{"id":"https://openalex.org/W2796567256","doi":"https://doi.org/10.1109/access.2018.2823299","title":"Performance and Power Efficient Massive Parallel Computational Model for HPC Heterogeneous Exascale Systems","display_name":"Performance and Power Efficient Massive Parallel Computational Model for HPC Heterogeneous Exascale Systems","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2796567256","doi":"https://doi.org/10.1109/access.2018.2823299","mag":"2796567256"},"language":"en","primary_location":{"id":"doi:10.1109/access.2018.2823299","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2823299","pdf_url":null,"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":null,"license_id":null,"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://doi.org/10.1109/access.2018.2823299","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081272298","display_name":"Muhammad Usman Ashraf","orcid":"https://orcid.org/0000-0001-7341-8625"},"institutions":[{"id":"https://openalex.org/I185163786","display_name":"King Abdulaziz University","ror":"https://ror.org/02ma4wv74","country_code":"SA","type":"education","lineage":["https://openalex.org/I185163786"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"M. Usman Ashraf","raw_affiliation_strings":["Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0001-7341-8625","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I185163786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034572330","display_name":"Fathy Alburaei Eassa","orcid":null},"institutions":[{"id":"https://openalex.org/I185163786","display_name":"King Abdulaziz University","ror":"https://ror.org/02ma4wv74","country_code":"SA","type":"education","lineage":["https://openalex.org/I185163786"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Fathy Alburaei Eassa","raw_affiliation_strings":["Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I185163786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045587553","display_name":"Aiiad Albeshri","orcid":"https://orcid.org/0000-0003-3796-0294"},"institutions":[{"id":"https://openalex.org/I185163786","display_name":"King Abdulaziz University","ror":"https://ror.org/02ma4wv74","country_code":"SA","type":"education","lineage":["https://openalex.org/I185163786"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Aiiad Ahmad Albeshri","raw_affiliation_strings":["Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I185163786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001718282","display_name":"Abdullah Algarni","orcid":"https://orcid.org/0000-0002-7154-9821"},"institutions":[{"id":"https://openalex.org/I185163786","display_name":"King Abdulaziz University","ror":"https://ror.org/02ma4wv74","country_code":"SA","type":"education","lineage":["https://openalex.org/I185163786"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Abdullah Algarni","raw_affiliation_strings":["Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I185163786"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I185163786"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":5.534,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.96924567,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"6","issue":null,"first_page":"23095","last_page":"23107"},"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":0.9976999759674072,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9975000023841858,"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":0.8728818893432617},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7786672115325928},{"id":"https://openalex.org/keywords/petascale-computing","display_name":"Petascale computing","score":0.7378647327423096},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.7195578217506409},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6615036129951477},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5935450792312622},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.5833120942115784},{"id":"https://openalex.org/keywords/subroutine","display_name":"Subroutine","score":0.5705872178077698},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.5413737893104553},{"id":"https://openalex.org/keywords/exascale-computing","display_name":"Exascale computing","score":0.5300597548484802},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.526063859462738},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.5045987367630005},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4727552533149719},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.47269678115844727},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.46787306666374207},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4452725350856781},{"id":"https://openalex.org/keywords/parallel-programming-model","display_name":"Parallel programming model","score":0.41853004693984985},{"id":"https://openalex.org/keywords/numerical-linear-algebra","display_name":"Numerical linear algebra","score":0.41365963220596313},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.205519437789917},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18733134865760803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8728818893432617},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7786672115325928},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.7378647327423096},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.7195578217506409},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6615036129951477},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5935450792312622},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.5833120942115784},{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.5705872178077698},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.5413737893104553},{"id":"https://openalex.org/C2778837361","wikidata":"https://www.wikidata.org/wiki/Q2450880","display_name":"Exascale computing","level":3,"score":0.5300597548484802},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.526063859462738},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.5045987367630005},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4727552533149719},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.47269678115844727},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.46787306666374207},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4452725350856781},{"id":"https://openalex.org/C137364921","wikidata":"https://www.wikidata.org/wiki/Q27929394","display_name":"Parallel