{"id":"https://openalex.org/W2060321634","doi":"https://doi.org/10.1145/2016604.2016612","title":"Scaling scientific applications on clusters of hybrid multicore/GPU nodes","display_name":"Scaling scientific applications on clusters of hybrid multicore/GPU nodes","publication_year":2011,"publication_date":"2011-05-03","ids":{"openalex":"https://openalex.org/W2060321634","doi":"https://doi.org/10.1145/2016604.2016612","mag":"2060321634"},"language":"en","primary_location":{"id":"doi:10.1145/2016604.2016612","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2016604.2016612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th ACM International Conference on Computing Frontiers","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/A5061009703","display_name":"Lingyuan Wang","orcid":"https://orcid.org/0009-0006-6481-2464"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lingyuan Wang","raw_affiliation_strings":["The George Washington University","the George Washington University"],"affiliations":[{"raw_affiliation_string":"The George Washington University","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"the George Washington University","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069173833","display_name":"Miaoqing Huang","orcid":"https://orcid.org/0000-0001-7376-3744"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miaoqing Huang","raw_affiliation_strings":["University of Arkansas","University Of Arkansas"],"affiliations":[{"raw_affiliation_string":"University of Arkansas","institution_ids":["https://openalex.org/I78715868"]},{"raw_affiliation_string":"University Of Arkansas","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077589337","display_name":"Vikram K. Narayana","orcid":"https://orcid.org/0000-0002-3878-0634"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikram K. Narayana","raw_affiliation_strings":["The George Washington University","the George Washington University"],"affiliations":[{"raw_affiliation_string":"The George Washington University","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"the George Washington University","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001914825","display_name":"Tarek El\u2010Ghazawi","orcid":"https://orcid.org/0000-0001-9687-7939"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tarek El-Ghazawi","raw_affiliation_strings":["The George Washington University","the George Washington University"],"affiliations":[{"raw_affiliation_string":"The George Washington University","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"the George Washington University","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061009703"],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":3.0224,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91820178,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9998999834060669,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8772757053375244},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8137483596801758},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6569938063621521},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.6453646421432495},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.6067662835121155},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5919505953788757},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5914040803909302},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5673079490661621},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.5633411407470703},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5298813581466675},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.46672147512435913},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.454555869102478},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4461890459060669},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4431678354740143},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.42966562509536743},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4219951331615448},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3637397885322571},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19771495461463928}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8772757053375244},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8137483596801758},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6569938063621521},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.6453646421432495},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.6067662835121155},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5919505953788757},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5914040803909302},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5673079490661621},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.5633411407470703},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5298813581466675},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.46672147512435913},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.454555869102478},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4461890459060669},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4431678354740143},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.42966562509536743},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4219951331615448},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3637397885322571},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19771495461463928},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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:10.1145/2016604.2016612","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2016604.2016612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th ACM International Conference on Computing Frontiers","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":15,"referenced_works":["https://openalex.org/W2099084006","https://openalex.org/W2109217687","https://openalex.org/W2111530316","https://openalex.org/W2121444153","https://openalex.org/W2121893797","https://openalex.org/W2122814645","https://openalex.org/W2125473407","https://openalex.org/W2146451305","https://openalex.org/W2148590584","https://openalex.org/W2164120929","https://openalex.org/W2165831368","https://openalex.org/W2167173222","https://openalex.org/W2170634604","https://openalex.org/W2753574770","https://openalex.org/W3187688612"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W2056717482","https://openalex.org/W2030707850","https://openalex.org/W3037515626","https://openalex.org/W4394633758","https://openalex.org/W2502510154","https://openalex.org/W2393490604","https://openalex.org/W2375309128"],"abstract_inverted_index":{"Rapid":[0],"advances":[1],"in":[2,36,43],"the":[3,25,45,54,72],"performance":[4,46],"and":[5,34,66],"programmability":[6],"of":[7,21,31,48],"graphics":[8],"accelerators":[9],"have":[10],"made":[11],"GPU":[12,49,58],"computing":[13],"a":[14,18,29,76],"compelling":[15],"solution":[16],"for":[17],"wide":[19],"variety":[20],"application":[22],"domains.":[23],"However,":[24],"increased":[26],"complexity":[27],"as":[28],"result":[30],"architectural":[32],"heterogeneity":[33],"imbalances":[35],"hardware":[37],"resources":[38],"poses":[39],"significant":[40],"programming":[41,79],"challenges":[42],"harnessing":[44],"advantages":[47],"accelerated":[50],"parallel":[51,78],"systems.":[52],"Moreover,":[53],"speedup":[55],"derived":[56],"from":[57],"often":[59],"gets":[60],"offset":[61],"by":[62],"longer":[63],"communication":[64],"latencies":[65],"inefficient":[67],"task":[68],"scheduling.":[69],"To":[70],"achieve":[71],"best":[73],"possible":[74],"performance,":[75],"suitable":[77],"model":[80],"is":[81],"therefore":[82],"essential.":[83]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}