{"id":"https://openalex.org/W3128857286","doi":"https://doi.org/10.1109/access.2021.3052976","title":"Towards Optimal Matrix Partitioning for Data Parallel Computing on a Hybrid Heterogeneous Server","display_name":"Towards Optimal Matrix Partitioning for Data Parallel Computing on a Hybrid Heterogeneous Server","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3128857286","doi":"https://doi.org/10.1109/access.2021.3052976","mag":"3128857286"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3052976","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3052976","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09328411.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/ielx7/6287639/9312710/09328411.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046977661","display_name":"Tania Malik","orcid":"https://orcid.org/0000-0002-4461-7120"},"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":"Tania Malik","raw_affiliation_strings":["School of Computer Science, University College Dublin, Dublin 4, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-4461-7120","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":1.1348,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.7481887,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"9","issue":null,"first_page":"17229","last_page":"17244"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9994999766349792,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9986000061035156,"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":0.8578805923461914},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5856812000274658},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5400673747062683},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5361874103546143},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5225976705551147},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.43057379126548767},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.42531710863113403},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.4158439636230469}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8578805923461914},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5856812000274658},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5400673747062683},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5361874103546143},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5225976705551147},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43057379126548767},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.42531710863113403},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.4158439636230469},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3052976","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3052976","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09328411.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:dbb08281d65a4f3bacb674e4f7900f5c","is_oa":true,"landing_page_url":"https://doaj.org/article/dbb08281d65a4f3bacb674e4f7900f5c","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 9, Pp 17229-17244 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3052976","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3052976","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09328411.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":0.9100000262260437,"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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3128857286.pdf","grobid_xml":"https://content.openalex.org/works/W3128857286.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1528000468","https://openalex.org/W1979087811","https://openalex.org/W2022146928","https://openalex.org/W2056999868","https://openalex.org/W2062065632","https://openalex.org/W2067052471","https://openalex.org/W2093326633","https://openalex.org/W2104779926","https://openalex.org/W2116367043","https://openalex.org/W2121463040","https://openalex.org/W2122619936","https://openalex.org/W2124462592","https://openalex.org/W2125980577","https://openalex.org/W2128624833","https://openalex.org/W2144854112","https://openalex.org/W2144997873","https://openalex.org/W2149932344","https://openalex.org/W2153637889","https://openalex.org/W2156371682","https://openalex.org/W2160556361","https://openalex.org/W2163674731","https://openalex.org/W2198580158","https://openalex.org/W2478462544","https://openalex.org/W2508492666","https://openalex.org/W2519627041","https://openalex.org/W2787450728","https://openalex.org/W2801415324","https://openalex.org/W2908578142","https://openalex.org/W2948541941","https://openalex.org/W3025634767","https://openalex.org/W3030561006","https://openalex.org/W3044220387","https://openalex.org/W3046897426","https://openalex.org/W3088616233","https://openalex.org/W6631784903","https://openalex.org/W6645027423","https://openalex.org/W6678744596","https://openalex.org/W6679329782","https://openalex.org/W6763335996","https://openalex.org/W6778475234"],"related_works":["https://openalex.org/W2092530219","https://openalex.org/W2388464034","https://openalex.org/W2533125852","https://openalex.org/W2140460949","https://openalex.org/W2105580438","https://openalex.org/W2057435755","https://openalex.org/W4214747436","https://openalex.org/W2953002963","https://openalex.org/W2009365093","https://openalex.org/W2946050103"],"abstract_inverted_index":{"Optimal":[0],"partitioning":[1,109],"of":[2,14,53,83,92,107,129,144,148,153,164,177,193],"a":[3,43,104,110,118,184],"square":[4,112],"computational":[5],"domain":[6],"over":[7,113],"several":[8],"heterogeneous":[9,115],"processors,":[10,50,87],"balancing":[11],"the":[12,15,19,51,80,90,126,145,154,158,162,174,189,207,211],"load":[13],"processors":[16,57,67,116,197],"and":[17,31,55,102,198,206],"minimizing":[18],"inter-processor":[20],"communication":[21,36,71,146,185],"cost,":[22],"is":[23,214],"crucial":[24],"for":[25,48,65,79,125,140],"data":[26,84,130,149,165,194],"parallel":[27,166],"dense":[28],"linear":[29],"algebra":[30],"other":[32],"applications":[33],"having":[34],"similar":[35],"pattern":[37],"on":[38],"modern":[39],"hybrid":[40,159],"servers.":[41],"Although":[42],"solution":[44,64],"has":[45],"been":[46],"found":[47],"two":[49],"cases":[52],"three":[54,66,114],"more":[56],"are":[58],"still":[59],"open.":[60],"The":[61],"state":[62],"of-the-art":[63],"uses":[68],"an":[69,137],"approximation":[70],"cost":[72,120],"function":[73],"which":[74,122],"fails":[75],"to":[76],"accurately":[77,123],"account":[78],"total":[81,127],"amount":[82,128],"moved":[85],"between":[86,132,151,196],"leaving":[88],"thus":[89],"question":[91],"its":[93,201],"global":[94],"optimality":[95],"unanswered.":[96],"In":[97],"this":[98,171],"work,":[99],"we":[100,182],"formulate":[101],"solve":[103],"mathematical":[105,179],"problem":[106],"optimal":[108],"real-valued":[111],"using":[117],"new":[119],"function,":[121],"accounts":[124],"communicated":[131],"processors.":[133],"We":[134,168],"also":[135],"develop":[136],"original":[138],"method":[139,172],"accurate":[141],"experimental":[142,175],"evaluation":[143],"time":[147],"movement":[150,195],"memories":[152],"compute":[155],"devices":[156],"in":[157,173],"platform":[160],"during":[161],"execution":[163],"applications.":[167],"successfully":[169],"use":[170],"validation":[176],"our":[178],"results.":[180],"Finally,":[181],"propose":[183],"energy":[186,191,217],"model":[187,204],"predicting":[188],"dynamic":[190],"consumption":[192],"experimentally":[199],"validate":[200],"accuracy.":[202],"This":[203],"predicts,":[205],"experiments":[208],"confirm,":[209],"that":[210],"performance-optimal":[212],"partition":[213],"not":[215],"necessarily":[216],"optimal.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
