{"id":"https://openalex.org/W2271597743","doi":"https://doi.org/10.1145/2854038.2854055","title":"Communication-aware mapping of stream graphs for multi-GPU platforms","display_name":"Communication-aware mapping of stream graphs for multi-GPU platforms","publication_year":2016,"publication_date":"2016-02-29","ids":{"openalex":"https://openalex.org/W2271597743","doi":"https://doi.org/10.1145/2854038.2854055","mag":"2271597743"},"language":"en","primary_location":{"id":"doi:10.1145/2854038.2854055","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2854038.2854055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Symposium on Code Generation and Optimization","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/A5101637741","display_name":"Dong Thanh Nguyen","orcid":"https://orcid.org/0000-0001-5011-1313"},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Dong Nguyen","raw_affiliation_strings":["Ulsan National Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Ulsan National Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I48566637"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100780257","display_name":"Jongeun Lee","orcid":"https://orcid.org/0000-0003-1523-2974"},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongeun Lee","raw_affiliation_strings":["Ulsan National Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Ulsan National Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I48566637"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101637741"],"corresponding_institution_ids":["https://openalex.org/I48566637"],"apc_list":null,"apc_paid":null,"fwci":1.1864,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81022957,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"94","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9993000030517578,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9988999962806702,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9980999827384949,"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":0.8716734051704407},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7897047996520996},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.6673640608787537},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6348971128463745},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.48065412044525146},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.46187472343444824},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4425666332244873},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4192125201225281},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34450656175613403},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.2548159956932068}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8716734051704407},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7897047996520996},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.6673640608787537},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6348971128463745},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.48065412044525146},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.46187472343444824},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4425666332244873},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4192125201225281},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34450656175613403},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.2548159956932068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2854038.2854055","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2854038.2854055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarworks.unist.ac.kr:201301/18371","is_oa":false,"landing_page_url":"http://unist.dcollection.net/jsp/common/DcLoOrgPer.jsp?sItemId=000002236799","pdf_url":null,"source":{"id":"https://openalex.org/S4306401118","display_name":"Scholarworks@UNIST (Ulsan National Institute of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I48566637","host_organization_name":"Ulsan National Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I48566637"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Master's thesis"},{"id":"pmh:oai:scholarworks.unist.ac.kr:201301/32808","is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?doid=2854038.2854055","pdf_url":null,"source":{"id":"https://openalex.org/S4306401118","display_name":"Scholarworks@UNIST (Ulsan National Institute of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I48566637","host_organization_name":"Ulsan National Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I48566637"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"CONFERENCE"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1568192366","https://openalex.org/W1980543047","https://openalex.org/W2076323772","https://openalex.org/W2114324808","https://openalex.org/W2115321789","https://openalex.org/W2119304316","https://openalex.org/W2122080725","https://openalex.org/W2133741166","https://openalex.org/W2135903696","https://openalex.org/W2140375692","https://openalex.org/W2159456929","https://openalex.org/W2165100134","https://openalex.org/W2170675383","https://openalex.org/W3011180447","https://openalex.org/W4235001905","https://openalex.org/W4235344346","https://openalex.org/W4241553019","https://openalex.org/W4253760721"],"related_works":["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/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"Stream":[0],"graphs":[1,22,37,102],"can":[2,152,166],"provide":[3],"a":[4,62,70,75,93,120,144],"natural":[5],"way":[6],"to":[7,27,30,42,47,158],"represent":[8],"many":[9],"applications":[10],"in":[11],"multimedia":[12],"and":[13,82,129,165],"DSP":[14],"domains.":[15],"Though":[16],"the":[17,104,137],"exposed":[18],"parallelism":[19],"of":[20,79,116,136],"stream":[21,36,55,101,117,125,163],"makes":[23],"it":[24],"relatively":[25],"easy":[26],"map":[28],"them":[29],"GP":[31],"(General":[32],"Purpose)-GPUs,":[33],"very":[34,76],"large":[35,100,162],"as":[38,40],"well":[39],"how":[41],"best":[43],"exploit":[44],"multi-GPU":[45,170],"platforms":[46],"achieve":[48],"scalable":[49,95,154],"performance":[50,111,155],"poses":[51],"great":[52],"challenges":[53],"for":[54,99,114,156,173],"graph":[56],"mapping.":[57],"Previous":[58],"work":[59],"considers":[60],"either":[61],"single":[63],"GPU":[64,110,146],"only":[65,85],"or":[66],"is":[67],"based":[68],"on":[69,143],"crude":[71],"heuristic":[72,123],"that":[73,149],"achieves":[74],"low":[77],"degree":[78],"workload":[80],"balancing,":[81],"thus":[83],"shows":[84],"limited":[86],"scalability.":[87],"In":[88],"this":[89],"paper":[90],"we":[91],"present":[92],"highly":[94,168],"GP-GPU":[96],"mapping":[97,138],"technique":[98,151],"with":[103,161],"following":[105],"highlights:":[106],"(1)":[107],"an":[108],"accurate":[109],"estimation":[112],"model":[113],"subsets":[115],"graphs,":[118,164],"(2)":[119],"novel":[121],"partitioning":[122],"exploiting":[124],"graph's":[126],"structural":[127],"properties,":[128],"(3)":[130],"ILP":[131],"(Integer":[132],"Linear":[133],"Programming)":[134],"formulation":[135],"problem.":[139],"Our":[140],"experimental":[141],"results":[142],"real":[145],"platform":[147],"demonstrate":[148],"our":[150],"generate":[153,167],"up":[157],"4":[159],"GPUs":[160],"optimized":[169],"code":[171],"especially":[172],"compute-bound":[174],"ones.":[175]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}