{"id":"https://openalex.org/W4416148779","doi":"https://doi.org/10.1109/tpds.2025.3632073","title":"DAHBM-GCN: A Flexible Graph Convolution Network Accelerator With Multiple Dataflows and HBM","display_name":"DAHBM-GCN: A Flexible Graph Convolution Network Accelerator With Multiple Dataflows and HBM","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416148779","doi":"https://doi.org/10.1109/tpds.2025.3632073"},"language":null,"primary_location":{"id":"doi:10.1109/tpds.2025.3632073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2025.3632073","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5101669669","display_name":"Zhang Xian","orcid":"https://orcid.org/0000-0003-3456-3701"},"institutions":[{"id":"https://openalex.org/I12393601","display_name":"Huaihua University","ror":"https://ror.org/04zn6xq74","country_code":"CN","type":"education","lineage":["https://openalex.org/I12393601"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xian Zhang","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Huaihua University, Huaihua, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Huaihua University, Huaihua, China","institution_ids":["https://openalex.org/I12393601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107094004","display_name":"Guoqing Xiao","orcid":"https://orcid.org/0000-0001-5008-4829"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqing Xiao","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662067","display_name":"Jiapeng Zhang","orcid":"https://orcid.org/0000-0002-0364-3568"},"institutions":[{"id":"https://openalex.org/I12393601","display_name":"Huaihua University","ror":"https://ror.org/04zn6xq74","country_code":"CN","type":"education","lineage":["https://openalex.org/I12393601"]},{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiapeng Zhang","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","School of Computer and Artificial Intelligence, Huaihua University, Huaihua, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Huaihua University, Huaihua, China","institution_ids":["https://openalex.org/I12393601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090246160","display_name":"Mingxing Duan","orcid":"https://orcid.org/0000-0002-1049-6244"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxing Duan","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078793726","display_name":"Kenli Li","orcid":"https://orcid.org/0000-0002-2635-7716"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kenli Li","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101669669"],"corresponding_institution_ids":["https://openalex.org/I12393601"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33692528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"1","first_page":"213","last_page":"229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.6557000279426575,"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":0.6557000279426575,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.2799000144004822,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T14347","display_name":"Big Data and Digital Economy","score":0.008899999782443047,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/dataflow","display_name":"Dataflow","score":0.8515999913215637},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5602999925613403},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5227000117301941},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5128999948501587},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.3797000050544739},{"id":"https://openalex.org/keywords/graph-bandwidth","display_name":"Graph bandwidth","score":0.3790999948978424},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.3702000081539154},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.36250001192092896},{"id":"https://openalex.org/keywords/data-flow-analysis","display_name":"Data-flow analysis","score":0.3587000072002411}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8694999814033508},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8515999913215637},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5602999925613403},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5227000117301941},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5128999948501587},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47589999437332153},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4415999948978424},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C134727501","wikidata":"https://www.wikidata.org/wiki/Q5597073","display_name":"Graph bandwidth","level":5,"score":0.3790999948978424},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3596000075340271},{"id":"https://openalex.org/C88468194","wikidata":"https://www.wikidata.org/wiki/Q1172416","display_name":"Data-flow analysis","level":3,"score":0.3587000072002411},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.358599990606308},{"id":"https://openalex.org/C2986651925","wikidata":"https://www.wikidata.org/wiki/Q1514868","display_name":"Graph algorithms","level":3,"score":0.3424000144004822},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.3057999908924103},{"id":"https://openalex.org/C48903430","wikidata":"https://www.wikidata.org/wiki/Q491370","display_name":"Graph