{"id":"https://openalex.org/W2765984990","doi":"https://doi.org/10.1145/3149704.3149762","title":"Enabling Work-Efficiency for High Performance Vertex-Centric Graph Analytics on GPUs","display_name":"Enabling Work-Efficiency for High Performance Vertex-Centric Graph Analytics on GPUs","publication_year":2017,"publication_date":"2017-11-03","ids":{"openalex":"https://openalex.org/W2765984990","doi":"https://doi.org/10.1145/3149704.3149762","mag":"2765984990"},"language":"en","primary_location":{"id":"doi:10.1145/3149704.3149762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3149704.3149762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh Workshop on Irregular Applications: Architectures and Algorithms","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/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":true,"raw_author_name":"Farzad Khorasani","raw_affiliation_strings":["School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054794473","display_name":"Keval Vora","orcid":"https://orcid.org/0000-0002-5462-5116"},"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":"Keval Vora","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100699251","display_name":"Rajiv Gupta","orcid":"https://orcid.org/0000-0002-9348-3974"},"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":"Rajiv Gupta","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048949780","display_name":"Laxmi N. Bhuyan","orcid":"https://orcid.org/0000-0002-8759-0458"},"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":"Laxmi N. Bhuyan","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036836220"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.182,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57767629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"43","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":0.9998999834060669,"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":0.9998999834060669,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9973000288009644,"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":0.8638317584991455},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6626666188240051},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.6036422848701477},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5095077157020569},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.4901757836341858},{"id":"https://openalex.org/keywords/graph-algorithms","display_name":"Graph algorithms","score":0.46541810035705566},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4623490571975708},{"id":"https://openalex.org/keywords/vertex","display_name":"Vertex (graph theory)","score":0.4358522891998291},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.42639297246932983},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.41713839769363403},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.41497987508773804},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4116024971008301},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13498547673225403},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.09672126173973083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8638317584991455},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6626666188240051},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.6036422848701477},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5095077157020569},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.4901757836341858},{"id":"https://openalex.org/C2986651925","wikidata":"https://www.wikidata.org/wiki/Q1514868","display_name":"Graph algorithms","level":3,"score":0.46541810035705566},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4623490571975708},{"id":"https://openalex.org/C80899671","wikidata":"https://www.wikidata.org/wiki/Q1304193","display_name":"Vertex (graph theory)","level":3,"score":0.4358522891998291},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42639297246932983},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.41713839769363403},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41497987508773804},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4116024971008301},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13498547673225403},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.09672126173973083},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3149704.3149762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3149704.3149762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh Workshop on Irregular Applications: Architectures and Algorithms","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":9,"referenced_works":["https://openalex.org/W142653777","https://openalex.org/W1482680420","https://openalex.org/W1965830721","https://openalex.org/W1985291160","https://openalex.org/W2268177516","https://openalex.org/W2295258302","https://openalex.org/W2505199798","https://openalex.org/W2755088640","https://openalex.org/W3006582303"],"related_works":["https://openalex.org/W2264067234","https://openalex.org/W3124243301","https://openalex.org/W1571502335","https://openalex.org/W1589409554","https://openalex.org/W2759038785","https://openalex.org/W2172232600","https://openalex.org/W3123876860","https://openalex.org/W3120961607","https://openalex.org/W3124172198","https://openalex.org/W2046181650"],"abstract_inverted_index":{"Massive":[0],"parallel":[1],"processing":[2,14,46],"power":[3],"of":[4,32,59],"GPUs":[5],"has":[6],"attracted":[7],"researchers":[8],"to":[9,86,124],"develop":[10],"iterative":[11],"vertex-centric":[12],"graph":[13,48,89],"frameworks":[15],"for":[16],"GPUs.":[17],"Enabling":[18],"work-efficiency":[19],"in":[20,113],"these":[21,43,120],"solutions,":[22],"however,":[23],"is":[24],"not":[25],"straightforward":[26],"and":[27,34,61,109,136],"comes":[28],"at":[29],"the":[30,47,88,110,127],"cost":[31],"SIMD-inefficiency":[33],"load":[35],"imbalance.":[36],"This":[37],"paper":[38],"offers":[39],"techniques":[40,121],"that":[41,73,103,119],"overcome":[42],"challenges":[44],"when":[45],"on":[49,64,92],"a":[50,53,101],"GPU.":[51],"For":[52],"SIMD-efficient":[54],"kernel":[55],"operation":[56],"involving":[57],"gathering":[58],"neighbors":[60],"performing":[62],"reduction":[63],"them,":[65],"we":[66,96],"employ":[67],"an":[68],"effective":[69],"task":[70],"expansion":[71],"strategy":[72],"avoids":[74],"intra-warp":[75],"thread":[76],"underutilization.":[77],"As":[78],"recording":[79],"vertex":[80,98],"activeness":[81],"requires":[82],"additional":[83],"data":[84],"structures,":[85],"attenuate":[87],"storage":[90],"overhead":[91],"limited":[93],"GPU":[94],"DRAM,":[95],"introduce":[97],"grouping":[99],"as":[100],"technique":[102],"enables":[104],"trade-off":[105],"between":[106],"memory":[107],"consumption":[108],"work":[111],"efficiency":[112],"our":[114],"solution.":[115],"Our":[116],"experiments":[117],"show":[118],"provide":[122],"up":[123],"5.46x":[125],"over":[126,133],"recently":[128],"proposed":[129],"WS-VR":[130],"[4]":[131],"framework":[132],"multiple":[134],"algorithms":[135],"inputs.":[137]},"counts_by_year":[{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}