{"id":"https://openalex.org/W2780244597","doi":"https://doi.org/10.1145/3120895.3120903","title":"A porting and optimization of search for neighbour-particle in MPS method for GPU by using OpenACC","display_name":"A porting and optimization of search for neighbour-particle in MPS method for GPU by using OpenACC","publication_year":2017,"publication_date":"2017-06-07","ids":{"openalex":"https://openalex.org/W2780244597","doi":"https://doi.org/10.1145/3120895.3120903","mag":"2780244597"},"language":"en","primary_location":{"id":"doi:10.1145/3120895.3120903","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3120895.3120903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies","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/A5022019173","display_name":"Takaaki Miyajima","orcid":"https://orcid.org/0000-0001-9409-0913"},"institutions":[{"id":"https://openalex.org/I2800865746","display_name":"Japan Aerospace Exploration Agency","ror":"https://ror.org/059yhyy33","country_code":"JP","type":"facility","lineage":["https://openalex.org/I2800865746"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takaaki Miyajima","raw_affiliation_strings":["Numerical Simulation Research Unit, Aeronautical Technology Directorate, Japan Aerospace Exploration Agency (JAXA), Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Numerical Simulation Research Unit, Aeronautical Technology Directorate, Japan Aerospace Exploration Agency (JAXA), Tokyo, Japan","institution_ids":["https://openalex.org/I2800865746"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109287578","display_name":"Kenichi Kubota","orcid":"https://orcid.org/0009-0004-9787-7630"},"institutions":[{"id":"https://openalex.org/I2800865746","display_name":"Japan Aerospace Exploration Agency","ror":"https://ror.org/059yhyy33","country_code":"JP","type":"facility","lineage":["https://openalex.org/I2800865746"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenichi Kubota","raw_affiliation_strings":["Numerical Simulation Research Unit, Aeronautical Technology Directorate, Japan Aerospace Exploration Agency (JAXA), Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Numerical Simulation Research Unit, Aeronautical Technology Directorate, Japan Aerospace Exploration Agency (JAXA), Tokyo, Japan","institution_ids":["https://openalex.org/I2800865746"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064441115","display_name":"Naoyuki Fujita","orcid":"https://orcid.org/0000-0003-3946-1288"},"institutions":[{"id":"https://openalex.org/I2800865746","display_name":"Japan Aerospace Exploration Agency","ror":"https://ror.org/059yhyy33","country_code":"JP","type":"facility","lineage":["https://openalex.org/I2800865746"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoyuki Fujita","raw_affiliation_strings":["Numerical Simulation Research Unit, Aeronautical Technology Directorate, Japan Aerospace Exploration Agency (JAXA), Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Numerical Simulation Research Unit, Aeronautical Technology Directorate, Japan Aerospace Exploration Agency (JAXA), Tokyo, Japan","institution_ids":["https://openalex.org/I2800865746"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022019173"],"corresponding_institution_ids":["https://openalex.org/I2800865746"],"apc_list":null,"apc_paid":null,"fwci":0.4802,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65091263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11694","display_name":"Fluid Dynamics Simulations and Interactions","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11694","display_name":"Fluid Dynamics Simulations and Interactions","score":1.0,"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/T11382","display_name":"Fluid Dynamics and Heat Transfer","score":0.9753999710083008,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9688000082969666,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/porting","display_name":"Porting","score":0.9011460542678833},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7295451760292053},{"id":"https://openalex.org/keywords/pci-express","display_name":"PCI Express","score":0.7281887531280518},{"id":"https://openalex.org/keywords/particle","display_name":"Particle (ecology)","score":0.6726106405258179},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5349138379096985},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5306441187858582},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5210913419723511},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5043705701828003},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4668591320514679},{"id":"https://openalex.org/keywords/particle-method","display_name":"Particle method","score":0.43644753098487854},{"id":"https://openalex.org/keywords/particle-number","display_name":"Particle