{"id":"https://openalex.org/W3217273882","doi":"https://doi.org/10.1109/nas51552.2021.9605484","title":"Locality-aware Thread Block Design in Single and Multi-GPU Graph Processing","display_name":"Locality-aware Thread Block Design in Single and Multi-GPU Graph Processing","publication_year":2021,"publication_date":"2021-10-01","ids":{"openalex":"https://openalex.org/W3217273882","doi":"https://doi.org/10.1109/nas51552.2021.9605484","mag":"3217273882"},"language":"en","primary_location":{"id":"doi:10.1109/nas51552.2021.9605484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas51552.2021.9605484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Networking, Architecture and Storage (NAS)","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/A5076814480","display_name":"Quan Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Quan Fan","raw_affiliation_strings":["Computer Science and Engineering, University of California, Riverside"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061737717","display_name":"Zizhong Chen","orcid":"https://orcid.org/0000-0003-2578-4940"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zizhong Chen","raw_affiliation_strings":["Computer Science and Engineering, University of California, Riverside"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076814480"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":0.0961,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.41978758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9990000128746033,"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":0.9976000189781189,"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":0.8662599325180054},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7090219259262085},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6734339594841003},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5556598901748657},{"id":"https://openalex.org/keywords/graph-partition","display_name":"Graph partition","score":0.5252066254615784},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4919290542602539},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.48521021008491516},{"id":"https://openalex.org/keywords/locality-of-reference","display_name":"Locality of reference","score":0.46692487597465515},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.44288262724876404},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.441273033618927},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.42604172229766846},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.39752495288848877},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3846597671508789},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.35333821177482605},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.15554338693618774},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09228059649467468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8662599325180054},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7090219259262085},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6734339594841003},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5556598901748657},{"id":"https://openalex.org/C48903430","wikidata":"https://www.wikidata.org/wiki/Q491370","display_name":"Graph partition","level":3,"score":0.5252066254615784},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4919290542602539},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.48521021008491516},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.46692487597465515},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.44288262724876404},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.441273033618927},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.42604172229766846},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.39752495288848877},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3846597671508789},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35333821177482605},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.15554338693618774},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09228059649467468},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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:10.1109/nas51552.2021.9605484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas51552.2021.9605484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Networking, Architecture and Storage (NAS)","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":14,"referenced_works":["https://openalex.org/W2022704179","https://openalex.org/W2070232376","https://openalex.org/W2080592089","https://openalex.org/W2181900708","https://openalex.org/W2295258302","https://openalex.org/W2346459029","https://openalex.org/W2581090187","https://openalex.org/W2765329037","https://openalex.org/W2767106296","https://openalex.org/W2998104365","https://openalex.org/W3098136731","https://openalex.org/W3168173119","https://openalex.org/W6686091084","https://openalex.org/W6705085183"],"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":{"Graphics":[0],"Processing":[1],"Unit":[2],"(GPU)":[3],"has":[4],"been":[5],"adopted":[6],"to":[7,104,125,153,166],"process":[8,22],"graphs":[9,23,30],"effectively.":[10],"Recently,":[11],"multi-GPU":[12],"systems":[13],"are":[14],"also":[15,123],"exploited":[16],"for":[17,132],"greater":[18],"performance":[19,157],"boost.":[20],"To":[21],"on":[24,74,144],"multiple":[25],"GPUs":[26],"in":[27],"parallel,":[28],"input":[29,88],"should":[31],"be":[32,68],"partitioned":[33],"into":[34],"parts":[35],"using":[36],"partitioning":[37,40,83,128,146],"schemes.":[38],"The":[39,141],"schemes":[41],"can":[42,67],"impact":[43],"the":[44,54,87,113,116,155,159],"communication":[45,66,109],"overhead,":[46],"locality":[47,114],"of":[48,118,158],"memory":[49],"accesses,":[50],"and":[51,64,97,100,111,129],"further":[52],"improve":[53,112,154],"overall":[55,156],"performance.":[56],"We":[57,122],"found":[58],"that":[59,148],"both":[60],"intra-GPU":[61],"data":[62],"sharing":[63],"inter-GPU":[65,108],"summarized":[69],"as":[70,90],"inter-TB":[71],"communication.":[72],"Based":[73],"this":[75],"key":[76],"idea,":[77],"we":[78],"propose":[79,124],"a":[80,91,127],"new":[81],"graph":[82,89,145],"scheme":[84,131,150],"by":[85,164],"redefining":[86],"TB":[92],"Graph":[93],"with":[94,138],"calculated":[95],"vertex":[96],"edge":[98],"weights,":[99],"then":[101],"partition":[102],"it":[103],"reduce":[105],"intra":[106],"&":[107],"overhead":[110],"at":[115],"granularity":[117],"Thread":[119],"Blocks":[120],"(TB).":[121],"develop":[126],"mapping":[130],"heterogeneous":[133],"architectures":[134],"including":[135],"physical":[136],"links":[137],"different":[139],"bandwidths.":[140],"experimental":[142],"results":[143],"show":[147],"our":[149],"is":[151],"effective":[152],"Breadth":[160],"First":[161],"Search":[162],"(BFS)":[163],"up":[165],"33%.":[167]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}