{"id":"https://openalex.org/W2393490604","doi":null,"title":"Research and Implementation of Performance Analysis Tool for CUDA Programs with Directive","display_name":"Research and Implementation of Performance Analysis Tool for CUDA Programs with Directive","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2393490604","mag":"2393490604"},"language":"en","primary_location":{"id":"mag:2393490604","doi":null,"is_oa":false,"landing_page_url":"https://en.cnki.com.cn/Article_en/CJFDTOTAL-DKDX201202023.htm","pdf_url":null,"source":{"id":"https://openalex.org/S2764615551","display_name":"Dianzi Ke-ji Daxue xuebao","issn_l":"1001-0548","issn":["1001-0548"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","poland-20","russia-white-list-4"],"host_organization":"https://openalex.org/P4310311921","host_organization_name":"University of Electronic Science and Technology of China","host_organization_lineage":["https://openalex.org/P4310311921"],"host_organization_lineage_names":["University of Electronic Science and Technology of China"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Dianzi Ke-ji Daxue xuebao","raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5027288740","display_name":"Lu Chuan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lu Chuan","raw_affiliation_strings":["and ZHANG Lei"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"and ZHANG Lei","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5027288740"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34783028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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":0.00039999998989515007,"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":0.9399999976158142},{"id":"https://openalex.org/keywords/gpu-performance-analysis","display_name":"GPU performance analysis","score":0.7310000061988831},{"id":"https://openalex.org/keywords/gpu-architecture","display_name":"GPU architecture","score":0.609000027179718},{"id":"https://openalex.org/keywords/parallel-program-performance-analysis","display_name":"parallel program performance analysis","score":0.7760000228881836},{"id":"https://openalex.org/keywords/gpu-computing","display_name":"GPU computing","score":0.609000027179718},{"id":"https://openalex.org/keywords/high-performance-computing","display_name":"high-performance computing","score":0.7609999775886536}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9667170643806458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.848278284072876},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.7610013484954834},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.669303834438324},{"id":"https://openalex.org/C2779547435","wikidata":"https://www.wikidata.org/wiki/Q1121492","display_name":"Directive","level":2,"score":0.6207531690597534},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5946427583694458},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.539191722869873},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4932669997215271},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4832518696784973},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.46273621916770935},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.46163129806518555},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.45410996675491333},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3511354923248291},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.30179834365844727},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06043252348899841},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2393490604","doi":null,"is_oa":false,"landing_page_url":"https://en.cnki.com.cn/Article_en/CJFDTOTAL-DKDX201202023.htm","pdf_url":null,"source":{"id":"https://openalex.org/S2764615551","display_name":"Dianzi Ke-ji Daxue xuebao","issn_l":"1001-0548","issn":["1001-0548"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","poland-20","russia-white-list-4"],"host_organization":"https://openalex.org/P4310311921","host_organization_name":"University of Electronic Science and Technology of China","host_organization_lineage":["https://openalex.org/P4310311921"],"host_organization_lineage_names":["University of Electronic Science and Technology of China"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Dianzi Ke-ji Daxue xuebao","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2265958892","https://openalex.org/W4390187649","https://openalex.org/W2105545110","https://openalex.org/W1909392418","https://openalex.org/W2087731213","https://openalex.org/W7100096486","https://openalex.org/W2403688781","https://openalex.org/W2559570907","https://openalex.org/W2389600408","https://openalex.org/W4247309590"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,the":[2],"rapid":[3],"expansion":[4],"of":[5,25,30,47,73],"graphics":[6],"processing":[7],"unit(GPU)":[8],"as":[9,11],"well":[10],"the":[12,23,28,45,71],"computer":[13],"unified":[14],"device":[15],"architecture(CUDA)":[16],"technology":[17],"proposed":[18],"by":[19],"NVIDIA":[20],"pushes":[21],"forward":[22],"application":[24],"GPU":[26,80],"in":[27,52],"field":[29],"high":[31],"performance":[32,50,56,75],"computing(HPC).In":[33],"this":[34,74],"paper,GPU\u2019s":[35],"architecture":[36],"and":[37,67],"CUDA":[38,60],"programming":[39],"model":[40],"are":[41],"introduced":[42],"first.According":[43],"to":[44],"method":[46],"parallel":[48],"program":[49],"analysis":[51,57,76],"CPU":[53],"cluster":[54],"mode,a":[55],"tool":[58,77],"for":[59],"programs":[61],"based":[62],"on":[63,78],"directive":[64],"is":[65],"designed":[66],"implemented.Experiment":[68],"results":[69],"validate":[70],"validity":[72],"different":[79],"hardware":[81],"platforms.":[82]},"counts_by_year":[],"updated_date":"2025-10-10T17:16:08.811792","created_date":"2016-06-24T00:00:00"}