{"id":"https://openalex.org/W7167063564","doi":"https://doi.org/10.1145/3797905.3800549","title":"CORE-BFS: Communication-Optimized REctangular-partitioned BFS Achieving 160.845 TeraTEPS on Frontier Supercomputer","display_name":"CORE-BFS: Communication-Optimized REctangular-partitioned BFS Achieving 160.845 TeraTEPS on Frontier Supercomputer","publication_year":2026,"publication_date":"2026-07-02","ids":{"openalex":"https://openalex.org/W7167063564","doi":"https://doi.org/10.1145/3797905.3800549"},"language":null,"primary_location":{"id":"doi:10.1145/3797905.3800549","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3800549","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3797905.3800549","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139935816","display_name":"Haoshen Yang","orcid":"https://orcid.org/0009-0001-7896-5019"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoshen Yang","raw_affiliation_strings":["Rutgers, The State University of New Jersey, Piscataway, NJ, USA"],"raw_orcid":"https://orcid.org/0009-0001-7896-5019","affiliations":[{"raw_affiliation_string":"Rutgers, The State University of New Jersey, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058248684","display_name":"Hao Lu","orcid":"https://orcid.org/0000-0001-8941-870X"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Lu","raw_affiliation_strings":["Oak Ridge National Laboratory, USA, Oak Ridge, TN, USA"],"raw_orcid":"https://orcid.org/0000-0001-8941-870X","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012951247","display_name":"Michael A. Matheson","orcid":"https://orcid.org/0000-0003-1512-5255"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Matheson","raw_affiliation_strings":["Oak Ridge National Laboratory, USA, Oak Ridge, TN, USA"],"raw_orcid":"https://orcid.org/0000-0003-1512-5255","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101916963","display_name":"Feiyi Wang","orcid":"https://orcid.org/0000-0002-0099-1559"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feiyi Wang","raw_affiliation_strings":["Oak Ridge National Laboratory, USA, Oak Ridge, TN, USA"],"raw_orcid":"https://orcid.org/0000-0002-0099-1559","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100623301","display_name":"Hang Liu","orcid":"https://orcid.org/0000-0001-6323-7388"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hang Liu","raw_affiliation_strings":["Rutgers, The State University of New Jersey, Piscataway, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0001-6323-7388","affiliations":[{"raw_affiliation_string":"Rutgers, The State University of New Jersey, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8922968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"727","last_page":"739"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9542999863624573,"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":0.9542999863624573,"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":0.01549999974668026,"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":0.010400000028312206,"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/bitmap","display_name":"Bitmap","score":0.7117999792098999},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.6029999852180481},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5724999904632568},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.5590000152587891},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.51910001039505},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4659999907016754},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.46540001034736633},{"id":"https://openalex.org/keywords/adjacency-list","display_name":"Adjacency list","score":0.43209999799728394},{"id":"https://openalex.org/keywords/breadth-first-search","display_name":"Breadth-first search","score":0.38769999146461487},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.38769999146461487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7576000094413757},{"id":"https://openalex.org/C3115412","wikidata":"https://www.wikidata.org/wiki/Q1194708","display_name":"Bitmap","level":2,"score":0.7117999792098999},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6492000222206116},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.6029999852180481},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5724999904632568},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.5590000152587891},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.51910001039505},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.46540001034736633},{"id":"https://openalex.org/C110484373","wikidata":"https://www.wikidata.org/wiki/Q264398","display_name":"Adjacency list","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C138843760","wikidata":"https://www.wikidata.org/wiki/Q325904","display_name":"Breadth-first search","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.37049999833106995},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.357699990272522},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C96333769","wikidata":"https://www.wikidata.org/wiki/Q907955","display_name":"Graph