{"id":"https://openalex.org/W4389166781","doi":"https://doi.org/10.1109/iccad57390.2023.10323722","title":"Accel-GCN: High-Performance GPU Accelerator Design for Graph Convolution Networks","display_name":"Accel-GCN: High-Performance GPU Accelerator Design for Graph Convolution Networks","publication_year":2023,"publication_date":"2023-10-28","ids":{"openalex":"https://openalex.org/W4389166781","doi":"https://doi.org/10.1109/iccad57390.2023.10323722"},"language":"en","primary_location":{"id":"doi:10.1109/iccad57390.2023.10323722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad57390.2023.10323722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD)","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/A5100642400","display_name":"Xie Xi","orcid":"https://orcid.org/0000-0003-2109-2816"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xi Xie","raw_affiliation_strings":["University of Connecticut"],"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045835605","display_name":"Hongwu Peng","orcid":"https://orcid.org/0000-0003-2025-2195"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongwu Peng","raw_affiliation_strings":["University of Connecticut"],"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109633079","display_name":"Amit Hasan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amit Hasan","raw_affiliation_strings":["University of Connecticut"],"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073345631","display_name":"Shaoyi Huang","orcid":"https://orcid.org/0000-0001-6093-9798"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaoyi Huang","raw_affiliation_strings":["University of Connecticut"],"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068081890","display_name":"Jiahui Zhao","orcid":"https://orcid.org/0000-0001-5359-3709"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahui Zhao","raw_affiliation_strings":["University of Connecticut"],"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112473990","display_name":"Haowen Fang","orcid":"https://orcid.org/0009-0009-7551-3373"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haowen Fang","raw_affiliation_strings":["University of Connecticut"],"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079321466","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-8947-9067"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["University of Connecticut"],"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078443672","display_name":"Tong Geng","orcid":"https://orcid.org/0000-0002-3644-2922"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong Geng","raw_affiliation_strings":["University of Rochester"],"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048129220","display_name":"Omer Khan","orcid":"https://orcid.org/0000-0001-6293-7403"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Omer Khan","raw_affiliation_strings":["University of Connecticut"],"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030060072","display_name":"Caiwen Ding","orcid":"https://orcid.org/0000-0003-0891-1231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caiwen Ding","raw_affiliation_strings":["University of Connecticut"],"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5100642400"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6153,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.91892048,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"09"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9994999766349792,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9990000128746033,"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/T11478","display_name":"Caching and Content Delivery","score":0.9896000027656555,"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/computer-science","display_name":"Computer science","score":0.8521006107330322},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7210226655006409},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48816972970962524},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.41266608238220215},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33578717708587646},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15377873182296753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8521006107330322},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7210226655006409},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48816972970962524},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.41266608238220215},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33578717708587646},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15377873182296753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad57390.2023.10323722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad57390.2023.10323722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1762731526","https://openalex.org/W1985312666","https://openalex.org/W2040404421","https://openalex.org/W2060778826","https://openalex.org/W2099625934","https://openalex.org/W2162707967","https://openalex.org/W2165854233","https://openalex.org/W2259950804","https://openalex.org/W2294347342","https://openalex.org/W2484446135","https://openalex.org/W2755088640","https://openalex.org/W2796649226","https://openalex.org/W2808128431","https://openalex.org/W2904192253","https://openalex.org/W2952269378","https://openalex.org/W2962711740","https://openalex.org/W2962812689","https://openalex.org/W2964015378","https://openalex.org/W2964337156","https://openalex.org/W2996084050","https://openalex.org/W2999347085","https://openalex.org/W3003537320","https://openalex.org/W3035492435","https://openalex.org/W3092125438","https://openalex.org/W3097300053","https://openalex.org/W3100078588","https://openalex.org/W3105753905","https://openalex.org/W3110933132","https://openalex.org/W3123909522","https://openalex.org/W3132695675","https://openalex.org/W3206743063","https://openalex.org/W4288419263","https://openalex.org/W4294558607","https://openalex.org/W4296300780","https://openalex.org/W4381894545","https://openalex.org/W6675533150","https://openalex.org/W6726873649","https://openalex.org/W6738964360","https://openalex.org/W6750448596","https://openalex.org/W6754929296","https://openalex.org/W6760045743","https://openalex.org/W6772320042","https://openalex.org/W6773836183","https://openalex.org/W6776488958","https://openalex.org/W6779827936"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W2990194547"],"abstract_inverted_index":{"Graph":[0],"Convolutional":[1],"Networks":[2],"(GCNs)":[3],"are":[4],"pivotal":[5],"in":[6,100,116],"extracting":[7],"latent":[8],"information":[9],"from":[10],"graph":[11],"data":[12],"across":[13,147],"various":[14],"domains,":[15],"yet":[16],"their":[17],"acceleration":[18],"on":[19,185],"mainstream":[20],"GPUs":[21],"is":[22],"challenged":[23],"by":[24,138,159],"workload":[25,70,77],"imbalance":[26],"and":[27,76,79,97,122,130,134,142,157,164],"memory":[28,74,95,132,136,140],"access":[29],"irregularity.":[30],"To":[31],"address":[32],"these":[33,108],"challenges,":[34],"we":[35,110],"present":[36],"Accel-GCN,":[37],"a":[38,50,62,89,112],"GPU":[39],"accelerator":[40],"architecture":[41],"for":[42,114,175],"GCNs.":[43],"The":[44,167,180],"design":[45],"of":[46,104,145,161],"Accel-GCN":[47,146,170],"encompasses:":[48],"(i)":[49],"lightweight":[51],"degree":[52],"sorting":[53],"stage":[54],"to":[55,84],"group":[56],"nodes":[57],"with":[58],"similar":[59],"degree;":[60],"(ii)":[61],"block-level":[63,120],"partition":[64],"strategy":[65,92],"that":[66,93,118,152],"dynamically":[67],"adjusts":[68],"warp":[69,91,124],"sizes,":[71],"enhancing":[72,176],"shared":[73],"locality":[75],"balance,":[78],"reducing":[80],"metadata":[81],"overhead":[82],"compared":[83],"designs":[85],"like":[86],"GNNAdvisor;":[87],"(iii)":[88],"combined":[90,123],"improves":[94],"coalescing":[96,141],"computational":[98,178],"parallelism":[99],"the":[101],"column":[102],"dimension":[103],"dense":[105],"matrices.":[106],"Utilizing":[107],"principles,":[109],"formulate":[111],"kernel":[113],"SpMM":[115],"GCNs":[117],"employs":[119],"partitioning":[121],"strategy.":[125],"This":[126],"approach":[127],"augments":[128],"performance":[129],"multi-level":[131],"efficiency":[133],"optimizes":[135],"bandwidth":[137],"exploiting":[139],"alignment.":[143],"Evaluation":[144],"18":[148],"benchmark":[149],"graphs":[150],"reveals":[151],"it":[153],"outperforms":[154],"cuSPARSE,":[155],"GNNAdvisor,":[156],"graph-BLAST":[158],"factors":[160],"1.17\u00d7,":[162],"1.86\u00d7,":[163],"2.94\u00d7":[165],"respectively.":[166],"results":[168],"underscore":[169],"as":[171],"an":[172],"effective":[173],"solution":[174],"GCN":[177],"efficiency.":[179],"implementation":[181],"can":[182],"be":[183],"found":[184],"Github*.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":12}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}