{"id":"https://openalex.org/W3048230252","doi":"https://doi.org/10.1145/3407947.3407963","title":"GPU Acceleration of a High-Order CFD Program","display_name":"GPU Acceleration of a High-Order CFD Program","publication_year":2020,"publication_date":"2020-06-27","ids":{"openalex":"https://openalex.org/W3048230252","doi":"https://doi.org/10.1145/3407947.3407963","mag":"3048230252"},"language":"en","primary_location":{"id":"doi:10.1145/3407947.3407963","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3407947.3407963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 4th International Conference on High Performance Compilation, Computing and Communications","raw_type":"proceedings-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/A5103002571","display_name":"Shengxiang Wang","orcid":"https://orcid.org/0000-0001-6698-790X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shengxiang Wang","raw_affiliation_strings":["Institute for Quantum Information & State Key Laboratory of High Performance Computing, College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Institute for Quantum Information & State Key Laboratory of High Performance Computing, College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059229969","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0001-9596-2752"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Institute for Quantum Information & State Key Laboratory of High Performance Computing, College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Institute for Quantum Information & State Key Laboratory of High Performance Computing, College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100889262","display_name":"Yonggang Che","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonggang Che","raw_affiliation_strings":["Institute for Quantum Information & State Key Laboratory of High Performance Computing, College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Institute for Quantum Information & State Key Laboratory of High Performance Computing, College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103002571"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.4621,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59131823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980999827384949,"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":0.9980999827384949,"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/T10173","display_name":"Computational Fluid Dynamics and Aerodynamics","score":0.9966999888420105,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.859387993812561},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.7966194152832031},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7651141285896301},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7440850734710693},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6167841553688049},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.5546191334724426},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5227342247962952},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.48146429657936096},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4456190764904022},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.44207918643951416},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.43275386095046997},{"id":"https://openalex.org/keywords/computational-fluid-dynamics","display_name":"Computational fluid dynamics","score":0.4130125939846039},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.22856959700584412},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19135969877243042},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.12577462196350098}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.859387993812561},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.7966194152832031},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7651141285896301},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7440850734710693},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6167841553688049},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.5546191334724426},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5227342247962952},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.48146429657936096},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4456190764904022},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.44207918643951416},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.43275386095046997},{"id":"https://openalex.org/C1633027","wikidata":"https://www.wikidata.org/wiki/Q815820","display_name":"Computational fluid dynamics","level":2,"score":0.4130125939846039},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.22856959700584412},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19135969877243042},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.12577462196350098},{"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/C57879066","wikidata":"https://www.wikidata.org/wiki/Q41217","display_name":"Mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3407947.3407963","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3407947.3407963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 4th International Conference on High Performance Compilation, Computing and Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1651373482","https://openalex.org/W1985658314","https://openalex.org/W2071447842","https://openalex.org/W2076874848","https://openalex.org/W2608177516","https://openalex.org/W2926767350","https://openalex.org/W2984602355","https://openalex.org/W3101708369"],"related_works":["https://openalex.org/W2621501241","https://openalex.org/W2208757713","https://openalex.org/W3177128669","https://openalex.org/W2147910609","https://openalex.org/W2609613932","https://openalex.org/W2991848348","https://openalex.org/W2008373862","https://openalex.org/W1963859303","https://openalex.org/W2331803692","https://openalex.org/W2466690044"],"abstract_inverted_index":{"HNSC":[0,27],"(High":[1],"order":[2],"Navier-Stokes":[3],"simulator":[4],"for":[5],"Compressible":[6],"flow)":[7],"is":[8,43,66,83],"an":[9],"aerodynamics":[10],"numerical":[11],"simulation":[12],"application":[13,108],"that":[14,106],"involves":[15],"high":[16],"computational":[17],"cost.":[18],"This":[19],"paper":[20],"presents":[21],"our":[22],"efforts":[23],"porting":[24],"and":[25,36,56,74,97],"optimizing":[26],"on":[28,50,85,135],"the":[29,46,51,70,77,107,114,121,132,136],"heterogeneous":[30],"architecture":[31],"consists":[32],"of":[33,53,129],"multi-core":[34],"CPUs":[35,96],"NVIDIA":[37,99],"GPUs.":[38],"The":[39,103,117],"basic":[40],"GPU":[41,115,118],"parallelization":[42],"done":[44,84],"with":[45,88],"CUDA":[47],"Fortran":[48],"based":[49],"characteristics":[52],"structured":[54],"mesh":[55],"fourth-order":[57],"Runge-Kutta":[58],"time":[59],"marching":[60],"scheme.":[61],"A":[62],"data":[63,72],"packing":[64],"method":[65],"proposed":[67],"to":[68,75],"optimize":[69],"CPU-GPU":[71],"transfer":[73],"improve":[76],"MPI":[78,133],"communication":[79],"efficiency.":[80],"Performance":[81],"evaluation":[82],"a":[86,125],"server":[87],"two":[89,137],"12-core":[90],"Intel":[91],"Xeon":[92],"Skylake":[93,138],"Gold":[94],"5118":[95],"one":[98],"Tesla":[100],"V100":[101,122],"GPU.":[102],"results":[104],"show":[105],"can":[109],"be":[110],"significantly":[111],"benefited":[112],"from":[113],"acceleration.":[116],"version,":[119],"using":[120],"GPU,":[123],"achieves":[124],"maximum":[126],"performance":[127],"speedup":[128],"9.3":[130],"over":[131],"implementation":[134],"CPUs.":[139]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}