{"id":"https://openalex.org/W4415250867","doi":"https://doi.org/10.1109/hpec67600.2025.11196373","title":"Scalable Graph Algorithms on Distributed UpDown Accelerators","display_name":"Scalable Graph Algorithms on Distributed UpDown Accelerators","publication_year":2025,"publication_date":"2025-09-15","ids":{"openalex":"https://openalex.org/W4415250867","doi":"https://doi.org/10.1109/hpec67600.2025.11196373"},"language":"en","primary_location":{"id":"doi:10.1109/hpec67600.2025.11196373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec67600.2025.11196373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5004423945","display_name":"Brian Wheatman","orcid":"https://orcid.org/0009-0005-2018-4577"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Brian Wheatman","raw_affiliation_strings":["University of Chicago,USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago,USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085538238","display_name":"Andrew A. Chien","orcid":"https://orcid.org/0000-0002-1204-206X"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew A. Chien","raw_affiliation_strings":["University of Chicago,Argonne National Laboratory"],"affiliations":[{"raw_affiliation_string":"University of Chicago,Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I40347166"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004423945"],"corresponding_institution_ids":["https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":2.1983,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88706344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.949999988079071,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.949999988079071,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9352999925613403,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9289000034332275,"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/scalability","display_name":"Scalability","score":0.6873999834060669},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6243000030517578},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5787000060081482},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.46070000529289246},{"id":"https://openalex.org/keywords/graph-algorithms","display_name":"Graph algorithms","score":0.453000009059906},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4507000148296356},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4390999972820282},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.3711000084877014}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8203999996185303},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6873999834060669},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6243000030517578},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5787000060081482},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4968999922275543},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.46790000796318054},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C2986651925","wikidata":"https://www.wikidata.org/wiki/Q1514868","display_name":"Graph algorithms","level":3,"score":0.453000009059906},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4390999972820282},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38830000162124634},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3434999883174896},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C56348326","wikidata":"https://www.wikidata.org/wiki/Q1047554","display_name":"Mutual exclusion","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C106937863","wikidata":"https://www.wikidata.org/wiki/Q7236518","display_name":"Power graph analysis","level":3,"score":0.26840001344680786},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.2590000033378601},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C558772884","wikidata":"https://www.wikidata.org/wiki/Q1508564","display_name":"Graph rewriting","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec67600.2025.11196373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec67600.2025.11196373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"},{"id":"https://openalex.org/F4320332179","display_name":"Office of the Director","ror":"https://ror.org/04nseet23"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2000041758","https://openalex.org/W2016559894","https://openalex.org/W2296412986","https://openalex.org/W2568149362","https://openalex.org/W2885289863","https://openalex.org/W2903131164","https://openalex.org/W3013652274","https://openalex.org/W3034302216","https://openalex.org/W3161374268","https://openalex.org/W3175994815","https://openalex.org/W3216615040","https://openalex.org/W4235810972","https://openalex.org/W4391952029","https://openalex.org/W4399347275","https://openalex.org/W4401352238","https://openalex.org/W4405348629","https://openalex.org/W4405755155","https://openalex.org/W4406157004","https://openalex.org/W4409131818"],"related_works":[],"abstract_inverted_index":{"Graphs":[0],"are":[1],"a":[2,65,91,172],"fundamental":[3],"tool":[4],"for":[5,97],"representing":[6],"and":[7,19,36,135],"analyzing":[8],"relationships":[9],"in":[10,145],"data,":[11],"with":[12,108,119],"applications":[13],"spanning":[14],"social":[15],"networks,":[16],"the":[17,20,24,34,39,140,151],"web,":[18],"biological":[21],"sciences.":[22],"As":[23],"volume":[25],"of":[26,38,110,116,147],"data":[27],"continues":[28],"to":[29,70,82,86,106,121],"grow,":[30],"so":[31],"too":[32],"do":[33],"size":[35],"complexity":[37],"graphs":[40,49],"we":[41,79,125],"must":[42],"process.":[43],"Extracting":[44],"insights":[45],"from":[46],"these":[47],"massive":[48],"requires":[50],"scalable,":[51,92],"high-performance":[52],"algorithmsWhile":[53],"many":[54],"graph":[55,84,103],"algorithms":[56,85,105],"exhibit":[57],"substantial":[58],"parallelism,":[59],"it":[60,68],"is":[61],"often":[62],"extremely":[63],"fine-grained\u2014just":[64],"few":[66],"instructions\u2014making":[67],"difficult":[69],"exploit":[71],"efficiently":[72,88],"on":[73,89],"conventional":[74],"architectures.":[75],"In":[76],"this":[77],"work,":[78],"demonstrate":[80],"how":[81],"restructure":[83],"run":[87],"UpDown,":[90],"programmable":[93],"accelerator":[94],"designed":[95],"specifically":[96],"fine-grained":[98],"parallelism.":[99],"UpDown":[100,117],"enables":[101],"scaling":[102],"processing":[104],"systems":[107,118,144],"millions":[109],"concurrent":[111],"hardware":[112],"threadsThrough":[113],"detailed":[114],"simulation":[115],"up":[120],"one":[122],"million":[123],"cores,":[124],"show":[126],"that":[127,138],"our":[128,154],"approach":[129,156],"achieves":[130],"over":[131],"100,000\u00d7":[132],"parallel":[133],"speedup":[134],"absolute":[136],"performance":[137,159],"outperforms":[139],"best":[141],"reported":[142],"distributed":[143],"terms":[146],"power":[148,169],"efficiency.":[149],"At":[150],"same":[152],"time,":[153],"load-balanced":[155],"retains":[157],"strong":[158],"at":[160],"smaller":[161],"scales,":[162],"outperforming":[163],"optimized":[164],"multicore":[165],"implementations":[166],"under":[167],"similar":[168],"budgets\u2014all":[170],"using":[171],"single,":[173],"unified":[174],"implementation.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-16T00:00:00"}