{"id":"https://openalex.org/W4406251082","doi":"https://doi.org/10.1145/3711925","title":"gHyPart: GPU-friendly End-to-End Hypergraph Partitioner","display_name":"gHyPart: GPU-friendly End-to-End Hypergraph Partitioner","publication_year":2025,"publication_date":"2025-01-10","ids":{"openalex":"https://openalex.org/W4406251082","doi":"https://doi.org/10.1145/3711925"},"language":"en","primary_location":{"id":"doi:10.1145/3711925","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711925","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1145/3711925","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102909989","display_name":"Zhenlin Wu","orcid":"https://orcid.org/0009-0006-6348-5211"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhenlin Wu","raw_affiliation_strings":["The Hong Kong University of Science and Technology - Guangzhou Campus, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-6348-5211","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology - Guangzhou Campus, Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063048955","display_name":"Haosong Zhao","orcid":"https://orcid.org/0009-0000-4735-4015"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haosong Zhao","raw_affiliation_strings":["The Hong Kong University of Science and Technology - Guangzhou Campus, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-4735-4015","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology - Guangzhou Campus, Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079275912","display_name":"Hongyuan Liu","orcid":"https://orcid.org/0000-0002-6961-6394"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyuan Liu","raw_affiliation_strings":["The Hong Kong University of Science and Technology - Guangzhou Campus, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6961-6394","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology - Guangzhou Campus, Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103129518","display_name":"Wujie Wen","orcid":"https://orcid.org/0000-0003-3440-1905"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wujie Wen","raw_affiliation_strings":["North Carolina State University at Raleigh, Raleigh, United States"],"raw_orcid":"https://orcid.org/0000-0003-3440-1905","affiliations":[{"raw_affiliation_string":"North Carolina State University at Raleigh, Raleigh, United States","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100454305","display_name":"Jiajia Li","orcid":"https://orcid.org/0000-0003-1270-4147"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiajia Li","raw_affiliation_strings":["North Carolina State University at Raleigh, Raleigh, United States"],"raw_orcid":"https://orcid.org/0000-0003-1270-4147","affiliations":[{"raw_affiliation_string":"North Carolina State University at Raleigh, Raleigh, United States","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102909989"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3062,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78268659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"22","issue":"1","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9991000294685364,"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":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7462401390075684},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7387843132019043},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5799620151519775},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5681869983673096},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.49641138315200806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2112646996974945}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7462401390075684},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387843132019043},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5799620151519775},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5681869983673096},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.49641138315200806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2112646996974945}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711925","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711925","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3711925","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711925","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1685950412","display_name":null,"funder_award_id":"#62302416","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4820524457","display_name":null,"funder_award_id":"62302416","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323537","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1978226299","https://openalex.org/W2000041758","https://openalex.org/W2022844803","https://openalex.org/W2032145219","https://openalex.org/W2053902150","https://openalex.org/W2078174680","https://openalex.org/W2109539905","https://openalex.org/W2118953734","https://openalex.org/W2127927798","https://openalex.org/W2142184646","https://openalex.org/W2145374351","https://openalex.org/W2260987415","https://openalex.org/W2288539294","https://openalex.org/W2340222647","https://openalex.org/W2436525433","https://openalex.org/W2808934018","https://openalex.org/W2912007486","https://openalex.org/W2915012400","https://openalex.org/W2916260876","https://openalex.org/W2945592068","https://openalex.org/W2990320905","https://openalex.org/W2998830375","https://openalex.org/W3005044149","https://openalex.org/W3111098492","https://openalex.org/W3117864297","https://openalex.org/W3167683174","https://openalex.org/W3211181114","https://openalex.org/W4200208073","https://openalex.org/W4226435553","https://openalex.org/W4235965948","https://openalex.org/W4236104888","https://openalex.org/W4239027469","https://openalex.org/W4244850198","https://openalex.org/W4249498220","https://openalex.org/W4250102534","https://openalex.org/W4309764772","https://openalex.org/W4362508216","https://openalex.org/W4376272906","https://openalex.org/W4387461247","https://openalex.org/W4392680915","https://openalex.org/W4401408827","https://openalex.org/W4404133525","https://openalex.org/W6704526361","https://openalex.org/W6752105272"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2005148983","https://openalex.org/W2012954338","https://openalex.org/W2096672917","https://openalex.org/W2392023973","https://openalex.org/W3189307731","https://openalex.org/W1428699136","https://openalex.org/W2949962288","https://openalex.org/W2364686214","https://openalex.org/W1998560227"],"abstract_inverted_index":{"Hypergraph":[0],"partitioning":[1,14,44,90],"finds":[2],"practical":[3],"applications":[4],"in":[5,15,37,42],"various":[6,137],"fields,":[7],"such":[8],"as":[9],"high-performance":[10,20],"computing":[11],"and":[12,66,108,170,180],"circuit":[13],"VLSI":[16],"physical":[17],"design,":[18],"where":[19],"solutions":[21,30],"often":[22],"demand":[23],"substantial":[24],"parallelism":[25],"beyond":[26],"what":[27],"existing":[28],"CPU-based":[29],"can":[31],"offer.":[32],"While":[33],"GPUs":[34],"are":[35],"promising":[36],"this":[38,48],"regard,":[39],"their":[40],"potential":[41],"hypergraph":[43,56,89],"remains":[45],"unexplored.":[46],"In":[47],"work,":[49,65],"we":[50,116,140],"first":[51,79],"develop":[52],"an":[53],"end-to-end":[54,80],"deterministic":[55],"partitioner":[57],"on":[58,91,156,164,168,173],"GPUs,":[59],"ported":[60],"from":[61],"state-of-the-art":[62],"multi-threaded":[63],"CPU":[64,178],"identify":[67],"three":[68],"major":[69],"performance":[70],"challenges":[71,96],"by":[72],"characterizing":[73],"its":[74],"performance.":[75],"We":[76],"propose":[77,141],"the":[78,86,95,130],"solution,":[81],"gHyPart":[82],",":[83,185],"to":[84,102,113,128,146,161],"unleash":[85],"potentials":[87],"of":[88,97,132],"GPUs.":[92],"To":[93],"overcome":[94],"GPU":[98,118,182],"thread":[99],"underutilization":[100],"due":[101,112],"imbalanced":[103],"workload,":[104],"long":[105],"critical":[106],"path,":[107],"high":[109],"work":[110],"complexity":[111],"excessive":[114],"operations,":[115],"redesign":[117],"algorithms":[119],"with":[120],"diverse":[121],"parallelization":[122,150],"strategies":[123],"thus":[124],"expanding":[125],"optimization":[126],"space;":[127],"address":[129],"challenge":[131],"no":[133],"one-size-fits-all":[134],"implementation":[135],"for":[136,152],"input":[138],"hypergraphs,":[139],"a":[142,148],"decision":[143],"tree-based":[144],"strategy":[145,151],"choose":[147],"suitable":[149],"each":[153],"kernel.":[154],"Evaluation":[155],"500":[157],"hypergraphs":[158],"shows":[159],"up":[160],"125.7\u00d7":[162],"(17.5\u00d7":[163],"average),":[165,169],"640.0\u00d7":[166],"(24.2\u00d7":[167],"171.6\u00d7":[171],"(1.4\u00d7":[172],"average)":[174],"speedups":[175],"over":[176],"two":[177],"partitioners":[179],"our":[181],"baseline":[183],"gHyPart-B":[184],"respectively.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-01-11T00:00:00"}