{"id":"https://openalex.org/W1976979937","doi":"https://doi.org/10.1109/ipdpsw.2010.5470823","title":"OpenCL - An effective programming model for data parallel computations at the Cell Broadband Engine","display_name":"OpenCL - An effective programming model for data parallel computations at the Cell Broadband Engine","publication_year":2010,"publication_date":"2010-04-01","ids":{"openalex":"https://openalex.org/W1976979937","doi":"https://doi.org/10.1109/ipdpsw.2010.5470823","mag":"1976979937"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw.2010.5470823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2010.5470823","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, Workshops and Phd Forum (IPDPSW)","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/A5058851813","display_name":"Jens Breitbart","orcid":null},"institutions":[{"id":"https://openalex.org/I106157433","display_name":"University of Kassel","ror":"https://ror.org/04zc7p361","country_code":"DE","type":"education","lineage":["https://openalex.org/I106157433"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jens Breitbart","raw_affiliation_strings":["Research Group Programming Languages / Methodologies, Universit\u00e4t Kassel, Germany","[Research Group Programming Languages, Methodologies Universit\u00e4t Kassel, Germany]"],"affiliations":[{"raw_affiliation_string":"Research Group Programming Languages / Methodologies, Universit\u00e4t Kassel, Germany","institution_ids":["https://openalex.org/I106157433"]},{"raw_affiliation_string":"[Research Group Programming Languages, Methodologies Universit\u00e4t Kassel, Germany]","institution_ids":["https://openalex.org/I106157433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045882588","display_name":"Claudia Fohry","orcid":null},"institutions":[{"id":"https://openalex.org/I106157433","display_name":"University of Kassel","ror":"https://ror.org/04zc7p361","country_code":"DE","type":"education","lineage":["https://openalex.org/I106157433"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Claudia Fohry","raw_affiliation_strings":["Research Group Programming Languages / Methodologies, Universit\u00e4t Kassel, Germany","[Research Group Programming Languages, Methodologies Universit\u00e4t Kassel, Germany]"],"affiliations":[{"raw_affiliation_string":"Research Group Programming Languages / Methodologies, Universit\u00e4t Kassel, Germany","institution_ids":["https://openalex.org/I106157433"]},{"raw_affiliation_string":"[Research Group Programming Languages, Methodologies Universit\u00e4t Kassel, Germany]","institution_ids":["https://openalex.org/I106157433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5058851813"],"corresponding_institution_ids":["https://openalex.org/I106157433"],"apc_list":null,"apc_paid":null,"fwci":2.4969,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.89775465,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9972000122070312,"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":0.8919509649276733},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.7716119885444641},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.700202226638794},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5713240504264832},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5520317554473877},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5235081315040588},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.495084673166275},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.46532413363456726},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.447682648897171},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4374787211418152},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2398066222667694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8919509649276733},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.7716119885444641},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.700202226638794},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5713240504264832},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5520317554473877},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5235081315040588},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.495084673166275},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.46532413363456726},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.447682648897171},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4374787211418152},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2398066222667694},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdpsw.2010.5470823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2010.5470823","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, Workshops and Phd Forum (IPDPSW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1553908659","https://openalex.org/W2098246017","https://openalex.org/W2117927105","https://openalex.org/W2507749557","https://openalex.org/W6677796095","https://openalex.org/W6724916924"],"related_works":["https://openalex.org/W3020739840","https://openalex.org/W4386875822","https://openalex.org/W3177128669","https://openalex.org/W2122078011","https://openalex.org/W4385574943","https://openalex.org/W2323476605","https://openalex.org/W3197664880","https://openalex.org/W2392023973","https://openalex.org/W2111416043","https://openalex.org/W2066709512"],"abstract_inverted_index":{"Current":[0],"processor":[1],"architectures":[2],"are":[3],"diverse":[4],"and":[5,12,28,59,74,91],"heterogeneous.":[6],"Examples":[7],"include":[8],"multicore":[9],"chips,":[10],"CPUs":[11],"the":[13,38,60,64,78,98,101,110,122,160,167,171,178],"Cell":[14],"Broadband":[15],"Engine":[16],"(CBE).":[17],"The":[18],"recent":[19],"Open":[20],"Compute":[21],"Language":[22],"(OpenCL)":[23],"standard":[24],"aims":[25],"at":[26],"efficiency":[27,34],"portability.":[29],"This":[30],"paper":[31,123],"explores":[32],"its":[33],"when":[35],"implemented":[36],"on":[37,54,97],"CBE,":[39],"without":[40],"using":[41],"CBE-specific":[42],"features":[43],"such":[44,148],"as":[45,113,149],"explicit":[46],"asynchronous":[47],"memory":[48,130],"transfers.":[49],"We":[50],"based":[51],"our":[52,104],"experiments":[53],"two":[55,157],"applications:":[56],"matrix":[57,81],"multiplication,":[58,82],"client":[61],"side":[62],"of":[63,87,121,159,170,180],"Einstein@Home":[65,102],"distributed":[66],"computing":[67],"project.":[68],"Both":[69],"were":[70],"programmed":[71],"in":[72,132,165],"OpenCL,":[73,133],"then":[75],"translated":[76,105],"to":[77,145,162],"CBE.":[79,99],"For":[80,100],"we":[83,155],"deployed":[84],"different":[85],"levels":[86],"OpenCL":[88,106,161],"performance":[89],"optimization,":[90],"observed":[92],"that":[93],"they":[94],"pay":[95],"off":[96],"application,":[103],"version":[107],"achieves":[108],"almost":[109],"same":[111],"speed":[112],"a":[114,125,181],"native":[115],"CBE":[116,163,172],"version.":[117],"Another":[118],"main":[119],"contribution":[120],"is":[124],"proposal":[126],"for":[127,152],"an":[128],"additional":[129],"level":[131],"called":[134],"static":[135],"local":[136],"memory.":[137],"With":[138],"little":[139],"programming":[140],"expense,":[141],"it":[142],"can":[143],"lead":[144],"significant":[146],"speedups":[147],"factor":[150],"seven":[151],"reduction.":[153],"Finally,":[154],"studied":[156],"versions":[158],"mapping,":[164],"which":[166],"PPE":[168],"component":[169],"does":[173,175],"or":[174],"not":[176],"take":[177],"role":[179],"compute":[182],"unit.":[183]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}