{"id":"https://openalex.org/W2558693665","doi":"https://doi.org/10.1109/asap.2016.7760771","title":"Unleashing the performance potential of CPU-GPU platforms for the 3D atmospheric Euler solver","display_name":"Unleashing the performance potential of CPU-GPU platforms for the 3D atmospheric Euler solver","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2558693665","doi":"https://doi.org/10.1109/asap.2016.7760771","mag":"2558693665"},"language":"en","primary_location":{"id":"doi:10.1109/asap.2016.7760771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2016.7760771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 27th International Conference on Application-specific Systems, Architectures and Processors (ASAP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5031545295","display_name":"Haohuan Fu","orcid":"https://orcid.org/0000-0002-6982-2235"},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haohuan Fu","raw_affiliation_strings":["Ministry of Education Key Lab. for Earth System Modeling, Center for Earth System Science, Tsinghua University","National Supercomputing Center in Wuxi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education Key Lab. for Earth System Modeling, Center for Earth System Science, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"National Supercomputing Center in Wuxi","institution_ids":["https://openalex.org/I4210158984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100659425","display_name":"Jingheng Xu","orcid":"https://orcid.org/0000-0001-7311-9924"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingheng Xu","raw_affiliation_strings":["Department of Computer Science & Technology, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038750675","display_name":"Lin Gan","orcid":"https://orcid.org/0000-0003-1297-4462"},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Gan","raw_affiliation_strings":["Department of Computer Science & Technology, Tsinghua University","National Supercomputing Center in Wuxi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"National Supercomputing Center in Wuxi","institution_ids":["https://openalex.org/I4210158984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005718995","display_name":"Chao Yang","orcid":"https://orcid.org/0000-0001-7426-6248"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Yang","raw_affiliation_strings":["Institute of Software, and State Key Laboratory of Computer Science, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software, and State Key Laboratory of Computer Science, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091437474","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0001-9740-6581"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["Department of Computer Science & Technology, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015849734","display_name":"Wenlai Zhao","orcid":"https://orcid.org/0000-0003-1036-4732"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenlai Zhao","raw_affiliation_strings":["Department of Computer Science & Technology, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101603393","display_name":"Wen Shi","orcid":"https://orcid.org/0000-0002-7716-2521"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Shi","raw_affiliation_strings":["Tsinghua University, Beijing, Beijing, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, Beijing, CN","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101487568","display_name":"Xinliang Wang","orcid":"https://orcid.org/0000-0002-9321-3069"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinliang Wang","raw_affiliation_strings":["Department of Computer Science & Technology, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101678397","display_name":"Guangwen Yang","orcid":"https://orcid.org/0000-0002-8673-8254"},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangwen Yang","raw_affiliation_strings":["Department of Computer Science & Technology, Tsinghua University","National Supercomputing Center in Wuxi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"National Supercomputing Center in Wuxi","institution_ids":["https://openalex.org/I4210158984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9172,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.9229708,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"63","issue":null,"first_page":"41","last_page":"49"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10466","display_name":"Meteorological Phenomena and Simulations","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9983000159263611,"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/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.787532389163971},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6957821249961853},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6847556233406067},{"id":"https://openalex.org/keywords/domain-decomposition-methods","display_name":"Domain decomposition methods","score":0.5665701627731323},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5555075407028198},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5127094984054565},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.49128955602645874},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.47810739278793335},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4632580876350403},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.45469987392425537},{"id":"https://openalex.org/keywords/backward-euler-method","display_name":"Backward Euler method","score":0.4432607889175415},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4170129597187042},{"id":"https://openalex.org/keywords/euler-equations","display_name":"Euler