{"id":"https://openalex.org/W2034832188","doi":"https://doi.org/10.1109/pdp.2013.61","title":"ELMO: A User-Friendly API to Enable Local Memory in OpenCL Kernels","display_name":"ELMO: A User-Friendly API to Enable Local Memory in OpenCL Kernels","publication_year":2013,"publication_date":"2013-02-01","ids":{"openalex":"https://openalex.org/W2034832188","doi":"https://doi.org/10.1109/pdp.2013.61","mag":"2034832188"},"language":"en","primary_location":{"id":"doi:10.1109/pdp.2013.61","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pdp.2013.61","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 21st Euromicro International Conference on Parallel, Distributed, and Network-Based Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/3434270","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083171604","display_name":"Jianbin Fang","orcid":"https://orcid.org/0000-0003-3542-4869"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jianbin Fang","raw_affiliation_strings":["Parallel and Distributed Systems Group, Delft University of Technology, Delft, Netherlands","Parallel & Distrib. Syst. Group, Delft Univ. of Technol., Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Parallel and Distributed Systems Group, Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Parallel & Distrib. Syst. Group, Delft Univ. of Technol., Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109847155","display_name":"Ana Lucia V\u0103rb\u0103nescu","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"A. L. Varbanescu","raw_affiliation_strings":["Parallel and Distributed Systems Group, Delft University of Technology, Delft, Netherlands","Parallel & Distrib. Syst. Group, Delft Univ. of Technol., Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Parallel and Distributed Systems Group, Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Parallel & Distrib. Syst. Group, Delft Univ. of Technol., Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101642102","display_name":"Jie Shen","orcid":"https://orcid.org/0000-0003-4247-7029"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jie Shen","raw_affiliation_strings":["Parallel and Distributed Systems Group, Delft University of Technology, Delft, Netherlands","Parallel & Distrib. Syst. Group, Delft Univ. of Technol., Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Parallel and Distributed Systems Group, Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Parallel & Distrib. Syst. Group, Delft Univ. of Technol., Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034054372","display_name":"Henk Sips","orcid":"https://orcid.org/0000-0001-8261-9170"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"H. Sips","raw_affiliation_strings":["Parallel and Distributed Systems Group, Delft University of Technology, Delft, Netherlands","Parallel & Distrib. Syst. Group, Delft Univ. of Technol., Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Parallel and Distributed Systems Group, Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Parallel & Distrib. Syst. Group, Delft Univ. of Technol., Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":0.8966,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.71201768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"375","last_page":"383"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9934999942779541,"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":0.891029953956604},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7426740527153015},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.7322273254394531},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.673923671245575},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.5607450604438782},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.48846927285194397},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4510280191898346},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.42586031556129456},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.38562726974487305},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2015289068222046},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.09970715641975403},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.06821033358573914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.891029953956604},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7426740527153015},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.7322273254394531},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.673923671245575},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.5607450604438782},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48846927285194397},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4510280191898346},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.42586031556129456},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.38562726974487305},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2015289068222046},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.09970715641975403},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.06821033358573914},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/pdp.2013.61","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pdp.2013.61","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 21st Euromicro International Conference on Parallel, Distributed, and Network-Based Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:3434270","is_oa":true,"landing_page_url":"https://zenodo.org/record/3434270","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:3434270","is_oa":true,"landing_page_url":"https://zenodo.org/record/3434270","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1993385165","https://openalex.org/W1998351670","https://openalex.org/W2028798345","https://openalex.org/W2049875313","https://openalex.org/W2104974755","https://openalex.org/W2113873920","https://openalex.org/W2116963870","https://openalex.org/W2119547137","https://openalex.org/W2129232868","https://openalex.org/W2157828735","https://openalex.org/W2164106630","https://openalex.org/W3147336131","https://openalex.org/W4237977381","https://openalex.org/W6677067475","https://openalex.org/W6678107477"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2953205341","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W1500978221"],"abstract_inverted_index":{"Recent":[0],"parallel":[1],"architectures":[2],"are":[3],"equipped":[4],"with":[5,114],"local":[6,44,56],"memory,":[7],"which":[8],"simplifies":[9],"hardware":[10],"design":[11],"at":[12],"the":[13,79,95,120],"cost":[14],"of":[15,43,116],"increased":[16],"program":[17],"complexity":[18],"due":[19],"to":[20,72,101],"explicit":[21],"management.":[22],"To":[23],"simplify":[24],"this":[25],"extra-burden":[26],"that":[27,36,53,84,115],"programmers":[28],"have,":[29],"we":[30,106],"introduce":[31],"an":[32],"easy-to-use":[33],"API,":[34],"ELMO,":[35],"improves":[37],"productivity":[38],"while":[39,119],"preserving":[40],"high":[41],"performance":[42,85,109],"memory":[45,57],"operations.":[46],"Specifically,":[47],"ELMO":[48,91,105],"is":[49,86,122],"a":[50],"generic":[51],"API":[52],"covers":[54],"different":[55],"use-cases.":[58],"We":[59],"also":[60],"present":[61],"prototype":[62],"implementations":[63],"for":[64],"these":[65],"APIs":[66],"and":[67,125],"perform":[68],"multiple":[69],"GPU-inspired":[70],"optimizations":[71],"maximize":[73],"their":[74],"performance.":[75],"Experimental":[76],"results":[77],"on":[78,92],"NVIDIA":[80],"Quadro5000":[81],"GPU":[82],"show":[83],"significantly":[87],"improved":[88],"by":[89],"using":[90,104],"native":[93],"implementations:":[94],"achieved":[96],"speedup":[97],"ranges":[98],"from":[99],"1.3x":[100],"3.7x.":[102],"Furthermore,":[103],"still":[107],"achieve":[108],"comparable":[110],"(if":[111],"not":[112],"better)":[113],"hand-tuned":[117],"applications,":[118],"code":[121],"shorter,":[123],"clearer,":[124],"safer.":[126]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2016-06-24T00:00:00"}
