{"id":"https://openalex.org/W2024639384","doi":"https://doi.org/10.1145/1964218.1964223","title":"Performance analysis of a hybrid MPI/CUDA implementation of the NASLU benchmark","display_name":"Performance analysis of a hybrid MPI/CUDA implementation of the NASLU benchmark","publication_year":2011,"publication_date":"2011-03-29","ids":{"openalex":"https://openalex.org/W2024639384","doi":"https://doi.org/10.1145/1964218.1964223","mag":"2024639384"},"language":"en","primary_location":{"id":"doi:10.1145/1964218.1964223","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1964218.1964223","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMETRICS Performance Evaluation Review","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/A5084262733","display_name":"S. J. Pennycook","orcid":"https://orcid.org/0000-0003-0237-3823"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"S. J. Pennycook","raw_affiliation_strings":["University of Warwick, UK","#N# University of Warwick, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Warwick, UK","institution_ids":["https://openalex.org/I39555362"]},{"raw_affiliation_string":"#N# University of Warwick, UK","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110790800","display_name":"S.D. Hammond","orcid":null},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"S. D. Hammond","raw_affiliation_strings":["University of Warwick, UK","#N# University of Warwick, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Warwick, UK","institution_ids":["https://openalex.org/I39555362"]},{"raw_affiliation_string":"#N# University of Warwick, UK","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051267613","display_name":"Stephen A. Jarvis","orcid":"https://orcid.org/0000-0002-1249-2167"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"S. A. Jarvis","raw_affiliation_strings":["University of Warwick, UK","#N# University of Warwick, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Warwick, UK","institution_ids":["https://openalex.org/I39555362"]},{"raw_affiliation_string":"#N# University of Warwick, UK","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070789282","display_name":"Gihan R. Mudalige","orcid":"https://orcid.org/0000-0002-1398-5174"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"G. R. Mudalige","raw_affiliation_strings":["University of Oxford, UK","University of Oxford, UK,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"University of Oxford, UK,","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.0934,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.97889381,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"38","issue":"4","first_page":"23","last_page":"29"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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":0.9997000098228455,"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/cuda","display_name":"CUDA","score":0.8468164205551147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8418428897857666},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8394984602928162},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7739633321762085},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.6650142669677734},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.5841333270072937},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.43430033326148987},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4300176203250885},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.41299569606781006},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.41077661514282227},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36531341075897217},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.33719971776008606}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8468164205551147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8418428897857666},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8394984602928162},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7739633321762085},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6650142669677734},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.5841333270072937},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.43430033326148987},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4300176203250885},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.41299569606781006},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.41077661514282227},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36531341075897217},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.33719971776008606},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1964218.1964223","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1964218.1964223","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMETRICS Performance Evaluation Review","raw_type":"journal-article"},{"id":"pmh:oai:wrap.warwick.ac.uk:47467","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400665","display_name":"Warwick Research Archive Portal (University of Warwick)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39555362","host_organization_name":"University of Warwick","host_organization_lineage":["https://openalex.org/I39555362"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Item"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.364.4798","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.364.4798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.oerc.ox.ac.uk/personal-pages/gihan/publications/p23-pennycook.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W158368254","https://openalex.org/W1496163785","https://openalex.org/W1504211003","https://openalex.org/W1504291959","https://openalex.org/W1517304607","https://openalex.org/W1558138778","https://openalex.org/W1570437034","https://openalex.org/W1841716671","https://openalex.org/W1980153429","https://openalex.org/W1992851788","https://openalex.org/W2007516655","https://openalex.org/W2011652244","https://openalex.org/W2013173369","https://openalex.org/W2022036382","https://openalex.org/W2057795393","https://openalex.org/W2108266785","https://openalex.org/W2108600626","https://openalex.org/W2112121929","https://openalex.org/W2112185810","https://openalex.org/W2114927422","https://openalex.org/W2132600716","https://openalex.org/W2139613964","https://openalex.org/W2146331174","https://openalex.org/W2152886061","https://openalex.org/W2155119349","https://openalex.org/W2159481344","https://openalex.org/W2164890169","https://openalex.org/W2165038730","https://openalex.org/W2168110206","https://openalex.org/W2608013373","https://openalex.org/W6638752821"],"related_works":["https://openalex.org/W2251285835","https://openalex.org/W2056717482","https://openalex.org/W2017587301","https://openalex.org/W2030707850","https://openalex.org/W2170611190","https://openalex.org/W2566934642","https://openalex.org/W1582436825","https://openalex.org/W2092007952","https://openalex.org/W2548246577","https://openalex.org/W2096672917"],"abstract_inverted_index":{"We":[0,65],"present":[1],"the":[2,9,13,29,57],"performance":[3,70],"analysis":[4],"of":[5,8,36,72,83],"a":[6,76,95],"port":[7],"LU":[10,73],"benchmark":[11],"from":[12,48],"NAS":[14],"Parallel":[15],"Benchmark":[16],"(NPB)":[17],"suite":[18],"to":[19,33,52,74],"NVIDIA's":[20,62],"Compute":[21],"Unified":[22],"Device":[23],"Architecture":[24],"(CUDA),":[25],"and":[26,86,101],"report":[27],"on":[28,61,90],"optimisation":[30],"efforts":[31],"employed":[32],"take":[34],"advantage":[35],"this":[37],"platform.":[38],"Execution":[39],"times":[40],"are":[41],"reported":[42],"for":[43],"several":[44],"different":[45],"GPUs,":[46],"ranging":[47],"low-end":[49],"consumergrade":[50],"products":[51],"high-end":[53],"HPC-grade":[54],"devices,":[55],"including":[56,94],"Tesla":[58],"C2050":[59],"built":[60,89],"Fermi":[63],"processor.":[64],"also":[66],"utilise":[67],"recently":[68],"developed":[69],"models":[71],"facilitate":[75],"comparison":[77],"between":[78],"future":[79],"large-scale":[80],"distributed":[81],"clusters":[82,88],"GPU":[84],"devices":[85],"existing":[87],"traditional":[91],"CPU":[92],"architectures,":[93],"quad-socket,":[96],"quad-core":[97],"AMD":[98],"Opteron":[99],"cluster":[100],"an":[102],"IBM":[103],"BlueGene/P.":[104]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":11}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
