{"id":"https://openalex.org/W2175961926","doi":"https://doi.org/10.1145/2381056.2381072","title":"Predictive modeling and analysis of OP2 on distributed memory GPU clusters","display_name":"Predictive modeling and analysis of OP2 on distributed memory GPU clusters","publication_year":2012,"publication_date":"2012-10-08","ids":{"openalex":"https://openalex.org/W2175961926","doi":"https://doi.org/10.1145/2381056.2381072","mag":"2175961926"},"language":"en","primary_location":{"id":"doi:10.1145/2381056.2381072","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2381056.2381072","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/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":["Oxford e-Research Centre, University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oxford e-Research Centre, University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056186758","display_name":"Michael B. Giles","orcid":"https://orcid.org/0000-0002-5445-3721"},"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":"M. B. Giles","raw_affiliation_strings":["Oxford e-Research Centre, University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oxford e-Research Centre, University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053563062","display_name":"Carlo Bertolli","orcid":"https://orcid.org/0009-0006-6852-1445"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"C. Bertolli","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000319133","display_name":"Paul H. J. Kelly","orcid":"https://orcid.org/0000-0001-5905-1804"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"P. H.J. Kelly","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4484,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82881466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"40","issue":"2","first_page":"61","last_page":"67"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8496842980384827},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.779405951499939},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.777783989906311},{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.7596439123153687},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7527768611907959},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.568383514881134},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5283100008964539},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5151575803756714},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4657018780708313},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.45706334710121155},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40003684163093567},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35837477445602417},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3547484874725342},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.3274380564689636},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22632041573524475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8496842980384827},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.779405951499939},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.777783989906311},{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.7596439123153687},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7527768611907959},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.568383514881134},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5283100008964539},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5151575803756714},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4657018780708313},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.45706334710121155},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40003684163093567},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35837477445602417},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3547484874725342},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.3274380564689636},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22632041573524475},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2381056.2381072","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2381056.2381072","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1484160293","https://openalex.org/W1555233232","https://openalex.org/W2012867959","https://openalex.org/W2024639384","https://openalex.org/W2039985559","https://openalex.org/W2075537166","https://openalex.org/W2118055195","https://openalex.org/W2146331174","https://openalex.org/W2154968583","https://openalex.org/W2170070166"],"related_works":["https://openalex.org/W3214851784","https://openalex.org/W2333876175","https://openalex.org/W1974295285","https://openalex.org/W2024639384","https://openalex.org/W2024548679","https://openalex.org/W3000108308","https://openalex.org/W2099034447","https://openalex.org/W3213915833","https://openalex.org/W4226161603","https://openalex.org/W1971132357"],"abstract_inverted_index":{"OP2":[0,56,69],"is":[1],"an":[2,24,107,122],"\"active\"":[3],"library":[4],"framework":[5],"for":[6,167],"the":[7,20,39,64,73,86,118,144],"development":[8],"and":[9,34,52,81,91,106,157],"solution":[10,87],"of":[11,23,55,66,75,88,170],"unstructured":[12],"mesh":[13],"based":[14,126],"applications.":[15,171],"It":[16],"aims":[17],"to":[18,30,41,116,131,162],"decouple":[19],"scientific":[21],"specification":[22],"application":[25,95],"from":[26],"its":[27,83],"parallel":[28],"implementation":[29],"achieve":[31],"code":[32],"longevity":[33],"near-optimal":[35],"performance":[36,50,84,114,120,134,145],"through":[37,151],"re-targeting":[38],"backend":[40],"different":[42],"multi-core/many-core":[43],"hardware.":[44],"This":[45],"paper":[46],"presents":[47],"a":[48,67,89,102],"predictive":[49],"analysis":[51],"benchmarking":[53],"study":[54],"on":[57,77,121,136,155],"heterogeneous":[58,140,158],"cluster":[59,165],"systems.":[60,141],"We":[61,111],"first":[62],"present":[63],"design":[65],"new":[68],"back-end":[70],"that":[71,147],"enables":[72],"execution":[74],"applications":[76],"distributed":[78,138],"memory":[79,139],"clusters,":[80],"benchmark":[82],"during":[85],"1.5M":[90],"26M":[92],"edge-based":[93],"CFD":[94],"written":[96],"using":[97],"OP2.":[98],"Benchmark":[99],"systems":[100,166],"include":[101],"large-scale":[103],"CrayXE6":[104],"system":[105],"Intel":[108],"Westmere/InfiniBand":[109],"cluster.":[110],"then":[112],"apply":[113],"modeling":[115],"predict":[117],"application's":[119],"NVIDIA":[123],"Tesla":[124],"C2070":[125],"GPU":[127],"cluster,":[128],"enabling":[129],"us":[130],"compare":[132],"OP2's":[133],"capabilities":[135],"emerging":[137],"Results":[142],"illustrate":[143],"benefits":[146],"can":[148],"be":[149],"gained":[150],"many-core":[152],"solutions":[153],"both":[154],"single-node":[156],"configurations":[159],"in":[160],"comparison":[161],"traditional":[163],"homogeneous":[164],"this":[168],"class":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}