{"id":"https://openalex.org/W4415250908","doi":"https://doi.org/10.1109/hpec67600.2025.11196651","title":"Accelerating Push-Relabel Algorithm on GPU via Two-Level Parallelism Paradigm and Efficient CSR Designs","display_name":"Accelerating Push-Relabel Algorithm on GPU via Two-Level Parallelism Paradigm and Efficient CSR Designs","publication_year":2025,"publication_date":"2025-09-15","ids":{"openalex":"https://openalex.org/W4415250908","doi":"https://doi.org/10.1109/hpec67600.2025.11196651"},"language":"en","primary_location":{"id":"doi:10.1109/hpec67600.2025.11196651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec67600.2025.11196651","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/A5111049508","display_name":"Chou-Ying Hsieh","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chou-Ying Hsieh","raw_affiliation_strings":["National Taiwan University,Department of Electrical Engineering"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Department of Electrical Engineering","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104269525","display_name":"Po-Chieh Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Po-Chieh Lin","raw_affiliation_strings":["National Taiwan University,Department of Electrical Engineering"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Department of Electrical Engineering","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043885374","display_name":"Sy\u2010Yen Kuo","orcid":"https://orcid.org/0000-0002-3021-8321"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Sy-Yen Kuo","raw_affiliation_strings":["National Taiwan University,Department of Electrical Engineering"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Department of Electrical Engineering","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111049508"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24921323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.8353000283241272,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.8353000283241272,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.7950999736785889,"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":0.7670999765396118,"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/speedup","display_name":"Speedup","score":0.6826000213623047},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.6015999913215637},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.5802000164985657},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.5753999948501587},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5737000107765198},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5051000118255615},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.43540000915527344},{"id":"https://openalex.org/keywords/idle","display_name":"Idle","score":0.4018999934196472},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.38199999928474426},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.3646000027656555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8554999828338623},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7070000171661377},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6826000213623047},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6015999913215637},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.5802000164985657},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.5753999948501587},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5737000107765198},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5051000118255615},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4611000120639801},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C16320812","wikidata":"https://www.wikidata.org/wiki/Q1812200","display_name":"Idle","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C61455927","wikidata":"https://www.wikidata.org/wiki/Q1030529","display_name":"Blossom algorithm","level":3,"score":0.36090001463890076},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.3601999878883362},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C194051981","wikidata":"https://www.wikidata.org/wiki/Q1337691","display_name":"Economic shortage","level":3,"score":0.34040001034736633},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C88468194","wikidata":"https://www.wikidata.org/wiki/Q1172416","display_name":"Data-flow analysis","level":3,"score":0.31940001249313354},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.302700012922287},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C184596265","wikidata":"https://www.wikidata.org/wiki/Q2651576","display_name":"Model of computation","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C11644782","wikidata":"https://www.wikidata.org/wiki/Q15401790","display_name":"Cost efficiency","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec67600.2025.11196651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec67600.2025.11196651","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,110],"push-relabel":[1,39,199],"algorithm":[2,6,40,129],"is":[3,191],"an":[4],"efficient":[5],"that":[7],"solves":[8],"the":[9,20,35,38,55,59,62,73,77,84,87,107,115,123,133,140,143,146,148,154,158,172,198],"maximum":[10,182],"flow/minimum":[11],"cut":[12],"problems":[13],"of":[14,22,37,61,86,127,135,142],"its":[15],"affinity":[16],"to":[17,33,105,164,171],"parallelization.":[18],"As":[19],"size":[21],"graphs":[23,180],"grows":[24],"exponentially,":[25],"researchers":[26],"have":[27],"used":[28],"Graphics":[29],"Processing":[30],"Units":[31],"(GPUs)":[32],"accelerate":[34],"computation":[36],"further.":[41],"However,":[42],"prior":[43],"works":[44],"suffer":[45],"from":[46],"a":[47,91],"significant":[48],"imbalanced":[49],"workload":[50,108],"distribution":[51],"while":[52,157],"computing":[53],"with":[54,76,98],"GPU,":[56],"which":[57],"reduces":[58,114],"utilization":[60,141],"GPU":[63],"and":[64,138,166,178,184],"increases":[65],"execution":[66,155],"time.":[67],"Therefore,":[68],"this":[69],"paper":[70],"first":[71],"identifies":[72],"two":[74,99],"challenges":[75],"cost":[78],"model":[79],"we":[80,89],"designed.":[81],"Based":[82],"on":[83,175,196],"observation":[85],"model,":[88],"propose":[90],"novel":[92],"two-level":[93,124],"parallelism":[94,125],"neighbor":[95],"scanning":[96],"(TLPNS)":[97],"enhanced":[100,111,149,176],"compressed":[101],"sparse":[102],"representations":[103],"(CSR)":[104],"alleviate":[106],"imbalance.":[109],"CSR":[112],"significantly":[113,152],"time":[116],"spent":[117],"searching":[118],"for":[119,193],"minimum-height":[120],"neighbors.":[121],"Additionally,":[122],"approach":[126],"our":[128],"can":[130,151,160],"effectively":[131],"reduce":[132],"number":[134],"idle":[136],"threads":[137],"improve":[139],"GPU.":[144],"In":[145],"experiment,":[147],"CSRs":[150,177],"decrease":[153],"time,":[156],"TLPNS":[159],"further":[161,194],"achieve":[162],"up":[163],"23x":[165],"6.9x":[167],"runtime":[168],"speedup":[169],"compared":[170],"state-of-the-art":[173],"work":[174],"real-world":[179],"in":[181],"flow":[183],"bipartite":[185],"matching":[186],"tasks,":[187],"respectively.":[188],"Our":[189],"code":[190],"open-sourced":[192],"research":[195],"accelerating":[197],"algorithm.":[200]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-16T00:00:00"}