{"id":"https://openalex.org/W2995604657","doi":"https://doi.org/10.1109/access.2019.2959905","title":"A Hierarchical Data-Partitioning Algorithm for Performance Optimization of Data-Parallel Applications on Heterogeneous Multi-Accelerator NUMA Nodes","display_name":"A Hierarchical Data-Partitioning Algorithm for Performance Optimization of Data-Parallel Applications on Heterogeneous Multi-Accelerator NUMA Nodes","publication_year":2019,"publication_date":"2019-12-17","ids":{"openalex":"https://openalex.org/W2995604657","doi":"https://doi.org/10.1109/access.2019.2959905","mag":"2995604657"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2959905","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2959905","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/08933138.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/08933138.pdf","any_repository_has_fulltext":true},"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, Dublin 4, Ireland"],"raw_orcid":"https://orcid.org/0000-0003-4070-7468","affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, 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, Dublin 4, Ireland"],"raw_orcid":"https://orcid.org/0000-0001-9181-3290","affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, 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, Dublin 4, Ireland"],"raw_orcid":"https://orcid.org/0000-0001-9460-3897","affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, 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":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.0748,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.87200599,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"8","issue":null,"first_page":"7861","last_page":"7876"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994000196456909,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9987999796867371,"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":0.8382452726364136},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7391512989997864},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3610963225364685},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33792924880981445}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8382452726364136},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7391512989997864},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3610963225364685},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33792924880981445}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2959905","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2959905","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/08933138.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ddc6cb6e90f94ed0b47acaa58c56b086","is_oa":true,"landing_page_url":"https://doaj.org/article/ddc6cb6e90f94ed0b47acaa58c56b086","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 7861-7876 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2959905","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2959905","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/08933138.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8700000047683716,"display_name":"Affordable and clean energy"}],"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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2995604657.pdf","grobid_xml":"https://content.openalex.org/works/W2995604657.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W137810137","https://openalex.org/W795794625","https://openalex.org/W1528000468","https://openalex.org/W1549662857","https://openalex.org/W1598937514","https://openalex.org/W1971404838","https://openalex.org/W1979087811","https://openalex.org/W2020177163","https://openalex.org/W2042421148","https://openalex.org/W2063554643","https://openalex.org/W2067052471","https://openalex.org/W2074207626","https://openalex.org/W2080592089","https://openalex.org/W2080804082","https://openalex.org/W2081306024","https://openalex.org/W2081422957","https://openalex.org/W2093326633","https://openalex.org/W2102624126","https://openalex.org/W2116367043","https://openalex.org/W2118064935","https://openalex.org/W2122619936","https://openalex.org/W2125980577","https://openalex.org/W2130388542","https://openalex.org/W2133684822","https://openalex.org/W2142677441","https://openalex.org/W2143498598","https://openalex.org/W2149234156","https://openalex.org/W2154750565","https://openalex.org/W2156371682","https://openalex.org/W2157598271","https://openalex.org/W2162322364","https://openalex.org/W2163674731","https