{"id":"https://openalex.org/W2039985559","doi":"https://doi.org/10.1093/comjnl/bxr062","title":"Performance Analysis and Optimization of the OP2 Framework on Many-Core Architectures","display_name":"Performance Analysis and Optimization of the OP2 Framework on Many-Core Architectures","publication_year":2011,"publication_date":"2011-07-12","ids":{"openalex":"https://openalex.org/W2039985559","doi":"https://doi.org/10.1093/comjnl/bxr062","mag":"2039985559"},"language":"en","primary_location":{"id":"doi:10.1093/comjnl/bxr062","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxr062","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","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/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, Oxford, UK","Oxford e-Research Centre, University of Oxford,Oxford,UK"],"affiliations":[{"raw_affiliation_string":"Oxford e-Research Centre, University of Oxford, Oxford, UK","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Oxford e-Research Centre, University of Oxford,Oxford,UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","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":true,"raw_author_name":"G. R. Mudalige","raw_affiliation_strings":["Oxford e-Research Centre, University of Oxford, Oxford, UK","Oxford e-Research Centre, University of Oxford,Oxford,UK"],"affiliations":[{"raw_affiliation_string":"Oxford e-Research Centre, University of Oxford, Oxford, UK","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Oxford e-Research Centre, University of Oxford,Oxford,UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037791710","display_name":"Z. Sharif","orcid":null},"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":"Z. Sharif","raw_affiliation_strings":["Department of Computing, Imperial College London, London, UK","Department of Computing; Imperial College London; London UK"],"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing; Imperial College London; London UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083653923","display_name":"Graham Markall","orcid":"https://orcid.org/0009-0003-9005-1716"},"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":"G. Markall","raw_affiliation_strings":["Department of Computing, Imperial College London, London, UK","Department of Computing; Imperial College London; London UK"],"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing; Imperial College London; London UK","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":["Department of Computing, Imperial College London, London, UK","Department of Computing; Imperial College London; London UK"],"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing; Imperial College London; London UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070789282"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":{"value":2635,"currency":"GBP","value_usd":3232},"apc_paid":null,"fwci":4.896,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.95543688,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"55","issue":"2","first_page":"168","last_page":"180"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9991999864578247,"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":0.9965999722480774,"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":0.8661963939666748},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.8419734239578247},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.7985372543334961},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7193633913993835},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6879001259803772},{"id":"https://openalex.org/keywords/many-core","display_name":"Many core","score":0.651643693447113},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5184870958328247},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5048697590827942},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4775486886501312},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4663825035095215},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4660891890525818},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.4614713191986084},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.26377958059310913},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.17732617259025574},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13571012020111084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8661963939666748},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.8419734239578247},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.7985372543334961},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7193633913993835},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6879001259803772},{"id":"https://openalex.org/C3020431745","wikidata":"https://www.wikidata.org/wiki/Q25325220","display_name":"Many core","level":2,"score":0.651643693447113},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5184870958328247},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5048697590827942},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4775486886501312},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4663825035095215},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4660891890525818},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.4614713191986084},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26377958059310913},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.17732617259025574},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13571012020111084},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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:10.1093/comjnl/bxr062","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxr062","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.713.5184","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.713.5184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.maths.ox.ac.uk/gilesm/files/OP2-CJ.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.5,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G2249403966","display_name":null,"funder_award_id":"EP/I00677X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7583076630","display_name":null,"funder_award_id":"EP/I006079/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1484160293","https://openalex.org/W1507090345","https://openalex.org/W1555233232","https://openalex.org/W1991106844","https://openalex.org/W2028262862","https://openalex.org/W2065080695","https://openalex.org/W2085123413","https://openalex.org/W2118055195","https://openalex.org/W2158640099","https://openalex.org/W2333521678"],"related_works":["https://openalex.org/W2740999212","https://openalex.org/W2188971969","https://openalex.org/W1994052277","https://openalex.org/W2769399951","https://openalex.org/W2024554511","https://openalex.org/W2588843388","https://openalex.org/W3042238487","https://openalex.org/W2885985254","https://openalex.org/W2599563411","https://openalex.org/W2841806531"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,66,72],"benchmarking,":[4],"performance":[5,49,61,107,150],"analysis":[6,103],"and":[7,42,47,90,94,114,142,151],"optimization":[8],"study":[9],"of":[10,24,35,74,111,122,128,137],"the":[11,21,32,36,52,87,105,109,120,135,139,145,148],"OP2":[12,28],"\u2018active\u2019":[13],"library,":[14],"which":[15],"provides":[16],"an":[17,123],"abstraction":[18],"framework":[19],"for":[20,65,119,155],"parallel":[22,40,117],"execution":[23],"unstructured":[25,68,125],"mesh":[26,69,126],"applications.":[27],"aims":[29],"to":[30,54],"decouple":[31],"scientific":[33],"specification":[34],"application":[37,53,70],"from":[38,82,97],"its":[39],"implementation,":[41],"thereby":[43],"achieve":[44],"code":[45],"longevity":[46],"near-optimal":[48],"through":[50],"re-targeting":[51],"execute":[55],"on":[56,71,86],"different":[57],"multi-core/many-core":[58],"hardware.":[59],"Runtime":[60],"results":[62],"are":[63],"presented":[64],"representative":[67],"variety":[73],"many-core":[75],"processor":[76],"systems,":[77],"including":[78],"traditional":[79],"X86":[80],"architectures":[81],"Intel":[83],"(Xeon":[84],"based":[85],"older":[88],"Penryn":[89],"current":[91],"Nehalem":[92],"micro-architectures)":[93],"GPU":[95,115,149],"offerings":[96],"NVIDIA":[98],"(GTX260,":[99],"Tesla":[100],"C2050).":[101],"Our":[102],"demonstrates":[104],"contrasting":[106],"between":[108],"use":[110],"CPU":[112],"(OpenMP)":[113],"(CUDA)":[116],"implementations":[118],"solution":[121],"industrial-sized":[124],"consisting":[127],"about":[129],"1.5":[130],"million":[131],"edges.":[132],"Results":[133],"show":[134],"significance":[136],"choosing":[138],"correct":[140],"partition":[141],"thread-block":[143],"configuration,":[144],"factors":[146],"limiting":[147],"insights":[152],"into":[153],"optimizations":[154],"improved":[156],"performance.":[157]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
