{"id":"https://openalex.org/W2641213828","doi":"https://doi.org/10.1145/2578948.2560692","title":"Reduction Operations in Parallel Loops for GPGPUs","display_name":"Reduction Operations in Parallel Loops for GPGPUs","publication_year":2014,"publication_date":"2014-02-07","ids":{"openalex":"https://openalex.org/W2641213828","doi":"https://doi.org/10.1145/2578948.2560692","mag":"2641213828"},"language":"en","primary_location":{"id":"doi:10.1145/2578948.2560692","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2578948.2560692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of Programming Models and Applications on Multicores and Manycores","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/A5083192531","display_name":"Rengan Xu","orcid":"https://orcid.org/0000-0002-5230-5530"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rengan Xu","raw_affiliation_strings":["Dept. of Computer Science, University of Houston, Houston, TX, 77004, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, University of Houston, Houston, TX, 77004, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051505683","display_name":"Xiaonan Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaonan Tian","raw_affiliation_strings":["Dept. of Computer Science, University of Houston, Houston, TX, 77004, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, University of Houston, Houston, TX, 77004, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102715061","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0002-5274-8526"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonghong Yan","raw_affiliation_strings":["Dept. of Computer Science, University of Houston, Houston, TX, 77004, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, University of Houston, Houston, TX, 77004, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009614578","display_name":"Sunita Chandrasekaran","orcid":"https://orcid.org/0000-0002-3560-9428"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sunita Chandrasekaran","raw_affiliation_strings":["Dept. of Computer Science, University of Houston, Houston, TX, 77004, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, University of Houston, Houston, TX, 77004, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053733660","display_name":"Barbara Chapman","orcid":"https://orcid.org/0000-0001-8449-8579"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barbara Chapman","raw_affiliation_strings":["Dept. of Computer Science, University of Houston, Houston, TX, 77004, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, University of Houston, Houston, TX, 77004, USA","institution_ids":["https://openalex.org/I44461941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I44461941"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9973000288009644,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9965999722480774,"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":0.8681395649909973},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.754422664642334},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6676468253135681},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.5404906868934631},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5329787731170654},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.4953536093235016},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4793435037136078},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41235822439193726},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.366686075925827},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2659263014793396},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.1271287202835083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8681395649909973},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.754422664642334},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6676468253135681},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.5404906868934631},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5329787731170654},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.4953536093235016},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4793435037136078},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41235822439193726},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.366686075925827},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2659263014793396},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.1271287202835083},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2578948.2560692","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2578948.2560692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of Programming Models and Applications on Multicores and Manycores","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":5,"referenced_works":["https://openalex.org/W122980706","https://openalex.org/W144747564","https://openalex.org/W1556574299","https://openalex.org/W1969917186","https://openalex.org/W1972906829"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W2023572661","https://openalex.org/W4245975140","https://openalex.org/W2532592438","https://openalex.org/W1977763331","https://openalex.org/W2062253548","https://openalex.org/W4225414539","https://openalex.org/W4236300446"],"abstract_inverted_index":{"Manycore":[0],"accelerators":[1,41],"offer":[2],"the":[3,8,21,57,80,95,98,107],"potential":[4],"of":[5,10,18,45,56,97],"significantly":[6],"improving":[7],"performance":[9,108],"scientific":[11],"applications":[12,39],"when":[13],"offloading":[14,48],"compute":[15],"intensive":[16],"portions":[17],"programs":[19],"to":[20,37],"accelerators.":[22],"Directive-based":[23],"programming":[24,33,53],"models":[25],"such":[26],"as":[27],"OpenACC":[28],"and":[29,70],"OpenMP":[30],"are":[31,60,77],"high-level":[32],"model":[34],"for":[35,40,47,84],"users":[36],"create":[38],"by":[42],"annotating":[43],"region":[44],"code":[46],"with":[49],"directives.":[50],"In":[51],"these":[52],"models,":[54],"most":[55],"offloaded":[58],"kernels":[59],"data":[61],"parallel":[62,81],"loops":[63],"processing":[64],"one":[65],"or":[66],"multiple":[67],"multi-dimensional":[68],"arrays,":[69],"it":[71],"is":[72],"often":[73],"that":[74],"scalar":[75],"variables":[76],"used":[78],"in":[79],"loop":[82],"body":[83],"reduction":[85,88],"operations.":[86],"Since":[87],"operation":[89],"itself":[90],"has":[91],"loop-carried":[92],"dependency":[93],"preventing":[94],"parallelization":[96],"loops,":[99],"this":[100],"could":[101],"have":[102],"a":[103],"significant":[104],"impact":[105],"on":[106],"if":[109],"not":[110],"handled":[111],"properly.":[112]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}