programming model","level":3,"score":0.41853004693984985},{"id":"https://openalex.org/C163834973","wikidata":"https://www.wikidata.org/wiki/Q2004891","display_name":"Numerical linear algebra","level":3,"score":0.41365963220596313},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.205519437789917},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18733134865760803},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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.2018.2823299","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2823299","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e2a98e1100fb4b8bb949505cd73f17c4","is_oa":true,"landing_page_url":"https://doaj.org/article/e2a98e1100fb4b8bb949505cd73f17c4","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 6, Pp 23095-23107 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2018.2823299","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2823299","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8799999952316284}],"awards":[{"id":"https://openalex.org/G76605738","display_name":null,"funder_award_id":"RG-3-611-38","funder_id":"https://openalex.org/F4320322322","funder_display_name":"King Abdulaziz University"}],"funders":[{"id":"https://openalex.org/F4320322322","display_name":"King Abdulaziz University","ror":"https://ror.org/02ma4wv74"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1501066815","https://openalex.org/W1812262877","https://openalex.org/W1837653564","https://openalex.org/W1839773802","https://openalex.org/W1859126261","https://openalex.org/W1947563839","https://openalex.org/W1967394905","https://openalex.org/W1974519274","https://openalex.org/W1981326836","https://openalex.org/W1984222112","https://openalex.org/W1989696490","https://openalex.org/W1993717328","https://openalex.org/W2009514331","https://openalex.org/W2017587301","https://openalex.org/W2018408367","https://openalex.org/W2024639384","https://openalex.org/W2025549820","https://openalex.org/W2036641664","https://openalex.org/W2047614366","https://openalex.org/W2048393105","https://openalex.org/W2048520013","https://openalex.org/W2056862683","https://openalex.org/W2068829602","https://openalex.org/W2080038255","https://openalex.org/W2086248020","https://openalex.org/W2087744586","https://openalex.org/W2096945381","https://openalex.org/W2108297871","https://openalex.org/W2122407197","https://openalex.org/W2147319166","https://openalex.org/W2158626113","https://openalex.org/W2162322364","https://openalex.org/W2167243874","https://openalex.org/W2178735577","https://openalex.org/W2300823947","https://openalex.org/W2301550466","https://openalex.org/W2306468091","https://openalex.org/W2400593953","https://openalex.org/W2521614036","https://openalex.org/W2521728311","https://openalex.org/W2546716216","https://openalex.org/W2560584690","https://openalex.org/W2592859824","https://openalex.org/W2595507424","https://openalex.org/W2734023159","https://openalex.org/W2766309915","https://openalex.org/W4205347548","https://openalex.org/W6638708518","https://openalex.org/W6676333568","https://openalex.org/W6698319996","https://openalex.org/W6712844777","https://openalex.org/W6730419024"],"related_works":["https://openalex.org/W2378666660","https://openalex.org/W2039771558","https://openalex.org/W3033495450","https://openalex.org/W2144511445","https://openalex.org/W2085780778","https://openalex.org/W2783439599","https://openalex.org/W596429175","https://openalex.org/W2789155518","https://openalex.org/W4285429071","https://openalex.org/W2796567256"],"abstract_inverted_index":{"The":[0,38,129,202],"emerging":[1,216],"high-performance":[2],"computing":[3,218],"Exascale":[4,217],"supercomputing":[5],"system,":[6],"which":[7,91],"is":[8,86,132],"anticipated":[9],"to":[10,52,190,214],"be":[11,58,207],"available":[12],"in":[13,29,47,155],"2020,":[14],"will":[15,24,41,57],"unravel":[16],"many":[17],"scientific":[18],"mysteries.":[19],"This":[20,105],"extraordinary":[21],"processing":[22],"framework":[23,40,131],"accomplish":[25],"a":[26,93,108],"thousand-folds":[27],"increment":[28],"figuring":[30],"power":[31,96],"contrasted":[32],"with":[33,66,167],"the":[34,53,74,77,152,164],"current":[35],"Petascale":[36],"framework.":[37,149],"prospective":[39],"help":[42],"development":[43],"communities":[44],"and":[45,120,125,137,162,182,194,211],"researchers":[46],"exploring":[48],"from":[49],"conventional":[50],"homogeneous":[51],"heterogeneous":[54,148],"frameworks":[55],"that":[56,113,143],"joined":[59],"into":[60],"energy":[61],"efficient":[62],"GPU":[63],"devices":[64],"along":[65],"traditional":[67],"CPUs.":[68],"For":[69],"accomplishing":[70],"ExaFlops":[71],"execution":[72],"through":[73],"Ultrascale":[75],"framework,":[76],"present":[78],"innovations":[79],"are":[80],"confronting":[81],"several":[82],"challenges.":[83],"Huge":[84],"parallelism":[85,116,122],"one":[87],"of":[88,134],"these":[89],"challenges,":[90],"requires":[92],"novel":[94],"low":[95],"consuming":[97,199],"parallel":[98,110],"programming":[99,111],"approach":[100,205],"for":[101],"attaining":[102],"massive":[103,115,196],"performance.":[104],"paper":[106],"introduced":[107],"new":[109],"model":[112,154,213],"achieves":[114],"by":[117,198],"combining":[118],"coarse-grained":[119],"fine-grained":[121],"over":[123,147],"inter-node":[124],"intranode":[126],"computation":[127],"respectively.":[128],"proposed":[130,153,203],"tri-hybrid":[133],"MPI,":[135],"OpenMP,":[136],"compute":[138,144],"unified":[139],"device":[140],"architecture":[141],"(MOC)":[142],"input":[145],"data":[146],"We":[150],"implemented":[151,192],"linear":[156,170,178,185],"algebraic":[157],"dense":[158],"matrix":[159],"multiplication":[160],"application,":[161],"compared":[163],"quantified":[165],"metrics":[166],"well-known":[168],"basic":[169,177,184],"algebra":[171,179,186],"subroutine":[172],"libraries":[173],"such":[174],"as":[175],"CUDA":[176],"subroutines":[180],"library":[181],"KAUST":[183],"subprograms.":[187],"MOC":[188,204],"outperformed":[189],"all":[191],"methods":[193],"achieved":[195],"performance":[197],"less":[200],"power.":[201],"can":[206],"considered":[208],"an":[209],"initial":[210],"leading":[212],"deal":[215],"systems.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
