{"id":"https://openalex.org/W2016939324","doi":"https://doi.org/10.1109/mm.2008.57","title":"Parallel Computing Experiences with CUDA","display_name":"Parallel Computing Experiences with CUDA","publication_year":2008,"publication_date":"2008-07-01","ids":{"openalex":"https://openalex.org/W2016939324","doi":"https://doi.org/10.1109/mm.2008.57","mag":"2016939324"},"language":"en","primary_location":{"id":"doi:10.1109/mm.2008.57","doi":"https://doi.org/10.1109/mm.2008.57","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2008.57","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-a","jufo-3","norway-2","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Micro","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5024606205","display_name":"Michael Garland","orcid":"https://orcid.org/0000-0001-6093-7602","observed_orcids":["https://orcid.org/0000-0001-6093-7602"]},"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":false,"raw_author_name":"Michael Garland","raw_affiliation_strings":["NVIDIA, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063252571","display_name":"Scott LeGrand","orcid":null,"observed_orcids":[]},"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":false,"raw_author_name":"Scott Le Grand","raw_affiliation_strings":["CUDA software team, NVIDIA","NVIDIA, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUDA software team, NVIDIA","institution_ids":[]},{"raw_affiliation_string":"NVIDIA, Santa Clara, CA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043819494","display_name":"John R. Nickolls","orcid":null,"observed_orcids":[]},"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":false,"raw_author_name":"John Nickolls","raw_affiliation_strings":["GPU computing, NVIDIA","NVIDIA, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GPU computing, NVIDIA","institution_ids":[]},{"raw_affiliation_string":"NVIDIA, Santa Clara, CA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111685523","display_name":"Joshua A. Anderson","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]},{"id":"https://openalex.org/I2802789608","display_name":"Ames National Laboratory","ror":"https://ror.org/041m9xr71","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I173911158","https://openalex.org/I2802789608","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua Anderson","raw_affiliation_strings":["Iowa State University and Ames Laboratory","Iowa State University and Ames Laboratory#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University and Ames Laboratory","institution_ids":["https://openalex.org/I173911158","https://openalex.org/I2802789608"]},{"raw_affiliation_string":"Iowa State University and Ames Laboratory#TAB#","institution_ids":["https://openalex.org/I173911158","https://openalex.org/I2802789608"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113575030","display_name":"Jim Hardwick","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210166369","display_name":"TechniScan (United States)","ror":"https://ror.org/05xpxan20","country_code":"US","type":"company","lineage":["https://openalex.org/I4210166369"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jim Hardwick","raw_affiliation_strings":["TechniScan Medical Systems, Salt Lake","TechniScan Medical Systems"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TechniScan Medical Systems, Salt Lake","institution_ids":["https://openalex.org/I4210166369"]},{"raw_affiliation_string":"TechniScan Medical Systems","institution_ids":["https://openalex.org/I4210166369"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Scott Morton","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16718484","display_name":"Hess (United States)","ror":"https://ror.org/00zbk1w77","country_code":"US","type":"company","lineage":["https://openalex.org/I16718484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Morton","raw_affiliation_strings":["Geophysical technology group, Hess Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Geophysical technology group, Hess Corporation","institution_ids":["https://openalex.org/I16718484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006141934","display_name":"Everett H. Phillips","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16718484","display_name":"Hess (United States)","ror":"https://ror.org/00zbk1w77","country_code":"US","type":"company","lineage":["https://openalex.org/I16718484"]},{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Everett Phillips","raw_affiliation_strings":["Geophysical technology group, Hess Corporation","university of california, davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Geophysical technology group, Hess Corporation","institution_ids":["https://openalex.org/I16718484"]},{"raw_affiliation_string":"university of california, davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100447001","display_name":"Yao Zhang","orcid":"https://orcid.org/0000-0003-0546-8131","observed_orcids":["https://orcid.org/0000-0003-0546-8131"]},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yao Zhang","raw_affiliation_strings":["Mechanical and aeronautical engineering and electrical and computer engineering","university of california, davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mechanical and aeronautical engineering and electrical and computer engineering","institution_ids":[]},{"raw_affiliation_string":"university of california, davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041898226","display_name":"Vasily Volkov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1336915759","display_name":"Gangwon Provincial