/W2123119012","https://openalex.org/W2123591640","https://openalex.org/W2129136709","https://openalex.org/W2144293278","https://openalex.org/W2146742876","https://openalex.org/W2147193503","https://openalex.org/W2149234156","https://openalex.org/W2149921618","https://openalex.org/W2160245390","https://openalex.org/W2160786443","https://openalex.org/W2161775046","https://openalex.org/W2167334577","https://openalex.org/W2213609752","https://openalex.org/W2620440553","https://openalex.org/W2997701623","https://openalex.org/W3145767355","https://openalex.org/W3147878143","https://openalex.org/W4250981202","https://openalex.org/W6738640236"],"related_works":["https://openalex.org/W2095909712","https://openalex.org/W7221376127","https://openalex.org/W2047532956","https://openalex.org/W2775240597","https://openalex.org/W191331148","https://openalex.org/W2358093243","https://openalex.org/W3010409494","https://openalex.org/W2106938618","https://openalex.org/W1985364901","https://openalex.org/W7221412785"],"abstract_inverted_index":{"Graphics":[0],"processing":[1],"units":[2],"(GPUs)":[3],"have":[4,52],"become":[5],"widely":[6],"accepted":[7],"as":[8,26,42,155],"the":[9,32,60,79,90,102,110,114,145,161,214,227],"computing":[10,18],"platform":[11],"of":[12,22,63,93,109,116,175,217,226],"choice":[13],"in":[14,56,182,189,194,201],"many":[15],"high":[16],"performance":[17,115,216],"domains.":[19],"The":[20,158],"availability":[21],"programming":[23],"standards":[24],"such":[25,41],"OpenCL":[27],"are":[28,74],"used":[29,96],"to":[30,49,76],"leverage":[31],"inherent":[33],"parallelism":[34],"offered":[35],"by":[36,105,185],"GPUs.":[37],"Source":[38],"code":[39],"optimizations":[40,95,177,211],"loop":[43],"unrolling":[44],"and":[45,132,137,144,151,163],"tiling":[46],"when":[47],"targeted":[48],"heterogeneous":[50,83,98,219],"applications":[51],"reported":[53],"large":[54],"gains":[55],"performance.":[57,195],"However,":[58],"given":[59],"power":[61,69,170,183,224],"consumption":[62,108,184,203],"GPUs,":[64],"platforms":[65],"can":[66,167,212],"exhaust":[67],"their":[68],"budgets":[70],"quickly.":[71],"Better":[72],"solutions":[73],"needed":[75],"effectively":[77],"exploit":[78],"power-efficiency":[80],"available":[81],"on":[82,97,120],"systems.":[84],"In":[85],"this":[86],"work,":[87],"we":[88],"evaluate":[89],"power/performance":[91,103],"efficiency":[92,225],"different":[94,117,122,205,210],"applications.":[99],"We":[100,112,172,196,207],"analyze":[101],"trade-off":[104],"evaluating":[106],"energy":[107,202],"optimizations.":[111,206],"compare":[113],"optimization":[118],"techniques":[119],"4":[121],"Fast":[123],"Fourier":[124],"Transform":[125],"implementations.":[126],"Our":[127],"study":[128,159],"covers":[129],"discrete":[130],"GPUs":[131,135],"shared":[133],"memory":[134],"(APUs),":[136],"includes":[138],"hardware":[139],"from":[140],"AMD":[141],"(Llano":[142],"APUs":[143],"Southern":[146],"Islands":[147],"GPU),":[148],"Nvidia":[149],"(Kepler)":[150],"Intel":[152],"(Ivy":[153],"Bridge)":[154],"test":[156],"platforms.":[157],"identifies":[160],"architectural":[162],"algorithmic":[164],"factors":[165],"which":[166,178],"most":[168],"impact":[169,223],"consumption.":[171],"explore":[173],"arange":[174],"application":[176],"show":[179],"an":[180],"increase":[181],"27%,":[186],"but":[187,221],"result":[188],"more":[190],"than":[191],"a":[192,198,218],"1.8Xspeedup":[193],"observe":[197],"11%":[199],"variation":[200],"among":[204],"highlight":[208],"how":[209],"improve":[213],"execution":[215],"application,":[220],"also":[222],"application.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}