{"id":"https://openalex.org/W2132032903","doi":"https://doi.org/10.1177/1094342012462751","title":"Progress towards accelerating HOMME on hybrid multi-core systems","display_name":"Progress towards accelerating HOMME on hybrid multi-core systems","publication_year":2012,"publication_date":"2012-11-16","ids":{"openalex":"https://openalex.org/W2132032903","doi":"https://doi.org/10.1177/1094342012462751","mag":"2132032903"},"language":"en","primary_location":{"id":"doi:10.1177/1094342012462751","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342012462751","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","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/A5060330870","display_name":"Ilene Carpenter","orcid":null},"institutions":[{"id":"https://openalex.org/I1297288678","display_name":"National Renewable Energy Laboratory","ror":"https://ror.org/036266993","country_code":"US","type":"facility","lineage":["https://openalex.org/I1297288678","https://openalex.org/I1330989302","https://openalex.org/I2800842121"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"I. Carpenter","raw_affiliation_strings":["National Renewable Energy Laboratory, Golden, CO, USA","National Renewable Energy Laboratory , Golden, CO, USA"],"affiliations":[{"raw_affiliation_string":"National Renewable Energy Laboratory, Golden, CO, USA","institution_ids":["https://openalex.org/I1297288678"]},{"raw_affiliation_string":"National Renewable Energy Laboratory , Golden, CO, USA","institution_ids":["https://openalex.org/I1297288678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043192992","display_name":"Richard Archibald","orcid":"https://orcid.org/0000-0002-4538-9780"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R.K. Archibald","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659440","display_name":"Katherine J. Evans","orcid":"https://orcid.org/0000-0001-8174-6450"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K.J. Evans","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003788134","display_name":"Jeff Larkin","orcid":"https://orcid.org/0000-0001-7132-3120"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. Larkin","raw_affiliation_strings":["Cray Inc., Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Cray Inc., Oak Ridge, TN, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072693649","display_name":"Paulius Micikevicius","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"P. Micikevicius","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA","[Nvidia, Santa Clara, CA, USA]"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"[Nvidia, Santa Clara, CA, USA]","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031399553","display_name":"Matthew Norman","orcid":"https://orcid.org/0000-0003-4764-3348"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Norman","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025892783","display_name":"Jakub Rosi\u0144ski","orcid":"https://orcid.org/0000-0001-7941-0296"},"institutions":[{"id":"https://openalex.org/I1308126019","display_name":"National Oceanic and Atmospheric Administration","ror":"https://ror.org/02z5nhe81","country_code":"US","type":"funder","lineage":["https://openalex.org/I1308126019","https://openalex.org/I1343035065"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Rosinski","raw_affiliation_strings":["National Oceanic and Atmospheric Administration, Boulder, CO, USA"],"affiliations":[{"raw_affiliation_string":"National Oceanic and Atmospheric Administration, Boulder, CO, USA","institution_ids":["https://openalex.org/I1308126019"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028112523","display_name":"James L. Schwarzmeier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. Schwarzmeier","raw_affiliation_strings":["Cray Inc., Chippewa Falls, WI, USA","Cray Inc., Chippewa Falls, WI, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Cray Inc., Chippewa Falls, WI, USA","institution_ids":[]},{"raw_affiliation_string":"Cray Inc., Chippewa Falls, WI, USA#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022737320","display_name":"Mark A. Taylor","orcid":"https://orcid.org/0000-0002-9267-2554"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M.A. Taylor","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM, USA"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5060330870"],"corresponding_institution_ids":["https://openalex.org/I1297288678"],"apc_list":null,"apc_paid":null,"fwci":2.9731,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.90406308,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"27","issue":"3","first_page":"335","last_page":"347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10466","display_name":"Meteorological Phenomena and Simulations","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1902","display_name":"Atmospheric Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10466","display_name":"Meteorological Phenomena and Simulations","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1902","display_name":"Atmospheric Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10173","display_name":"Computational Fluid Dynamics and Aerodynamics","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10159","display_name":"Ionosphere