{"id":"https://openalex.org/W2016909619","doi":"https://doi.org/10.1109/hpcsim.2012.6266884","title":"High performance computing and simulations on the GPU using CUDA","display_name":"High performance computing and simulations on the GPU using CUDA","publication_year":2012,"publication_date":"2012-07-01","ids":{"openalex":"https://openalex.org/W2016909619","doi":"https://doi.org/10.1109/hpcsim.2012.6266884","mag":"2016909619"},"language":"en","primary_location":{"id":"doi:10.1109/hpcsim.2012.6266884","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2012.6266884","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Conference on High Performance Computing & Simulation (HPCS)","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/A5001884113","display_name":"Manuel Ujald\u00f3n","orcid":"https://orcid.org/0000-0002-4656-6400"},"institutions":[{"id":"https://openalex.org/I82767444","display_name":"Universidad de M\u00e1laga","ror":"https://ror.org/036b2ww28","country_code":"ES","type":"education","lineage":["https://openalex.org/I82767444"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Manuel Ujaldon","raw_affiliation_strings":["Computer Architecture Department, University of Malaga, Spain","[Computer Architecture Department, University of Malaga, Spain]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Architecture Department, University of Malaga, Spain","institution_ids":["https://openalex.org/I82767444"]},{"raw_affiliation_string":"[Computer Architecture Department, University of Malaga, Spain]","institution_ids":["https://openalex.org/I82767444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5001884113"],"corresponding_institution_ids":["https://openalex.org/I82767444"],"apc_list":null,"apc_paid":null,"fwci":0.3783,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.49760123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9986000061035156,"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":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.8665933609008789},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7652726173400879},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7392919659614563},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.7122212052345276},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5959757566452026},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.5469777584075928},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5184935331344604},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.492216020822525},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4665178060531616},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.43489742279052734},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.411954790353775},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20729073882102966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8665933609008789},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7652726173400879},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7392919659614563},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.7122212052345276},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5959757566452026},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.5469777584075928},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5184935331344604},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.492216020822525},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4665178060531616},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.43489742279052734},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.411954790353775},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20729073882102966},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcsim.2012.6266884","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2012.6266884","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Conference on High Performance Computing & Simulation (HPCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1246293132","https://openalex.org/W1965327223","https://openalex.org/W2130737320","https://openalex.org/W6641487369"],"related_works":["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","https://openalex.org/W2792081825"],"abstract_inverted_index":{"The":[0],"computational":[1],"power":[2],"and":[3,53,76],"memory":[4,78],"bandwidth":[5,79],"of":[6,34,46,50],"graphics":[7],"processing":[8],"units":[9],"(GPUs)":[10],"have":[11],"turned":[12],"them":[13],"into":[14],"attractive":[15],"platforms":[16],"for":[17,99],"general-purpose":[18,100],"applications":[19],"at":[20],"significant":[21],"speed":[22],"gains":[23],"versus":[24],"their":[25],"CPU":[26],"counterparts":[27],"[1].":[28],"In":[29,55],"addition,":[30],"an":[31,60,67,95],"increasing":[32],"number":[33],"today's":[35],"state-of-the-art":[36],"supercomputers":[37],"include":[38],"commodity":[39],"GPUs":[40],"to":[41,62,92],"bring":[42],"us":[43],"unprecedented":[44],"levels":[45],"performance":[47],"in":[48],"terms":[49],"raw":[51],"GFLOPS":[52],"GFLOPS/cost.":[54],"this":[56],"paper,":[57],"we":[58],"provide":[59],"introduction":[61],"CUDA":[63],"programming":[64],"paradigm":[65],"with":[66],"emphasis":[68],"on":[69,80],"simulations":[70],"which":[71],"can":[72],"exploit":[73],"SIMD":[74],"parallelism":[75],"high":[77],"GPUs.":[81],"OpenCL":[82],"is":[83],"also":[84],"briefly":[85],"described":[86],"as":[87],"a":[88],"recent":[89],"standardization":[90],"effort":[91],"set":[93],"up":[94],"open":[96],"standard":[97],"API":[98],"manycore":[101],"architectures.":[102]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}