{"id":"https://openalex.org/W2991081937","doi":"https://doi.org/10.1109/hpec.2019.8916551","title":"Improving Parallelism of Breadth First Search (BFS) Algorithm for Accelerated Performance on GPUs","display_name":"Improving Parallelism of Breadth First Search (BFS) Algorithm for Accelerated Performance on GPUs","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2991081937","doi":"https://doi.org/10.1109/hpec.2019.8916551","mag":"2991081937"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2019.8916551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2019.8916551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5100771563","display_name":"Hao Wen","orcid":"https://orcid.org/0000-0003-3165-3859"},"institutions":[{"id":"https://openalex.org/I184840846","display_name":"Virginia Commonwealth University","ror":"https://ror.org/02nkdxk79","country_code":"US","type":"education","lineage":["https://openalex.org/I184840846"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao Wen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Virginia Commonwealth University, Richmond, VA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Virginia Commonwealth University, Richmond, VA","institution_ids":["https://openalex.org/I184840846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100756634","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-4960-3190"},"institutions":[{"id":"https://openalex.org/I184840846","display_name":"Virginia Commonwealth University","ror":"https://ror.org/02nkdxk79","country_code":"US","type":"education","lineage":["https://openalex.org/I184840846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Virginia Commonwealth University, Richmond, VA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Virginia Commonwealth University, Richmond, VA","institution_ids":["https://openalex.org/I184840846"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100771563"],"corresponding_institution_ids":["https://openalex.org/I184840846"],"apc_list":null,"apc_paid":null,"fwci":0.2042,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.55895521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9977999925613403,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9957000017166138,"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":0.8181238174438477},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7643252015113831},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6358787417411804},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5582324266433716},{"id":"https://openalex.org/keywords/breadth-first-search","display_name":"Breadth-first search","score":0.4797709882259369},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4582679569721222},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.4291422367095947},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.411528617143631},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35452955961227417},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.32024890184402466},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.26313185691833496}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8181238174438477},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7643252015113831},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6358787417411804},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5582324266433716},{"id":"https://openalex.org/C138843760","wikidata":"https://www.wikidata.org/wiki/Q325904","display_name":"Breadth-first search","level":2,"score":0.4797709882259369},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4582679569721222},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.4291422367095947},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.411528617143631},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35452955961227417},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.32024890184402466},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26313185691833496},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec.2019.8916551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2019.8916551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2004388081","https://openalex.org/W2026812620","https://openalex.org/W2042545849","https://openalex.org/W2055497547","https://openalex.org/W2061660549","https://openalex.org/W2080592089","https://openalex.org/W2093043622","https://openalex.org/W2109473404","https://openalex.org/W2143114052","https://openalex.org/W2167675119","https://openalex.org/W2295258302","https://openalex.org/W2535742285","https://openalex.org/W2581724516","https://openalex.org/W2790789009","https://openalex.org/W4237819810","https://openalex.org/W6729033847"],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W1554644772","https://openalex.org/W2003935582","https://openalex.org/W2494130044","https://openalex.org/W2177838837","https://openalex.org/W3170887803","https://openalex.org/W2963831937","https://openalex.org/W74409296","https://openalex.org/W1991844655","https://openalex.org/W3209384898"],"abstract_inverted_index":{"Breadth-first":[0],"search":[1,8],"(BFS)":[2],"is":[3,22,31,70,80,185],"a":[4,10,24,37,39,46],"basis":[5],"for":[6,14,82],"graph":[7,17,69,117,128],"and":[9,152,181],"core":[11],"building":[12],"block":[13],"many":[15],"higher-level":[16],"analysis":[18],"applications.":[19],"However,":[20],"BFS":[21,93,175],"also":[23,71,156,186],"typical":[25],"example":[26],"of":[27,42,49,62,67,76,85,92,138,174],"parallel":[28],"computation":[29],"that":[30,133,145,163],"inefficient":[32],"on":[33,56,95,101],"GPU":[34,78,147,172],"architectures.":[35],"In":[36,58],"graph,":[38],"small":[40],"portion":[41],"nodes":[43,63,125],"may":[44],"have":[45,134],"large":[47],"number":[48,61,75,137],"neighbors,":[50,139],"which":[51,140],"leads":[52],"to":[53,105,113],"irregular":[54],"tasks":[55],"GPUs.":[57],"addition,":[59],"the":[60,68,74,90,97,107,116,123,127,142,153,164,170,177,182],"in":[64,126],"each":[65,83],"layer":[66,84],"irregular.":[72],"Therefore,":[73],"active":[77],"threads":[79,148],"different":[81],"execution.":[86],"These":[87],"irregularities":[88],"limit":[89],"parallelism":[91,143],"executing":[94],"GPUs.Unlike":[96],"previous":[98],"works":[99],"focusing":[100],"fine-grained":[102],"task":[103],"management":[104],"address":[106],"irregularity,":[108],"we":[109],"propose":[110],"Virtual-BFS":[111],"(VBFS)":[112],"virtually":[114],"change":[115],"itself.":[118],"By":[119],"adding":[120],"virtual":[121],"vertices,":[122],"high-degree":[124],"are":[129],"divided":[130],"into":[131],"groups":[132],"an":[135],"equal":[136],"increases":[141],"such":[144],"more":[146,158],"can":[149],"work":[150],"concurrently,":[151],"data":[154],"set":[155],"becomes":[157],"regular.Our":[159],"experimental":[160],"results":[161],"show":[162],"VBFS":[165],"achieves":[166],"significant":[167],"speedup":[168],"over":[169],"current":[171],"implementation":[173],"from":[176],"Rodinia":[178],"benchmark":[179],"[4],":[180],"energy":[183],"efficiency":[184],"improved.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-07T13:37:22.277990","created_date":"2025-10-10T00:00:00"}