{"id":"https://openalex.org/W2002510097","doi":"https://doi.org/10.1145/2688500.2688537","title":"A collection-oriented programming model for performance portability","display_name":"A collection-oriented programming model for performance portability","publication_year":2015,"publication_date":"2015-01-24","ids":{"openalex":"https://openalex.org/W2002510097","doi":"https://doi.org/10.1145/2688500.2688537","mag":"2002510097"},"language":"en","primary_location":{"id":"doi:10.1145/2688500.2688537","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2688500.2688537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","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/A5033185286","display_name":"Saurav Muralidharan","orcid":"https://orcid.org/0000-0003-4024-3958"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Saurav Muralidharan","raw_affiliation_strings":["University of Utah, USA"],"affiliations":[{"raw_affiliation_string":"University of Utah, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024606205","display_name":"Michael Garland","orcid":"https://orcid.org/0000-0001-6093-7602"},"institutions":[{"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"]},{"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"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Michael Garland","raw_affiliation_strings":["NVIDIA, USA","[NVIDIA, USA]"],"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"[NVIDIA, USA]","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066242985","display_name":"Bryan Catanzaro","orcid":"https://orcid.org/0000-0003-0034-7728"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bryan Catanzaro","raw_affiliation_strings":["Baidu, USA"],"affiliations":[{"raw_affiliation_string":"Baidu, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004915198","display_name":"Albert Sidelnik","orcid":null},"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":false,"raw_author_name":"Albert Sidelnik","raw_affiliation_strings":["NVIDIA, USA","[NVIDIA, USA]"],"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"[NVIDIA, USA]","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030152493","display_name":"Mary Hall","orcid":"https://orcid.org/0000-0002-3058-7573"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary Hall","raw_affiliation_strings":["University of Utah, USA"],"affiliations":[{"raw_affiliation_string":"University of Utah, USA","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5033185286"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":0.9689,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75362711,"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":"263","last_page":"264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10126","display_name":"Logic, programming, and type systems","score":0.9983999729156494,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9887999892234802,"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":0.8625538349151611},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8367388844490051},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.8062882423400879},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6711077690124512},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6638953685760498},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6276555061340332},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.555557906627655},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.500751256942749},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4942522346973419},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4674704074859619},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.4598250687122345},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.45151543617248535},{"id":"https://openalex.org/keywords/toolchain","display_name":"Toolchain","score":0.4169508218765259},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.292844295501709},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.19665107131004333},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1535290777683258}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8625538349151611},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8367388844490051},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.8062882423400879},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6711077690124512},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6638953685760498},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6276555061340332},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.555557906627655},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.500751256942749},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4942522346973419},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4674704074859619},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.4598250687122345},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.45151543617248535},{"id":"https://openalex.org/C2777062904","wikidata":"https://www.wikidata.org/wiki/Q545406","display_name":"Toolchain","level":3,"score":0.4169508218765259},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.292844295501709},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.19665107131004333},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1535290777683258},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2688500.2688537","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2688500.2688537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1583210003","https://openalex.org/W2128853364","https://openalex.org/W2138163628"],"related_works":["https://openalex.org/W2013037783","https://openalex.org/W2909413202","https://openalex.org/W3020739840","https://openalex.org/W2913998709","https://openalex.org/W4386875822","https://openalex.org/W3177128669","https://openalex.org/W2111416043","https://openalex.org/W2460870572","https://openalex.org/W4243399827","https://openalex.org/W4236300446"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"Surge,":[3],"a":[4,24,72],"collection-oriented":[5],"programming":[6],"model":[7],"that":[8,33,75],"enables":[9,34],"programmers":[10,35,63],"to":[11,38,119],"compose":[12],"parallel":[13,49],"computations":[14,59],"using":[15],"nested":[16],"high-level":[17],"data":[18],"collections":[19],"and":[20,36,55,70,78,96,99,107],"operators.":[21],"Surge":[22,86,111],"exposes":[23],"code":[25,115],"generation":[26],"interface,":[27],"decoupled":[28],"from":[29,60,90,100],"the":[30,44,101],"core":[31],"computation,":[32],"autotuners":[37],"easily":[39],"generate":[40,71,105],"multiple":[41,66],"implementations":[42],"of":[43],"same":[45,102],"computation":[46],"on":[47],"various":[48],"architectures":[50,67],"such":[51,92],"as":[52,93],"multi-core":[53],"CPUs":[54],"GPUs.":[56],"By":[57],"decoupling":[58],"architecture-specific":[61],"implementation,":[62],"can":[64],"target":[65],"more":[68],"easily,":[69],"search":[73],"space":[74],"facilitates":[76],"optimization":[77],"customization":[79],"for":[80],"specific":[81],"architectures.":[82],"We":[83],"express":[84],"in":[85],"four":[87],"real-world":[88],"benchmarks":[89],"domains":[91],"sparse":[94],"linear-algebra":[95],"machine":[97],"learning":[98],"performance-portable":[103],"specification,":[104],"OpenMP":[106],"CUDA":[108,125],"C++":[109],"implementations.":[110],"generates":[112],"efficient,":[113],"scalable":[114],"which":[116],"achieves":[117],"up":[118],"1.32x":[120],"speedup":[121],"over":[122],"handcrafted,":[123],"well-optimized":[124],"code.":[126]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}