://openalex.org/W2170611190","https://openalex.org/W2175477959","https://openalex.org/W2195884801","https://openalex.org/W2241264454","https://openalex.org/W2270278874","https://openalex.org/W2397644582","https://openalex.org/W2401335561","https://openalex.org/W2508492666","https://openalex.org/W2518008961","https://openalex.org/W2519627041","https://openalex.org/W2548704823","https://openalex.org/W2573700972","https://openalex.org/W2755294164","https://openalex.org/W2801415324","https://openalex.org/W2889240405","https://openalex.org/W2901070955","https://openalex.org/W3101951032","https://openalex.org/W3137957122","https://openalex.org/W4236499338","https://openalex.org/W6605620451","https://openalex.org/W6679759112","https://openalex.org/W6689915511","https://openalex.org/W6694235415","https://openalex.org/W6785324210"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Modern":[0],"HPC":[1],"platforms":[2,108],"are":[3,109],"highly":[4,270],"heterogeneous":[5,157,175,256,284],"with":[6,230],"tight":[7],"integration":[8],"of":[9,34,102,143,148,168,186,206,216,233,242,247,263,309],"multicore":[10,291],"CPUs":[11],"and":[12,36,59,80,112,269,277,298,304],"accelerators":[13],"(such":[14],"as":[15,52,64,73,84,162],"Graphics":[16],"Processing":[17],"Units,":[18],"Intel":[19,290,300],"Xeon":[20,301],"Phis,":[21],"or":[22],"Field-Programmable":[23],"Gate":[24],"Arrays)":[25],"empowering":[26],"them":[27],"to":[28,40,96,123,172],"address":[29],"the":[30,99,116,139,173,184,197,223,227,231,243,261],"twin":[31],"critical":[32],"concerns":[33],"performance":[35,100],"energy":[37],"efficiency.":[38],"Due":[39,95],"this":[41,128],"inherent":[42],"characteristic,":[43],"processing":[44],"elements":[45],"contend":[46],"for":[47,91,245],"shared":[48,60],"on-chip":[49],"resources":[50,62],"such":[51,63,72,83,310],"Last":[53],"Level":[54],"Cache":[55],"(LLC),":[56],"interconnect,":[57],"etc.":[58],"nodal":[61],"DRAM,":[65],"PCI-E":[66],"links,":[67],"etc.,":[68],"resulting":[69],"in":[70,204],"complexities":[71],"resource":[74],"contention,":[75],"non-uniform":[76],"memory":[77,87],"access":[78],"(NUMA),":[79],"accelerator-specific":[81],"limitations":[82],"limited":[85],"main":[86],"thereby":[88],"necessitating":[89],"support":[90],"efficient":[92],"out-of-card":[93],"execution.":[94],"these":[97,107,187],"complexities,":[98],"profiles":[101],"data-parallel":[103,144,273],"applications":[104,145],"executing":[105],"on":[106,146,282],"not":[110,179,200],"smooth":[111],"deviate":[113],"significantly":[114],"from":[115],"shapes":[117,185],"that":[118],"allowed":[119],"state-of-the-art":[120,224],"load-balancing":[121],"algorithms":[122],"find":[124],"optimal":[125,193],"solutions.":[126],"In":[127],"paper,":[129],"we":[130],"propose":[131,239],"a":[132,283,305],"hierarchical":[133],"two-level":[134],"data":[135],"partitioning":[136],"algorithm":[137,160,198,211,225,244,265],"minimizing":[138],"parallel":[140],"execution":[141,207],"time":[142,214],"clusters":[147,246],"h":[149,218,248],"identical":[150],"nodes":[151,250],"where":[152,251],"each":[153,252],"node":[154,253,287],"has":[155,212,254],"c":[156,164,174,255],"processors.":[158,176,257],"This":[159],"takes":[161],"input":[163],"discrete":[165],"speed":[166],"functions":[167],"cardinality":[169],"m":[170],"corresponding":[171],"It":[177],"does":[178],"make":[180],"any":[181],"assumptions":[182],"about":[183],"functions.":[188],"Unlike":[189],"load":[190],"balancing":[191],"algorithms,":[192],"solutions":[194],"found":[195],"by":[196],"may":[199],"load-balance":[201],"an":[202,240,289,294,299],"application":[203],"terms":[205],"time.":[208],"The":[209],"proposed":[210],"low":[213],"complexity":[215,232],"O(m2\u00d7":[217],"+":[219],"m3\u00d7":[220],"c3)":[221],"unlike":[222],"solving":[226],"same":[228],"problem":[229],"O(m3\u00d7":[234],"c3\u00d7":[235],"h3).":[236],"We":[237,258],"also":[238],"extension":[241],"non-identical":[249],"experimentally":[259],"demonstrate":[260],"optimality":[262],"our":[264],"using":[266],"two":[267],"well-known":[268],"optimized":[271],"multi-threaded":[272],"applications,":[274],"matrix-matrix":[275],"multiplication":[276],"2D":[278],"fast":[279],"Fourier":[280],"transform,":[281],"multi-accelerator":[285],"NUMA":[286],"containing":[288],"Haswell":[292],"CPU,":[293],"Nvidia":[295],"K40c":[296],"GPU,":[297],"Phi":[302],"co-processor":[303],"simulated":[306],"homogeneous":[307],"cluster":[308],"nodes.":[311]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}