and magnetosphere dynamics","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/3103","display_name":"Astronomy and Astrophysics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8110589981079102},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7283322215080261},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6539509296417236},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6513684988021851},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5699080228805542},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5390599966049194},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.46950483322143555},{"id":"https://openalex.org/keywords/dynamic-mode-decomposition","display_name":"Dynamic mode decomposition","score":0.41418737173080444},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.41147178411483765},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3401302099227905},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3202640414237976},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09908458590507507}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8110589981079102},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7283322215080261},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6539509296417236},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6513684988021851},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5699080228805542},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5390599966049194},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.46950483322143555},{"id":"https://openalex.org/C2777032711","wikidata":"https://www.wikidata.org/wiki/Q5318993","display_name":"Dynamic mode decomposition","level":2,"score":0.41418737173080444},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.41147178411483765},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3401302099227905},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3202640414237976},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09908458590507507},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342012462751","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342012462751","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1978001967","https://openalex.org/W1985217958","https://openalex.org/W1995016628","https://openalex.org/W2008642300","https://openalex.org/W2016411152","https://openalex.org/W2036126147","https://openalex.org/W2077101634","https://openalex.org/W2109356213","https://openalex.org/W2111530316","https://openalex.org/W2118898240","https://openalex.org/W2127900800","https://openalex.org/W2129522239","https://openalex.org/W2146901682","https://openalex.org/W2166823841","https://openalex.org/W3138798301"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W3191490922","https://openalex.org/W2794038527","https://openalex.org/W2151092287","https://openalex.org/W2523801036","https://openalex.org/W2505959877"],"abstract_inverted_index":{"The":[0,46,87],"suitability":[1],"of":[2,59,80,118,184],"a":[3,32,104],"spectral":[4,186],"element":[5],"based":[6],"dynamical":[7,47],"core":[8,48],"(HOMME)":[9],"within":[10,31,84],"the":[11,50,56,78,121,131,136,145,148,161,169,178,182,191],"Community":[12],"Atmospheric":[13],"Model":[14],"(CAM)":[15],"for":[16,168,181],"GPU-based":[17],"architectures":[18],"is":[19,49,125],"examined":[20],"and":[21,77,90,115],"initial":[22],"performance":[23,57,111,175],"results":[24,119],"are":[25,100,152],"reported.":[26],"This":[27],"work":[28,83],"was":[29],"done":[30],"project":[33],"to":[34,37,68,96,154],"enable":[35],"CAM":[36],"run":[38],"at":[39],"high":[40],"resolution":[41],"on":[42,112,144,190],"next-generation,":[43],"multi-petaflop":[44],"systems.":[45],"present":[51],"focus":[52],"because":[53],"it":[54],"dominates":[55],"profile":[58],"our":[60],"target":[61,170],"problem.":[62,171],"HOMME":[63,95,123],"enjoys":[64],"good":[65],"scalability":[66],"due":[67],"its":[69],"underlying":[70],"cubed-sphere":[71],"mesh":[72],"with":[73,103],"full":[74,122,162],"two-dimensional":[75],"decomposition":[76],"localization":[79],"all":[81],"computational":[82],"each":[85],"element.":[86],"thread":[88],"blocking":[89],"code":[91],"changes":[92],"that":[93,130,164],"allow":[94],"effectively":[97],"use":[98],"GPUs":[99],"described":[101],"along":[102],"rewritten":[105],"vertical":[106],"remapping":[107],"scheme,":[108],"which":[109],"improves":[110],"both":[113],"CPUs":[114],"GPUs.":[116],"Validation":[117],"in":[120,135],"model":[124,137,163],"also":[126],"described.":[127],"We":[128],"demonstrate":[129],"most":[132],"expensive":[133],"kernel":[134],"executes":[138],"more":[139],"than":[140,147],"three":[141],"times":[142],"faster":[143],"GPU":[146],"CPU.":[149],"These":[150],"improvements":[151],"expected":[153],"provide":[155],"improved":[156],"efficiency":[157],"when":[158],"incorporated":[159],"into":[160],"has":[165],"been":[166],"configured":[167],"Remaining":[172],"issues":[173],"affecting":[174],"include":[176],"optimizing":[177],"boundary":[179],"exchanges":[180],"case":[183],"multiple":[185],"elements":[187],"being":[188],"computed":[189],"GPU.":[192]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
