{"id":"https://openalex.org/W2113190809","doi":"https://doi.org/10.1145/1513895.1513905","title":"3D finite difference computation on GPUs using CUDA","display_name":"3D finite difference computation on GPUs using CUDA","publication_year":2009,"publication_date":"2009-03-08","ids":{"openalex":"https://openalex.org/W2113190809","doi":"https://doi.org/10.1145/1513895.1513905","mag":"2113190809"},"language":"en","primary_location":{"id":"doi:10.1145/1513895.1513905","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1513895.1513905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2nd Workshop on General Purpose Processing on Graphics Processing Units","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/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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Paulius Micikevicius","raw_affiliation_strings":["NVIDIA, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5072693649"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":201.3908,"has_fulltext":false,"cited_by_count":522,"citation_normalized_percentile":{"value":1.0,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"79","last_page":"84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10271","display_name":"Seismic Imaging and Inversion Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1908","display_name":"Geophysics"},"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/T10271","display_name":"Seismic Imaging and Inversion Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1908","display_name":"Geophysics"},"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/T11609","display_name":"Geophysical Methods and Applications","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"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/T11757","display_name":"Seismic Waves and Analysis","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1908","display_name":"Geophysics"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8763103485107422},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8537230491638184},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7898297309875488},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.7403815388679504},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6918672919273376},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.6319912075996399},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5089125633239746},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.4815519154071808},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2764459252357483},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.11602699756622314},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11471229791641235},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.08663222193717957}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8763103485107422},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8537230491638184},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7898297309875488},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.7403815388679504},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6918672919273376},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.6319912075996399},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5089125633239746},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.4815519154071808},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2764459252357483},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.11602699756622314},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11471229791641235},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.08663222193717957},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1513895.1513905","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1513895.1513905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2nd Workshop on General Purpose Processing on Graphics Processing Units","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.472.447","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.472.447","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://developer.download.nvidia.com/CUDA/CUDA_Zone/papers/gpu_3dfd_rev.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5299999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307925","display_name":"Hess Corporation","ror":"https://ror.org/00zbk1w77"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2028499920","https://openalex.org/W2044804449","https://openalex.org/W2076211048","https://openalex.org/W2129471558","https://openalex.org/W2154786353","https://openalex.org/W2155503253","https://openalex.org/W3138798301"],"related_works":["https://openalex.org/W2162458236","https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"describe":[4],"a":[5,75,89,94],"GPU":[6],"parallelization":[7,101],"of":[8,39,46,62,69,85],"the":[9,22,26,31,37,40,53,56,60],"3D":[10],"finite":[11],"difference":[12],"computation":[13],"using":[14],"CUDA.":[15],"Data":[16],"access":[17],"redundancy":[18],"is":[19,44,81,102],"used":[20],"as":[21,34,36],"metric":[23],"to":[24,65],"determine":[25],"optimal":[27],"implementation":[28],"for":[29],"both":[30],"stencil-only":[32],"computation,":[33],"well":[35],"discretization":[38],"wave":[41],"equation,":[42],"which":[43],"currently":[45],"great":[47],"interest":[48],"in":[49],"seismic":[50,98],"computing.":[51],"For":[52],"larger":[54],"stencils,":[55],"described":[57],"approach":[58],"achieves":[59],"throughput":[61],"between":[63],"2,400":[64],"over":[66],"3,000":[67],"million":[68],"output":[70],"points":[71],"per":[72],"second":[73],"on":[74],"single":[76],"Tesla":[77],"10-series":[78],"GPU.":[79],"This":[80],"roughly":[82],"an":[83],"order":[84],"magnitude":[86],"higher":[87],"than":[88],"4-core":[90],"Harpertown":[91],"CPU":[92],"running":[93],"similar":[95],"code":[96],"from":[97],"industry.":[99],"Multi-GPU":[100],"also":[103],"described,":[104],"achieving":[105],"linear":[106],"scaling":[107],"with":[108,114],"GPUs":[109],"by":[110],"overlapping":[111],"inter-GPU":[112],"communication":[113],"computation.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":24},{"year":2017,"cited_by_count":27},{"year":2016,"cited_by_count":33},{"year":2015,"cited_by_count":42},{"year":2014,"cited_by_count":62},{"year":2013,"cited_by_count":54},{"year":2012,"cited_by_count":50}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}