equations","score":0.2666357755661011},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.174907386302948},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.10936519503593445},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08188390731811523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.787532389163971},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6957821249961853},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6847556233406067},{"id":"https://openalex.org/C198880260","wikidata":"https://www.wikidata.org/wiki/Q5289813","display_name":"Domain decomposition methods","level":3,"score":0.5665701627731323},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5555075407028198},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5127094984054565},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.49128955602645874},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.47810739278793335},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4632580876350403},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.45469987392425537},{"id":"https://openalex.org/C768646","wikidata":"https://www.wikidata.org/wiki/Q2736820","display_name":"Backward Euler method","level":3,"score":0.4432607889175415},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4170129597187042},{"id":"https://openalex.org/C38409319","wikidata":"https://www.wikidata.org/wiki/Q375175","display_name":"Euler equations","level":2,"score":0.2666357755661011},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.174907386302948},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.10936519503593445},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08188390731811523},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asap.2016.7760771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2016.7760771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 27th International Conference on Application-specific Systems, Architectures and Processors (ASAP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8399999737739563,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W204599449","https://openalex.org/W1978782819","https://openalex.org/W1982763896","https://openalex.org/W1995016628","https://openalex.org/W2002950519","https://openalex.org/W2022036382","https://openalex.org/W2026834539","https://openalex.org/W2028145761","https://openalex.org/W2037274813","https://openalex.org/W2037520749","https://openalex.org/W2039378765","https://openalex.org/W2058327612","https://openalex.org/W2072480616","https://openalex.org/W2076377833","https://openalex.org/W2078528030","https://openalex.org/W2084520764","https://openalex.org/W2086151478","https://openalex.org/W2094281253","https://openalex.org/W2111530316","https://openalex.org/W2113190809","https://openalex.org/W2116729868","https://openalex.org/W2131608756","https://openalex.org/W2132032903","https://openalex.org/W2144481293","https://openalex.org/W2169120285","https://openalex.org/W2291408505","https://openalex.org/W4234438392","https://openalex.org/W6608260506"],"related_works":["https://openalex.org/W2056717482","https://openalex.org/W2017587301","https://openalex.org/W2030707850","https://openalex.org/W2170611190","https://openalex.org/W2566934642","https://openalex.org/W2548246577","https://openalex.org/W2092007952","https://openalex.org/W2096672917","https://openalex.org/W2019821619","https://openalex.org/W2220608481"],"abstract_inverted_index":{"As":[0],"a":[1,34,81,137,151,165,205],"traditional":[2],"application":[3],"on":[4,52,117,130,150,190],"various":[5],"supercomputers,":[6],"atmospheric":[7,36],"modeling":[8],"has":[9,114],"long":[10],"been":[11,115],"suffering":[12],"from":[13],"the":[14,23,39,44,58,73,87,102,107,131,141,174,183,200,215],"low":[15],"performance":[16,46,112,142,168],"efficiency.":[17],"In":[18,147,203],"this":[19],"paper,":[20],"we":[21,78,135],"pick":[22],"3D":[24],"Euler":[25,103],"equation":[26],"solver":[27],"(the":[28],"most":[29],"essential":[30],"dynamic":[31],"component":[32],"for":[33,71,101],"non-hydrostatic":[35],"model)":[37],"as":[38,197],"target":[40],"application,":[41],"and":[42,64,75,127,160],"explore":[43],"maximum":[45],"efficiency":[47,184,210],"that":[48],"can":[49],"be":[50],"achieved":[51,116,212],"CPU-GPU":[53,153],"hybrid":[54,60,152],"architectures.":[55],"Besides":[56],"presenting":[57],"suitable":[59],"domain":[61,219],"decomposition":[62,220],"methodology":[63],"taking":[65],"proper":[66],"usage":[67],"of":[68,143,169,173,185,217],"tuning":[69,84],"techniques":[70],"both":[72],"CPU":[74],"GPU":[76,83,119],"parts,":[77],"further":[79],"propose":[80],"novel":[82],"technique,":[85],"namely":[86],"customizable":[88],"data":[89],"caching":[90],"mechanism":[91],"with":[92,155],"thread":[93],"warp":[94],"rescheduling":[95],"scheme,":[96],"which":[97,178,213],"is":[98,176,179,211],"specifically":[99],"designed":[100],"solver.":[104],"Combining":[105],"all":[106],"optimizing":[108,187],"approaches":[109],"together,":[110],"remarkable":[111],"boost":[113],"mainstream":[118],"architectures":[120],"including":[121],"Tesla":[122,133,162],"Fermi":[123],"C2050,":[124],"K20\u00d7,":[125],"K40":[126],"K80.":[128],"Especially,":[129],"latest":[132],"K80,":[134],"demonstrate":[136,214],"31.64\u00d7":[138],"speedup":[139],"over":[140],"12-core":[144,157],"E5-2697":[145,158],"CPU.":[146],"addition,":[148,204],"based":[149,189],"node":[154],"two":[156,161],"CPUs":[159],"K80":[163],"GPUs,":[164],"sustained":[166],"double-precision":[167],"1.04":[170],"Tflops":[171],"(16%":[172],"peak)":[175],"achieved,":[177],"remarkably":[180],"higher":[181],"than":[182,195],"similar":[186],"tasks":[188],"heterogeneous":[191],"platforms":[192],"(strictly":[193],"less":[194],"10%,":[196],"demonstrated":[198],"in":[199],"related":[201],"work).":[202],"nearly":[206],"linear":[207],"weak":[208],"scaling":[209],"effectiveness":[216],"our":[218],"method.":[221]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
