{"id":"https://openalex.org/W2984602355","doi":"https://doi.org/10.1145/3295500.3356209","title":"GPU acceleration of extreme scale pseudo-spectral simulations of turbulence using asynchronism","display_name":"GPU acceleration of extreme scale pseudo-spectral simulations of turbulence using asynchronism","publication_year":2019,"publication_date":"2019-11-07","ids":{"openalex":"https://openalex.org/W2984602355","doi":"https://doi.org/10.1145/3295500.3356209","mag":"2984602355"},"language":"en","primary_location":{"id":"doi:10.1145/3295500.3356209","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3295500.3356209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","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/A5090200208","display_name":"K. Ravikumar","orcid":"https://orcid.org/0000-0002-3869-7515"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kiran Ravikumar","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055298466","display_name":"David Appelhans","orcid":"https://orcid.org/0000-0003-1433-9198"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Appelhans","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005975375","display_name":"P. K. Yeung","orcid":"https://orcid.org/0000-0002-6278-6032"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. K. Yeung","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10466","display_name":"Meteorological Phenomena and Simulations","score":0.9993000030517578,"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":0.9993000030517578,"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/T10360","display_name":"Fluid Dynamics and Turbulent Flows","score":0.998199999332428,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.991599977016449,"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/computer-science","display_name":"Computer science","score":0.8190000057220459},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7331722378730774},{"id":"https://openalex.org/keywords/petascale-computing","display_name":"Petascale computing","score":0.6502490639686584},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.6370376348495483},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5482138991355896},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5152040123939514},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5005588531494141},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.4449312090873718},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4257504940032959},{"id":"https://openalex.org/keywords/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.4166211783885956},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.39321959018707275},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11135005950927734}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8190000057220459},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7331722378730774},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.6502490639686584},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.6370376348495483},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5482138991355896},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5152040123939514},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5005588531494141},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.4449312090873718},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4257504940032959},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.4166211783885956},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.39321959018707275},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11135005950927734},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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:10.1145/3295500.3356209","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3295500.3356209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W68986789","https://openalex.org/W323536346","https://openalex.org/W1272383281","https://openalex.org/W1528581602","https://openalex.org/W1983144994","https://openalex.org/W2089297419","https://openalex.org/W2105864099","https://openalex.org/W2140980608","https://openalex.org/W2255672477","https://openalex.org/W2400648951","https://openalex.org/W2408478130","https://openalex.org/W2563901451","https://openalex.org/W2592859824","https://openalex.org/W2766043324","https://openalex.org/W2792539412","https://openalex.org/W2798865130","https://openalex.org/W2811111775","https://openalex.org/W3103952756","https://openalex.org/W4298060601"],"related_works":["https://openalex.org/W2021702679","https://openalex.org/W3038449658","https://openalex.org/W1582746211","https://openalex.org/W2266027327","https://openalex.org/W2278366184","https://openalex.org/W2073684863","https://openalex.org/W4206324154","https://openalex.org/W1978931242","https://openalex.org/W2154629969","https://openalex.org/W1602284866"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"new":[3],"advances":[4],"in":[5,56,95,142],"GPU-driven":[6],"Fourier":[7],"pseudo-spectral":[8],"numerical":[9],"algorithms,":[10],"which":[11,54,89],"allow":[12],"the":[13,23,27,37,67,72,77,84],"simulation":[14],"of":[15,26,40,83,121,129],"turbulent":[16],"fluid":[17],"flow":[18],"at":[19],"problem":[20,87,116,134,138],"sizes":[21,88],"beyond":[22],"current":[24],"state":[25],"art.":[28],"In":[29],"contrast":[30],"to":[31,93,113,126],"several":[32],"massively":[33],"parallel":[34],"petascale":[35],"systems,":[36],"dense":[38],"nodes":[39,120],"Summit,":[41,122],"Sierra,":[42],"and":[43,76],"expected":[44],"exascale":[45],"machines":[46],"can":[47],"be":[48],"exploited":[49],"with":[50,66,123],"coarser":[51],"MPI":[52,58],"decompositions":[53],"result":[55],"improved":[57,102],"all-to-all":[59],"scaling.":[60],"An":[61],"asynchronous":[62],"batching":[63],"strategy,":[64],"combined":[65],"fast":[68,78],"hardware":[69],"connection":[70],"between":[71],"large":[73,92],"CPU":[74,127],"memory":[75],"GPUs":[79,85],"allows":[80],"effective":[81],"use":[82],"on":[86,118],"are":[90],"too":[91],"reside":[94],"GPU":[96,125],"memory.":[97],"Communication":[98],"performance":[99,109],"is":[100,110],"further":[101],"by":[103],"a":[104,114,124,132],"hybrid":[105],"MPI+OpenMP":[106],"approach.":[107],"Favorable":[108],"obtained":[111],"up":[112],"184323":[115],"size":[117,135,139],"3072":[119],"speedup":[128],"4.7":[130],"for":[131],"122883":[133],"(the":[136],"largest":[137],"previously":[140],"published":[141],"turbulence":[143],"literature).":[144]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}