partition","level":3,"score":0.305400013923645},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3021000027656555},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2720000147819519},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C558772884","wikidata":"https://www.wikidata.org/wiki/Q1508564","display_name":"Graph rewriting","level":3,"score":0.25200000405311584},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2025.3632073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2025.3632073","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3653478790","display_name":null,"funder_award_id":"2023JJ50457","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"},{"id":"https://openalex.org/G4221925008","display_name":null,"funder_award_id":"CSTB2022NSCQ-MSX1213","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"},{"id":"https://openalex.org/G4700541222","display_name":null,"funder_award_id":"2024JJ6154","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"}],"funders":[{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null},{"id":"https://openalex.org/F4320323172","display_name":"Natural Science Foundation of Chongqing","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2979310060","https://openalex.org/W3000310304","https://openalex.org/W3016832937","https://openalex.org/W3017228913","https://openalex.org/W3103168911","https://openalex.org/W3105753905","https://openalex.org/W3136941290","https://openalex.org/W3152893301","https://openalex.org/W3157609068","https://openalex.org/W3172512547","https://openalex.org/W3188218896","https://openalex.org/W3201267481","https://openalex.org/W3211236454","https://openalex.org/W3211445324","https://openalex.org/W4200157451","https://openalex.org/W4200504397","https://openalex.org/W4205993941","https://openalex.org/W4211038054","https://openalex.org/W4225660637","https://openalex.org/W4226137788","https://openalex.org/W4226439885","https://openalex.org/W4280509186","https://openalex.org/W4280551927","https://openalex.org/W4306167924","https://openalex.org/W4309022712","https://openalex.org/W4312305797","https://openalex.org/W4312779330","https://openalex.org/W4319990426","https://openalex.org/W4327503237","https://openalex.org/W4360831960","https://openalex.org/W4379115974","https://openalex.org/W4379116054","https://openalex.org/W4381327268","https://openalex.org/W4388145402","https://openalex.org/W4389166781"],"related_works":[],"abstract_inverted_index":{"Graph-structured":[0],"data":[1],"has":[2,17],"been":[3],"widely":[4],"applied":[5],"in":[6,45],"transportation,":[7],"molecular,":[8],"and":[9,32,71,89,135,155,180,185,196,209,223],"e-commerce":[10],"networks,":[11],"etc.":[12],"Graph":[13],"Convolutional":[14],"Network":[15],"(GCN)":[16],"emerged":[18],"as":[19],"an":[20,93,116],"efficient":[21,117],"approach":[22],"to":[23,108,128,183,191],"processing":[24],"non-Euclidean":[25],"graph":[26,35,50],"data.":[27],"However,":[28],"the":[29,39,42,49,54,97,103,110,150,192,218],"varying":[30],"sizes":[31],"sparsity":[33],"of":[34,41,56,119,162,178,205,220],"datasets,":[36,173],"coupled":[37],"with":[38,158],"dependency":[40],"dataflow":[43,112],"patterns":[44],"GCN":[46,57,65,145,151],"computation":[47,153],"on":[48,69,102,187,212],"data,":[51],"have":[52],"rendered":[53],"acceleration":[55],"inference":[58,66],"increasingly":[59],"challenging.":[60],"This":[61],"paper":[62],"proposes":[63],"a":[64,81,139],"accelerator":[67],"based":[68,101],"multi-dataflow":[70,98],"high":[72,221],"bandwidth":[73,136],"memory":[74,133],"(HBM),":[75],"named":[76],"DAHBM-GCN.":[77],"Firstly,":[78],"we":[79],"designed":[80],"computing":[82,99,113],"engine":[83,100],"that":[84,170],"supports":[85],"multiple":[86],"dataflows,":[87],"aggregation-first,":[88],"combination-first":[90],"orders.":[91],"Furthermore,":[92],"adaptive":[94],"selector":[95],"for":[96,123,144],"decision":[104],"tree":[105],"is":[106,126,146],"proposed":[107],"select":[109],"optimal":[111],"engine.":[114],"Secondly,":[115],"mapping":[118],"pseudo":[120],"channels":[121],"(PCs)":[122],"multi-channel":[124],"HBM":[125],"devised":[127],"enhance":[129],"bandwidth,":[130],"effectively":[131],"alleviating":[132],"latency":[134],"bottlenecks.":[137],"Thirdly,":[138],"hybrid":[140],"fixed-point":[141],"quantization":[142],"strategy":[143],"introduced,":[147],"which":[148],"reduces":[149],"model's":[152],"complexity":[154],"parameter":[156],"count":[157],"almost":[159],"no":[160],"loss":[161],"accuracy.":[163],"Finally,":[164],"extensive":[165],"performance":[166],"evaluation":[167],"experiments":[168],"demonstrate":[169],"across":[171],"various":[172,213],"DAHBM-GCN":[174,200,216],"achieved":[175],"average":[176,203],"speedups":[177,204],"52.5\u2013129.3\u00d7":[179],"4.9\u20137.9\u00d7":[181],"compared":[182],"PyG-GCN":[184],"DGL-GCN":[186],"CPU,":[188],"respectively.":[189],"Compared":[190],"AWB-GCN,":[193],"HyGCN,":[194],"HLS-GCN,":[195],"GCNAX":[197],"accelerators":[198],"FPGA-based,":[199],"also":[201],"exhibits":[202],"1.21\u20132.21\u00d7,":[206],"1.25\u20131.98\u00d7,":[207],"1.65\u20132.68\u00d7,":[208],"1.18\u20131.56\u00d7":[210],"respectively,":[211],"datasets.":[214],"Additionally,":[215],"possesses":[217],"advantages":[219],"flexibility":[222],"low":[224],"energy":[225],"consumption.":[226]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-12T00:00:00"}