{"id":"https://openalex.org/W2519627041","doi":"https://doi.org/10.1109/tpds.2016.2608824","title":"New Model-Based Methods and Algorithms for Performance and Energy Optimization of Data Parallel Applications on Homogeneous Multicore Clusters","display_name":"New Model-Based Methods and Algorithms for Performance and Energy Optimization of Data Parallel Applications on Homogeneous Multicore Clusters","publication_year":2016,"publication_date":"2016-09-13","ids":{"openalex":"https://openalex.org/W2519627041","doi":"https://doi.org/10.1109/tpds.2016.2608824","mag":"2519627041"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2016.2608824","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2608824","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/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":null,"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/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":null,"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":9.5149,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.97927912,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"28","issue":"4","first_page":"1119","last_page":"1133"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.996399998664856,"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":0.8278727531433105},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.7693430185317993},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.763479471206665},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.702681303024292},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6209900379180908},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5560332536697388},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.4273848235607147},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.41570496559143066},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4118134081363678},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3594423532485962}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8278727531433105},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.7693430185317993},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.763479471206665},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.702681303024292},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6209900379180908},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5560332536697388},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.4273848235607147},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.41570496559143066},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4118134081363678},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3594423532485962},{"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2016.2608824","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2608824","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":[],"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":41,"referenced_works":["https://openalex.org/W55109682","https://openalex.org/W1468576370","https://openalex.org/W1528000468","https://openalex.org/W1794165208","https://openalex.org/W2003094427","https://openalex.org/W2020177163","https://openalex.org/W2030129803","https://openalex.org/W2067052471","https://openalex.org/W2081422957","https://openalex.org/W2093326633","https://openalex.org/W2102624126","https://openalex.org/W2109426995","https://openalex.org/W2110165211","https://openalex.org/W2116367043","https://openalex.org/W2122619936","https://openalex.org/W2123031400","https://openalex.org/W2125980577","https://openalex.org/W2137789117","https://openalex.org/W2142421493","https://openalex.org/W2154790372","https://openalex.org/W2163674731","https://openalex.org/W2166417226","https://openalex.org/W2171473263","https://openalex.org/W2195884801","https://openalex.org/W2241264454","https://openalex.org/W2278129015","https://openalex.org/W2291749214","https://openalex.org/W2397644582","https://openalex.org/W2401335561","https://openalex.org/W2508492666","https://openalex.org/W2519627041","https://openalex.org/W2573700972","https://openalex.org/W2727655179","https://openalex.org/W4244789640","https://openalex.org/W4251173935","https://openalex.org/W4295162670","https://openalex.org/W6602209748","https://openalex.org/W6628746399","https://openalex.org/W6684857869","https://openalex.org/W6689915511","https://openalex.org/W6696726799"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W3214280620","https://openalex.org/W2329539859","https://openalex.org/W3191490922","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W1582436825","https://openalex.org/W1996803181","https://openalex.org/W2119413962","https://openalex.org/W2997952415"],"abstract_inverted_index":{"Modern":[0],"homogeneous":[1,119],"parallel":[2,113,179],"platforms":[3,59],"are":[4,60],"composed":[5],"of":[6,53,95,99,106,111,134,145,173,194,202],"tightly":[7],"integrated":[8],"multicore":[9,120,190],"CPUs.":[10,196],"This":[11],"tight":[12],"integration":[13],"has":[14],"resulted":[15],"in":[16],"the":[17,48,68,102,117,124,143,153,164,169,200],"cores":[18],"contending":[19],"for":[20,93,101,176],"various":[21],"shared":[22],"on-chip":[23],"resources":[24],"such":[25,195],"as":[26],"Last":[27],"Level":[28],"Cache":[29],"(LLC)":[30],"and":[31,37,50,63,73,91,97,108,126,130,171,183,192],"interconnect,":[32],"leading":[33],"to":[34,43,78,150],"resource":[35],"contention":[36],"non-uniform":[38],"memory":[39],"access":[40],"(NUMA).":[41],"Due":[42],"these":[44,58,138,159],"newly":[45],"introduced":[46],"complexities,":[47],"performance":[49,107,125],"energy":[51,98,109,127],"profiles":[52,110],"real-life":[54],"scientific":[55],"applications":[56,114],"on":[57,116,187],"not":[61,162],"smooth":[62],"may":[64,161],"deviate":[65],"significantly":[66],"from":[67],"shapes":[69,105],"that":[70,152],"allowed":[71],"traditional":[72],"state-of-the-art":[74],"load":[75],"balancing":[76],"algorithms":[77,92,133,160,175],"minimize":[79],"their":[80],"computation":[81],"time.":[82],"In":[83],"this":[84],"paper,":[85],"we":[86],"propose":[87],"new":[88],"model-based":[89],"methods":[90],"minimization":[94],"time":[96],"computations":[100],"most":[103],"general":[104],"data":[112,178],"observed":[115],"modern":[118,189],"clusters.":[121],"We":[122,166,197],"formulate":[123],"optimization":[128],"problems":[129,139],"present":[131],"efficient":[132],"complexity":[135],"O(p2)":[136],"solving":[137],"where":[140],"p":[141],"is":[142,148],"number":[144],"processors.":[146],"It":[147],"important":[149],"note":[151],"globally":[154],"optimal":[155],"solutions":[156,203],"found":[157],"by":[158,205],"load-balance":[163],"application.":[165],"experimentally":[167],"study":[168],"efficiency":[170],"scalability":[172],"our":[174,206],"two":[177],"applications,":[180],"matrix":[181],"multiplication":[182],"fast":[184],"Fourier":[185],"transform,":[186],"a":[188],"CPU":[191],"clusters":[193],"also":[198],"demonstrate":[199],"optimality":[201],"determined":[204],"algorithms.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}