number","score":0.42118746042251587},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.3846322298049927},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.1283871829509735},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1121821403503418},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10400068759918213},{"id":"https://openalex.org/keywords/nuclear-physics","display_name":"Nuclear physics","score":0.08443182706832886},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.07642996311187744},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.06999200582504272}],"concepts":[{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.9011460542678833},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7295451760292053},{"id":"https://openalex.org/C64270927","wikidata":"https://www.wikidata.org/wiki/Q206924","display_name":"PCI Express","level":3,"score":0.7281887531280518},{"id":"https://openalex.org/C2778517922","wikidata":"https://www.wikidata.org/wiki/Q7140482","display_name":"Particle (ecology)","level":2,"score":0.6726106405258179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5349138379096985},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5306441187858582},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5210913419723511},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5043705701828003},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4668591320514679},{"id":"https://openalex.org/C2987747430","wikidata":"https://www.wikidata.org/wiki/Q24898874","display_name":"Particle method","level":3,"score":0.43644753098487854},{"id":"https://openalex.org/C74412414","wikidata":"https://www.wikidata.org/wiki/Q181155","display_name":"Particle number","level":3,"score":0.42118746042251587},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3846322298049927},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.1283871829509735},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1121821403503418},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10400068759918213},{"id":"https://openalex.org/C185544564","wikidata":"https://www.wikidata.org/wiki/Q81197","display_name":"Nuclear physics","level":1,"score":0.08443182706832886},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.07642996311187744},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.06999200582504272},{"id":"https://openalex.org/C82706917","wikidata":"https://www.wikidata.org/wiki/Q10251","display_name":"Plasma","level":2,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3120895.3120903","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3120895.3120903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.41999998688697815}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1041077039","https://openalex.org/W1669682122","https://openalex.org/W2295412046","https://openalex.org/W2326455597","https://openalex.org/W2402494931"],"related_works":["https://openalex.org/W2356602486","https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2351992668","https://openalex.org/W2324828474","https://openalex.org/W2374315191","https://openalex.org/W2391207559","https://openalex.org/W1662038552","https://openalex.org/W3021568819","https://openalex.org/W2780244597"],"abstract_inverted_index":{"Moving":[0],"Particle":[1],"Semi-implicit":[2],"(MPS)":[3],"method":[4,8,65],"is":[5,18,44,131],"a":[6,21,111],"particle":[7,22,35],"used":[9],"in":[10,63],"fields":[11],"such":[12],"as":[13,20],"computational":[14],"fluid":[15],"dynamics.":[16],"It":[17,71],"classified":[19],"method.":[23,51],"Target":[24],"fluids":[25],"and":[26,33,57,85,95,108],"objects":[27],"are":[28],"divided":[29],"up":[30],"into":[31],"particles,":[32],"each":[34],"interacts":[36],"with":[37,88,120],"its":[38],"neighbour-particle.":[39],"The":[40],"search":[41],"for":[42,60,66,73],"neighbour-particle":[43],"the":[45,49,77,127],"main":[46],"bottleneck":[47],"of":[48,75,129],"MPS":[50,64],"In":[52],"this":[53],"paper,":[54],"we":[55],"port":[56],"optimize":[58],"\"search":[59],"neighbour-particle\"":[61],"part":[62],"GPU":[67,114],"by":[68],"using":[69],"OpenACC.":[70],"accounted":[72],"56%":[74],"all":[76],"processing":[78],"time.":[79],"We":[80,98],"present":[81],"three":[82,89],"different":[83,90,102],"optimizations":[84],"evaluated":[86],"them":[87],"data":[91],"sets;":[92],"25,704,":[93],"224,910":[94],"2,247,750":[96],"particles.":[97],"also":[99],"use":[100],"four":[101],"GPUs;":[103],"NVIDIA":[104],"K20c,":[105],"GTX1080,":[106],"P100(PCIe)":[107],"P100(NVlink).":[109],"As":[110],"result,":[112],"P100(NVlink)":[113],"achieves":[115],"41.5":[116],"times":[117],"speed-up":[118],"compared":[119],"24":[121],"MPI":[122],"process":[123],"CPU":[124],"version":[125],"when":[126],"number":[128],"particles":[130],"2,247,750.":[132]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
