{"id":"https://openalex.org/W2131324202","doi":"https://doi.org/10.1109/ipdps.2010.5470378","title":"Parallel computing with CUDA","display_name":"Parallel computing with CUDA","publication_year":2010,"publication_date":"2010-04-01","ids":{"openalex":"https://openalex.org/W2131324202","doi":"https://doi.org/10.1109/ipdps.2010.5470378","mag":"2131324202"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2010.5470378","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)","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/A5024606205","display_name":"Michael Garland","orcid":"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"]},{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Michael Garland","raw_affiliation_strings":["NVIDIA Corporation, USA","Nvidia"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5024606205"],"corresponding_institution_ids":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":3.7453,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.93861424,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.923799991607666,"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":0.923799991607666,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.9420524835586548},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8701158761978149},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7105588316917419},{"id":"https://openalex.org/keywords/directx","display_name":"DirectX","score":0.6057441234588623},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.5865346193313599},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5071346759796143},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4943721294403076},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4851284921169281},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4329224228858948},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.42842209339141846},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4112207889556885},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1903749704360962}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9420524835586548},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8701158761978149},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7105588316917419},{"id":"https://openalex.org/C544400634","wikidata":"https://www.wikidata.org/wiki/Q188695","display_name":"DirectX","level":2,"score":0.6057441234588623},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.5865346193313599},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5071346759796143},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4943721294403076},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4851284921169281},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4329224228858948},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.42842209339141846},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4112207889556885},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1903749704360962},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2010.5470378","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W1762731526"],"related_works":["https://openalex.org/W2364285279","https://openalex.org/W2361648799","https://openalex.org/W2284500134","https://openalex.org/W6477890","https://openalex.org/W2353085999","https://openalex.org/W2002487373","https://openalex.org/W2131324202","https://openalex.org/W4236300446","https://openalex.org/W2168921806","https://openalex.org/W4308083742"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2],"given.":[3],"NVIDIA's":[4],"CUDA":[5,28,49,95,120],"architecture":[6,50],"provides":[7],"a":[8,42],"powerful":[9],"platform":[10],"for":[11,20,81,113],"writing":[12],"highly":[13],"parallel":[14,83],"programs.":[15],"By":[16],"providing":[17],"simple":[18],"abstractions":[19],"hierarchical":[21],"thread":[22],"organization,":[23],"memories,":[24],"and":[25,55,62,78,97],"synchronization,":[26],"the":[27,38,89,94,104,119],"programming":[29,46,56,84,90],"model":[30,91],"allows":[31],"programmers":[32],"to":[33],"write":[34],"scalable":[35],"programs":[36],"without":[37],"burden":[39],"of":[40,44,73],"learning":[41],"multitude":[43],"new":[45],"constructs.":[47],"The":[48],"can":[51],"support":[52],"many":[53],"languages":[54],"environments,":[57],"including":[58],"C,":[59],"Fortran,":[60],"OpenCL,":[61],"DirectX":[63],"Compute.":[64],"In":[65],"this":[66,100],"tutorial,":[67],"I":[68,86,108],"will":[69,87,109],"provide":[70],"an":[71],"overview":[72],"modern":[74],"GPU":[75],"processor":[76],"design":[77],"its":[79],"implications":[80],"successful":[82],"models.":[85],"present":[88],"adopted":[92],"by":[93],"architecture,":[96],"demonstrate":[98],"how":[99],"is":[101],"exposed":[102],"in":[103,118],"C/C++":[105],"language.":[106],"Finally,":[107],"sketch":[110],"some":[111],"techniques":[112],"implementing":[114],"common":[115],"data-parallel":[116],"algorithms":[117],"model.":[121]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}