University","ror":"https://ror.org/006fs1j92","country_code":"KR","type":"education","lineage":["https://openalex.org/I1336915759"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Vasily Volkov","raw_affiliation_strings":["GPU","University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GPU","institution_ids":["https://openalex.org/I1336915759"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2995,"currency":"USD","value_usd":2995},"apc_paid":null,"fwci":44.5944,"has_fulltext":false,"cited_by_count":573,"citation_normalized_percentile":{"value":0.99824845,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"28","issue":"4","first_page":"13","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.0003000000142492354,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/cuda","display_name":"CUDA","score":0.9739999771118164},{"id":"https://openalex.org/keywords/gpu-computing","display_name":"GPU computing","score":0.875},{"id":"https://openalex.org/keywords/massively-parallel-processing","display_name":"massively parallel computing","score":0.703000009059906},{"id":"https://openalex.org/keywords/parallel-speedup","display_name":"parallel speedup","score":0.8579999804496765},{"id":"https://openalex.org/keywords/cpu-vs-gpu-performance-comparison","display_name":"CPU vs GPU performance comparison","score":0.6190000176429749},{"id":"https://openalex.org/keywords/parallel-programming-models","display_name":"parallel programming models","score":0.6420000195503235}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9437596201896667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8822192549705505},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8308573961257935},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.7360599637031555},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.55440354347229},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5542652606964111},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.5187216401100159},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46518415212631226},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.39796561002731323},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.37474846839904785},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15227237343788147},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.14014926552772522},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10385817289352417},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10149124264717102}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/mm.2008.57","doi":"https://doi.org/10.1109/mm.2008.57","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2008.57","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-a","jufo-3","norway-2","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Micro","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.171.339","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.171.339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://grothoff.org/christian/teaching/2008/4704/ParallelComputingExperienceswithCUDA.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.182.2863","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.182.2863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cecm.sfu.ca/CAG/papers/CUDA.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1898130445","https://openalex.org/W1971321752","https://openalex.org/W1992851788","https://openalex.org/W2011652244","https://openalex.org/W2013173369","https://openalex.org/W2019465613","https://openalex.org/W2025254819","https://openalex.org/W2027829941","https://openalex.org/W2028499920","https://openalex.org/W2035720425","https://openalex.org/W2050277572","https://openalex.org/W2078391824","https://openalex.org/W2116917057","https://openalex.org/W2155503253","https://openalex.org/W2159350554","https://openalex.org/W2159497832","https://openalex.org/W2166621589","https://openalex.org/W2187691968","https://openalex.org/W2620440553","https://openalex.org/W2885483166","https://openalex.org/W2997230959","https://openalex.org/W3013265033","https://openalex.org/W3138798301","https://openalex.org/W6738640236"],"related_works":["https://openalex.org/W7097347073","https://openalex.org/W2389600408","https://openalex.org/W2131324202","https://openalex.org/W7097955417","https://openalex.org/W7023753343","https://openalex.org/W2028499920","https://openalex.org/W177985515","https://openalex.org/W2128022558","https://openalex.org/W2341833987","https://openalex.org/W7030038367"],"abstract_inverted_index":{"The":[0],"CUDA":[1,33],"programming":[2],"model":[3],"provides":[4],"a":[5,35],"straightforward":[6],"means":[7],"of":[8,38],"describing":[9],"inherently":[10],"parallel":[11,24,42],"computations,":[12],"and":[13,40],"NVIDIA's":[14],"Tesla":[15],"GPU":[16],"architecture":[17],"delivers":[18],"high":[19],"computational":[20],"throughput":[21],"on":[22,48,57],"massively":[23],"problems.":[25],"This":[26],"article":[27],"surveys":[28],"experiences":[29],"gained":[30],"in":[31],"applying":[32],"to":[34],"diverse":[36],"set":[37],"problems":[39],"the":[41,58],"speedups":[43],"over":[44],"sequential":[45],"codes":[46],"running":[47],"traditional":[49],"CPU":[50],"architectures":[51],"attained":[52],"by":[53],"executing":[54],"key":[55],"computations":[56],"GPU.":[59]},"counts_by_year":[{"year":2026,"cited_by_count":19},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":27},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":25},{"year":2017,"cited_by_count":21},{"year":2016,"cited_by_count":25},{"year":2015,"cited_by_count":28},{"year":2014,"cited_by_count":45},{"year":2013,"cited_by_count":68},{"year":2012,"cited_by_count":45}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2016-06-24T00:00:00"}