{"id":"https://openalex.org/W2133741166","doi":"https://doi.org/10.1145/2145816.2145818","title":"Scalable framework for mapping streaming applications onto multi-GPU systems","display_name":"Scalable framework for mapping streaming applications onto multi-GPU systems","publication_year":2012,"publication_date":"2012-02-25","ids":{"openalex":"https://openalex.org/W2133741166","doi":"https://doi.org/10.1145/2145816.2145818","mag":"2133741166"},"language":"en","primary_location":{"id":"doi:10.1145/2145816.2145818","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2145816.2145818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th 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/A5077959628","display_name":"Huynh Phung Huynh","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Huynh Phung Huynh","raw_affiliation_strings":["A*STAR Institute of High Performance Computing, Singapore, Singapore","[A*STAR, Institute of High Performance Computing, Singapore, Singapore]"],"affiliations":[{"raw_affiliation_string":"A*STAR Institute of High Performance Computing, Singapore, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]},{"raw_affiliation_string":"[A*STAR, Institute of High Performance Computing, Singapore, Singapore]","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054042334","display_name":"Andrei Hagiescu","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Andrei Hagiescu","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023989495","display_name":"Weng\u2010Fai Wong","orcid":"https://orcid.org/0000-0002-4281-2053"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weng-Fai Wong","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001599295","display_name":"Rick Siow Mong Goh","orcid":"https://orcid.org/0000-0001-9116-1595"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rick Siow Mong Goh","raw_affiliation_strings":["A*STAR Institute of High Performance Computing, Singapore, Singapore","[A*STAR, Institute of High Performance Computing, Singapore, Singapore]"],"affiliations":[{"raw_affiliation_string":"A*STAR Institute of High Performance Computing, Singapore, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]},{"raw_affiliation_string":"[A*STAR, Institute of High Performance Computing, Singapore, Singapore]","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077959628"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3004594783"],"apc_list":null,"apc_paid":null,"fwci":8.7831,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.98263386,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9998000264167786,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.906532883644104},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7366522550582886},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6299940347671509},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5747371912002563},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5746715068817139},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.5341184735298157},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5169631838798523},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5091831088066101},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5044039487838745},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.47014620900154114},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.426480233669281},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.41596975922584534},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.41328543424606323},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12734243273735046},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11117216944694519},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.09672284126281738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.906532883644104},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7366522550582886},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6299940347671509},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5747371912002563},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5746715068817139},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.5341184735298157},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5169631838798523},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5091831088066101},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5044039487838745},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.47014620900154114},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.426480233669281},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.41596975922584534},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.41328543424606323},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12734243273735046},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11117216944694519},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.09672284126281738},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2145816.2145818","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2145816.2145818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/41995","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/41995","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.309.8005","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.309.8005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.comp.nus.edu.sg/~wongwf/papers/PPoPP12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1975539994","https://openalex.org/W2000335122","https://openalex.org/W2004951603","https://openalex.org/W2032309817","https://openalex.org/W2095117703","https://openalex.org/W2102922928","https://openalex.org/W2103838950","https://openalex.org/W2108157916","https://openalex.org/W2110195531","https://openalex.org/W2113282196","https://openalex.org/W2114324808","https://openalex.org/W2119304316","https://openalex.org/W2120431055","https://openalex.org/W2122080725","https://openalex.org/W2130336316","https://openalex.org/W2130561688","https://openalex.org/W2134408405","https://openalex.org/W2140375692","https://openalex.org/W2159456929","https://openalex.org/W2161190431","https://openalex.org/W2161455936","https://openalex.org/W2165100134","https://openalex.org/W2296705214","https://openalex.org/W4241513866"],"related_works":["https://openalex.org/W2983282793","https://openalex.org/W1973046741","https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2370314112","https://openalex.org/W1912958759"],"abstract_inverted_index":{"Graphics":[0],"processing":[1,10],"units":[2],"leverage":[3],"on":[4,55,172],"a":[5,17,78,129,159,182,202],"large":[6],"array":[7],"of":[8,16,169,184],"parallel":[9],"cores":[11],"to":[12,123,140],"boost":[13],"the":[14,36,56,84,92,102,120,125,135,151,155,167,170,173,185],"performance":[15,127,198],"specific":[18],"streaming":[19,38,75,107],"computation":[20],"pattern":[21],"frequently":[22],"found":[23],"in":[24,98],"graphics":[25],"applications.":[26,108],"Unfortunately,":[27],"while":[28,153],"many":[29],"other":[30],"general":[31,73],"purpose":[32,74],"applications":[33,76],"do":[34],"exhibit":[35],"required":[37,104],"behavior,":[39],"they":[40],"also":[41],"possess":[42],"unfavorable":[43],"data":[44],"layout":[45],"and":[46,65,87,196],"poor":[47],"computation-to-communication":[48],"ratios":[49],"that":[50,70,118],"penalize":[51],"any":[52],"straight-forward":[53],"execution":[54,163,168],"GPU.":[57],"In":[58],"this":[59],"paper":[60],"we":[61,110],"describe":[62],"an":[63,112,144],"efficient":[64,113,145],"scalable":[66],"code":[67],"generation":[68],"framework":[69,82,100,177],"can":[71],"map":[72],"onto":[77],"multi-GPU":[79,93,174],"system.":[80,94,175],"This":[81],"spans":[83],"entire":[85],"core":[86],"memory":[88,132],"hierarchy":[89],"exposed":[90],"by":[91,105],"Several":[95],"key":[96],"features":[97],"our":[99],"ensure":[101],"scalability":[103,195],"complex":[106,121],"First,":[109],"propose":[111],"stream":[114],"graph":[115],"partitioning":[116],"algorithm":[117],"partitions":[119,137,171],"application":[122],"achieve":[124],"best":[126],"under":[128],"given":[130],"shared":[131],"constraint.":[133],"Next,":[134],"resulting":[136],"are":[138],"mapped":[139],"multiple":[141],"GPUs":[142],"using":[143],"architecture-driven":[146],"strategy.":[147],"The":[148,176],"mapping":[149],"balances":[150],"workload":[152],"considering":[154],"communication":[156],"overhead.":[157],"Finally,":[158],"highly":[160],"effective":[161],"pipeline":[162],"is":[164],"employed":[165],"for":[166],"has":[178],"been":[179],"implemented":[180],"as":[181],"back-end":[183],"StreamIt":[186],"programming":[187],"language":[188],"compiler.":[189],"Our":[190],"comprehensive":[191],"experiments":[192],"show":[193],"its":[194],"significant":[197],"speedup":[199],"compared":[200],"with":[201],"previous":[203],"state-of-the-art":[204],"solution.":[205]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}