{"id":"https://openalex.org/W3083985534","doi":"https://doi.org/10.1109/hpcs48598.2019.9188120","title":"High Performance Multilevel Graph Partitioning on GPU","display_name":"High Performance Multilevel Graph Partitioning on GPU","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W3083985534","doi":"https://doi.org/10.1109/hpcs48598.2019.9188120","mag":"3083985534"},"language":"en","primary_location":{"id":"doi:10.1109/hpcs48598.2019.9188120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcs48598.2019.9188120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on High Performance Computing & Simulation (HPCS)","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/A5016385511","display_name":"Bahareh Goodarzi","orcid":null},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bahareh Goodarzi","raw_affiliation_strings":["Department of Computer Science, Concordia University, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Concordia University, Montreal, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036836220","display_name":"Farzad Khorasani","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Farzad Khorasani","raw_affiliation_strings":["Department of Computer Science, Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043513001","display_name":"Vivek Sarkar","orcid":"https://orcid.org/0000-0002-3433-8830"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivek Sarkar","raw_affiliation_strings":["Department of Computer Science, Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111411144","display_name":"Dhrubajyoti Goswami","orcid":null},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Dhrubajyoti Goswami","raw_affiliation_strings":["Department of Computer Science, Concordia University, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Concordia University, Montreal, Canada","institution_ids":["https://openalex.org/I60158472"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.186,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.60808045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"769","last_page":"778"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9991000294685364,"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":0.9991000294685364,"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/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8834018707275391},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7738885879516602},{"id":"https://openalex.org/keywords/graph-partition","display_name":"Graph partition","score":0.6821098327636719},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6409207582473755},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5246601104736328},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5179237723350525},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5102376937866211},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5070681571960449},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46982264518737793},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4316188097000122},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3654633164405823},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19904285669326782},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.17789480090141296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8834018707275391},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7738885879516602},{"id":"https://openalex.org/C48903430","wikidata":"https://www.wikidata.org/wiki/Q491370","display_name":"Graph partition","level":3,"score":0.6821098327636719},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6409207582473755},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5246601104736328},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5179237723350525},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5102376937866211},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5070681571960449},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46982264518737793},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4316188097000122},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3654633164405823},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19904285669326782},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.17789480090141296},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcs48598.2019.9188120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcs48598.2019.9188120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on High Performance Computing & Simulation (HPCS)","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":42,"referenced_works":["https://openalex.org/W63129197","https://openalex.org/W579519726","https://openalex.org/W1538076361","https://openalex.org/W1556784394","https://openalex.org/W1599507069","https://openalex.org/W1910515323","https://openalex.org/W1974165492","https://openalex.org/W1975464357","https://openalex.org/W2004951603","https://openalex.org/W2035080386","https://openalex.org/W2059966434","https://openalex.org/W2059985735","https://openalex.org/W2070232376","https://openalex.org/W2093832225","https://openalex.org/W2094722168","https://openalex.org/W2095117703","https://openalex.org/W2118953734","https://openalex.org/W2133732112","https://openalex.org/W2144856557","https://openalex.org/W2150302083","https://openalex.org/W2152377721","https://openalex.org/W2161455936","https://openalex.org/W2166604263","https://openalex.org/W2172051569","https://openalex.org/W2188390201","https://openalex.org/W2225892715","https://openalex.org/W2273593125","https://openalex.org/W2295258302","https://openalex.org/W2327315803","https://openalex.org/W2481354194","https://openalex.org/W2505199798","https://openalex.org/W2523536562","https://openalex.org/W2560165255","https://openalex.org/W2782087530","https://openalex.org/W3098342588","https://openalex.org/W3149246379","https://openalex.org/W4241856644","https://openalex.org/W4300544635","https://openalex.org/W6632141491","https://openalex.org/W6677275879","https://openalex.org/W6679639368","https://openalex.org/W6725032520"],"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/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825","https://openalex.org/W2893308117"],"abstract_inverted_index":{"Graph":[0],"partitioning":[1,40,51,88,162],"is":[2,122,139,159,182],"a":[3,27,142,148],"common":[4],"computational":[5],"phase":[6],"in":[7,38,161],"many":[8],"application":[9],"domains,":[10],"including":[11],"social":[12],"network":[13],"analysis,":[14],"data":[15,36],"mining,":[16],"scheduling,":[17],"and":[18,41,48,70,81,96,115,158],"VLSI":[19],"design.":[20],"The":[21],"significant":[22],"SIMT":[23],"compute":[24],"power":[25],"of":[26,61,108,144,178],"GPU":[28,58,101,133,145],"makes":[29],"it":[30,181],"an":[31,79],"appropriate":[32,106],"platform":[33],"to":[34,84,110,166,175],"exploit":[35],"parallelism":[37],"graph":[39,50,87,113,171],"accelerate":[42],"the":[43,98,112,126,132,167,176,183],"computation.":[44],"However,":[45],"irregular,":[46],"non-uniform,":[47],"data-dependent":[49],"sub-tasks":[52],"pose":[53],"multiple":[54],"challenges":[55,63],"for":[56,141],"efficient":[57],"utilization.":[59],"Some":[60],"these":[62],"include":[64],"load":[65,99],"imbalance,":[66],"non-coalesced":[67],"memory":[68],"accesses,":[69],"warp":[71],"execution":[72],"inefficiency.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77],"describe":[78],"effective":[80],"methodological":[82],"approach":[83,155,186],"enable":[85],"multi-level":[86],"on":[89,187],"GPUs.":[90],"Our":[91,120],"solution":[92],"avoids":[93],"thread":[94],"divergence":[95],"balances":[97],"over":[100],"threads":[102,109],"by":[103,131],"dynamically":[104],"assigning":[105],"number":[107],"process":[111],"vertices":[114],"their":[116],"irregular":[117],"sized":[118],"neighbors.":[119],"design":[121],"autonomous,":[123],"i.e.,":[124],"all":[125],"steps":[127],"are":[128],"carried":[129],"out":[130],"with":[134,164],"minimal":[135],"CPU":[136],"involvement,":[137],"which":[138],"required":[140],"range":[143],"applications":[146],"as":[147],"pre-processing":[149],"step.":[150],"We":[151],"show":[152],"that":[153],"our":[154,179],"performs":[156],"better":[157],"comparable":[160],"quality":[163],"respect":[165],"state-of-the-art":[168],"CPU-based":[169],"parallel":[170],"partitioner":[172],"(mtmetis).":[173],"Moreover,":[174],"best":[177],"knowledge,":[180],"first":[184],"autonomous":[185],"GPU.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}