{"id":"https://openalex.org/W3090575287","doi":"https://doi.org/10.1109/tpds.2020.3027338","title":"Bi-Objective Optimization of Data-Parallel Applications on Heterogeneous HPC Platforms for Performance and Energy Through Workload Distribution","display_name":"Bi-Objective Optimization of Data-Parallel Applications on Heterogeneous HPC Platforms for Performance and Energy Through Workload Distribution","publication_year":2020,"publication_date":"2020-09-29","ids":{"openalex":"https://openalex.org/W3090575287","doi":"https://doi.org/10.1109/tpds.2020.3027338","mag":"3090575287"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2020.3027338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2020.3027338","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5006106085","display_name":"Hamidreza Khaleghzadeh","orcid":"https://orcid.org/0000-0003-4070-7468"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Hamidreza Khaleghzadeh","raw_affiliation_strings":["School of Computer Science, University College Dublin, Belfield, Dublin 4, Ireland"],"raw_orcid":"https://orcid.org/0000-0003-4070-7468","affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Belfield, Dublin 4, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004717582","display_name":"Muhammad Fahad","orcid":"https://orcid.org/0000-0002-3595-8484"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Muhammad Fahad","raw_affiliation_strings":["School of Computer Science, University College Dublin, Belfield, Dublin 4, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-3595-8484","affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Belfield, Dublin 4, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013795937","display_name":"Arsalan Shahid","orcid":"https://orcid.org/0000-0002-3748-6361"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Arsalan Shahid","raw_affiliation_strings":["School of Computer Science, University College Dublin, Belfield, Dublin 4, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-3748-6361","affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Belfield, Dublin 4, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078230040","display_name":"Ravi Reddy Manumachu","orcid":"https://orcid.org/0000-0001-9181-3290"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Ravi Reddy Manumachu","raw_affiliation_strings":["School of Computer Science, University College Dublin, Belfield, Dublin 4, Ireland"],"raw_orcid":"https://orcid.org/0000-0001-9181-3290","affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Belfield, Dublin 4, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084068586","display_name":"Alexey Lastovetsky","orcid":"https://orcid.org/0000-0001-9460-3897"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Alexey Lastovetsky","raw_affiliation_strings":["School of Computer Science, University College Dublin, Belfield, Dublin 4, Ireland"],"raw_orcid":"https://orcid.org/0000-0001-9460-3897","affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Belfield, Dublin 4, Ireland","institution_ids":["https://openalex.org/I100930933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I100930933"],"apc_list":null,"apc_paid":null,"fwci":5.4587,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.96648457,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"32","issue":"3","first_page":"543","last_page":"560"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.7836025357246399},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5386417508125305},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.47263404726982117},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4584891200065613},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.45635986328125},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.45560070872306824},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.45144104957580566},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4420916736125946},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4400709271430969},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.4359474778175354},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4164380729198456},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4125126004219055},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.39242982864379883},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.34371423721313477},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30169567465782166},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09027773141860962}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7836025357246399},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5386417508125305},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.47263404726982117},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4584891200065613},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.45635986328125},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.45560070872306824},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.45144104957580566},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4420916736125946},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4400709271430969},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.4359474778175354},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4164380729198456},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4125126004219055},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.39242982864379883},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.34371423721313477},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30169567465782166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09027773141860962},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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:10.1109/tpds.2020.3027338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2020.3027338","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1766076957","display_name":"Meeting the Future Challenges of Heterogeneous and Extreme-Scale Parallel