traversal","level":3,"score":0.32260000705718994},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.3188000023365021},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.3084999918937683},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.3009999990463257},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2953000068664551},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2930999994277954},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.28529998660087585},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.28360000252723694},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.26910001039505005},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2632000148296356},{"id":"https://openalex.org/C134066672","wikidata":"https://www.wikidata.org/wiki/Q1424639","display_name":"Payload (computing)","level":3,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3797905.3800549","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3800549","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3797905.3800549","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3800549","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W312849892","https://openalex.org/W1987396134","https://openalex.org/W1992011279","https://openalex.org/W2004388081","https://openalex.org/W2036850008","https://openalex.org/W2042545849","https://openalex.org/W2047345171","https://openalex.org/W2068612205","https://openalex.org/W2081538566","https://openalex.org/W2128853364","https://openalex.org/W2130488390","https://openalex.org/W2134237243","https://openalex.org/W2141662114","https://openalex.org/W2154111453","https://openalex.org/W2397037157","https://openalex.org/W2399395406","https://openalex.org/W2435994428","https://openalex.org/W2568149362","https://openalex.org/W2585968540","https://openalex.org/W2606769571","https://openalex.org/W2730740223","https://openalex.org/W2790789009","https://openalex.org/W2902906695","https://openalex.org/W2902968852","https://openalex.org/W2948742909","https://openalex.org/W2950537538","https://openalex.org/W3013652274","https://openalex.org/W3161340861","https://openalex.org/W3167837697","https://openalex.org/W3169942475","https://openalex.org/W4220754604","https://openalex.org/W4240241667","https://openalex.org/W4284900192","https://openalex.org/W4309236229","https://openalex.org/W4378835752","https://openalex.org/W4379116128","https://openalex.org/W4405755155"],"related_works":[],"abstract_inverted_index":{"Distributed":[0],"Breadth-First":[1],"Search":[2],"(BFS)":[3],"is":[4,17],"fundamental":[5],"to":[6,119,131,141,161,184],"many":[7],"large-scale":[8],"graph":[9],"applications,":[10],"but":[11],"its":[12],"performance":[13],"on":[14,102,116,138],"parallel":[15],"systems":[16],"often":[18],"limited":[19],"by":[20],"high":[21],"communication":[22,94,121,174],"overhead.":[23,175],"This":[24],"paper":[25],"presents":[26],"\\({\\mathrm\\small":[27,180],"{CORE-BFS}}\\),":[28],"an":[29],"extremely":[30],"scalable":[31],"GPU-based":[32],"BFS":[33],"implementation":[34],"that":[35,61,96,127,151],"introduces":[36],"a":[37,75,196],"unique":[38],"rectangular":[39,104],"2D":[40],"partitioning-based":[41],"design":[42],"for":[43],"Frontier":[44,186,203],"supercomputer.":[45],"To":[46],"further":[47],"improve":[48,142],"performance,":[49],"we":[50],"propose":[51],"four":[52],"key":[53],"optimizations:":[54],"(1)":[55],"Rectangular":[56],"2D-partition":[57],"specific":[58],"data":[59],"formats":[60],"use":[62],"two":[63],"compressed":[64,68],"row":[65],"and":[66,87,99,112,134,145,173,191],"one":[67],"column":[69],"status":[70],"array":[71],"bitmaps":[72],"combined":[73],"with":[74,157,188],"Double":[76],"Compressed":[77],"Sparse":[78],"Row":[79],"(DCSR)":[80],"format":[81],"per":[82],"partition,":[83],"reducing":[84,171],"memory":[85,146,172],"footprint":[86],"inter-rank":[88,163],"traffic;":[89],"(2)":[90],"Adaptive":[91],"frontier":[92,117,129],"&":[93],"strategy":[95],"unifies":[97],"top-down":[98,110],"bottom-up":[100,153],"traversal":[101],"the":[103,177],"layout,":[105],"uses":[106],"lazy":[107],"synchronization":[108],"in":[109],"levels,":[111],"switches":[113],"variants":[114],"based":[115,137],"size":[118],"minimize":[120],"overhead;":[122],"(3)":[123],"Frontier-split":[124],"degree-aware":[125],"update":[126],"maps":[128],"vertices":[130],"thread-centric,":[132],"wavefront-centric,":[133],"block-centric":[135],"kernels":[136],"their":[139],"degree":[140],"GPU":[143],"utilization":[144],"coalescing;":[147],"(4)":[148],"Row-reduction":[149],"pipeline":[150],"overlaps":[152],"adjacency":[154],"list":[155],"processing":[156],"row-wise":[158],"bitmap":[159],"reduction":[160],"hide":[162],"latency.":[164],"Together,":[165],"these":[166],"techniques":[167],"increase":[168],"parallelism":[169],"while":[170],"On":[176],"Graph500":[178],"benchmark,":[179],"{CORE-BFS}}\\)":[181],"scales":[182],"up":[183],"9,248":[185],"nodes":[187],"scale-42":[189],"graphs":[190],"reaches":[192],"160.845":[193],"TTEPS,":[194],"delivering":[195],"5.42":[197],"\u00d7":[198],"speedup":[199],"over":[200],"our":[201],"previous":[202],"implementation.":[204]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-03T00:00:00"}