Computing","funder_award_id":"14/IA/2474","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W84160644","https://openalex.org/W174695359","https://openalex.org/W624975885","https://openalex.org/W795794625","https://openalex.org/W1468576370","https://openalex.org/W1809169466","https://openalex.org/W1842406863","https://openalex.org/W1971216521","https://openalex.org/W1972270941","https://openalex.org/W1974573565","https://openalex.org/W1978969737","https://openalex.org/W1993734353","https://openalex.org/W1994052277","https://openalex.org/W2015915218","https://openalex.org/W2018198861","https://openalex.org/W2019176653","https://openalex.org/W2021752456","https://openalex.org/W2028469001","https://openalex.org/W2033597569","https://openalex.org/W2035276889","https://openalex.org/W2045350099","https://openalex.org/W2065461987","https://openalex.org/W2067052471","https://openalex.org/W2068448872","https://openalex.org/W2070525241","https://openalex.org/W2087064593","https://openalex.org/W2093326633","https://openalex.org/W2093752441","https://openalex.org/W2101366119","https://openalex.org/W2118046912","https://openalex.org/W2125980577","https://openalex.org/W2129686813","https://openalex.org/W2129832837","https://openalex.org/W2130388542","https://openalex.org/W2136009677","https://openalex.org/W2139469116","https://openalex.org/W2148459868","https://openalex.org/W2149813938","https://openalex.org/W2153169188","https://openalex.org/W2156371682","https://openalex.org/W2163674731","https://openalex.org/W2168843308","https://openalex.org/W2170059648","https://openalex.org/W2342906597","https://openalex.org/W2508492666","https://openalex.org/W2518008961","https://openalex.org/W2519627041","https://openalex.org/W2544171875","https://openalex.org/W2552249601","https://openalex.org/W2625627861","https://openalex.org/W2727655179","https://openalex.org/W2748740248","https://openalex.org/W2751498991","https://openalex.org/W2755294164","https://openalex.org/W2780884712","https://openalex.org/W2801415324","https://openalex.org/W2905912478","https://openalex.org/W2948541941","https://openalex.org/W2995604657","https://openalex.org/W3006997840","https://openalex.org/W3025634767","https://openalex.org/W3105244973","https://openalex.org/W4230084366","https://openalex.org/W4233376872","https://openalex.org/W4244593655","https://openalex.org/W6603396934","https://openalex.org/W6628746399","https://openalex.org/W6638953996","https://openalex.org/W6748112299","https://openalex.org/W6757396186"],"related_works":["https://openalex.org/W2388464034","https://openalex.org/W2533125852","https://openalex.org/W2140460949","https://openalex.org/W4327521644","https://openalex.org/W2105580438","https://openalex.org/W2978884468","https://openalex.org/W2168413811","https://openalex.org/W2005846134","https://openalex.org/W3159511836","https://openalex.org/W2119413962"],"abstract_inverted_index":{"Performance":[0],"and":[1,57,65,73,82,128,139,151,158,165,233,246,265],"energy":[2,28,58,66,140,179,190],"are":[3,80,272],"the":[4,42,51,104,114,167,176,181,189,218,260,267],"two":[5,69,237],"most":[6],"important":[7],"objectives":[8],"for":[9,25,50,94,102],"optimization":[10,24,32,100,116,131],"on":[11,33,118,198,236],"modern":[12,162],"parallel":[13,163],"platforms.":[14],"In":[15],"this":[16],"article,":[17],"we":[18],"show":[19,251],"that":[20,75,79,133,186,252,271],"moving":[21],"from":[22],"single-objective":[23],"performance":[26,56,64,138],"or":[27,99],"to":[29,85,96],"their":[30],"bi-objective":[31,115],"heterogeneous":[34,119,200,239],"processors":[35],"results":[36],"in":[37,41,161],"a":[38,110,184,193,199,255],"tremendous":[39],"increase":[40],"number":[43],"of":[44,54,68,89,146,242],"optimal":[45],"solutions":[46,169,264,270],"(workload":[47],"distributions)":[48],"even":[49],"simple":[52],"case":[53],"linear":[55],"profiles.":[59],"We":[60,215,250],"then":[61],"study":[62],"full":[63],"profiles":[67,141],"real-life":[70],"data-parallel":[71,195,224],"applications":[72],"find":[74],"they":[76],"exhibit":[77],"shapes":[78],"non-linear":[81],"complex":[83],"enough":[84],"prevent":[86],"good":[87],"approximation":[88],"them":[90],"as":[91,135,142],"analytical":[92],"functions":[93,145],"input":[95,137,177],"exact":[97,129],"algorithms":[98],"software":[101],"determining":[103],"Pareto":[105,257],"front.":[106],"We,":[107],"therefore,":[108],"propose":[109],"solution":[111,220],"method":[112,182,221],"solving":[113],"problem":[117],"processors.":[120],"The":[121],"method's":[122],"novel":[123],"component":[124],"is":[125],"an":[126,136],"efficient":[127],"global":[130],"algorithm":[132],"takes":[134],"arbitrary":[143],"discrete":[144,178],"workload":[147],"size,":[148],"which":[149],"accurately":[150,187],"realistically":[152],"take":[153],"into":[154],"account":[155],"resource":[156],"contention":[157],"NUMA":[159],"inherent":[160],"platforms,":[164],"returns":[166],"Pareto-optimal":[168],"(generally":[170],"speaking,":[171],"load":[172,262,268,275],"imbalanced).":[173],"To":[174],"construct":[175],"functions,":[180],"employs":[183],"methodology":[185],"models":[188],"consumption":[191],"by":[192,212,274],"hybrid":[194],"application":[196],"executing":[197],"HPC":[201],"platform":[202],"containing":[203,259],"different":[204],"computing":[205],"devices":[206],"using":[207,222],"system-level":[208],"power":[209,213],"measurements":[210],"provided":[211],"meters.":[214],"experimentally":[216],"analyse":[217],"proposed":[219],"three":[223],"applications,":[225],"matrix":[226],"multiplication,":[227],"2D":[228],"fast":[229],"Fourier":[230],"transform":[231],"(2D-FFT),":[232],"gene":[234],"sequencing,":[235],"connected":[238],"servers":[240],"consisting":[241],"multicore":[243],"CPUs,":[244],"GPUs,":[245],"Intel":[247],"Xeon":[248],"Phi.":[249],"it":[253],"determines":[254],"superior":[256],"front":[258],"best":[261],"balanced":[263],"all":[266],"imbalanced":[269],"ignored":[273],"balancing":[276],"methods.":[277]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
