{"id":"https://openalex.org/W4410949647","doi":"https://doi.org/10.1109/tsusc.2025.3575285","title":"HS-GCN: A High-Performance, Sustainable, and Scalable Chiplet-Based Accelerator for Graph Convolutional Network Inference","display_name":"HS-GCN: A High-Performance, Sustainable, and Scalable Chiplet-Based Accelerator for Graph Convolutional Network Inference","publication_year":2025,"publication_date":"2025-06-02","ids":{"openalex":"https://openalex.org/W4410949647","doi":"https://doi.org/10.1109/tsusc.2025.3575285"},"language":"en","primary_location":{"id":"doi:10.1109/tsusc.2025.3575285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsusc.2025.3575285","pdf_url":null,"source":{"id":"https://openalex.org/S4210221417","display_name":"IEEE Transactions on Sustainable Computing","issn_l":"2377-3782","issn":["2377-3782","2377-3790"],"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 Sustainable Computing","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/A5027724935","display_name":"Yingnan Zhao","orcid":"https://orcid.org/0000-0002-1761-3669"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yingnan Zhao","raw_affiliation_strings":["George Washington University, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025289290","display_name":"Ke Wang","orcid":"https://orcid.org/0000-0001-7189-9293"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Wang","raw_affiliation_strings":["University of North Carolina at Charlotte, Charlotte, NC, USA"],"affiliations":[{"raw_affiliation_string":"University of North Carolina at Charlotte, Charlotte, NC, USA","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034189643","display_name":"Ahmed Louri","orcid":"https://orcid.org/0000-0003-4262-6688"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed Louri","raw_affiliation_strings":["George Washington University, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027724935"],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":2.8599,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91107623,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"10","issue":"5","first_page":"1019","last_page":"1030"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9617000222206116,"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":0.9617000222206116,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9516000151634216,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9505000114440918,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7334250211715698},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6897302865982056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6700190305709839},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5706323385238647},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3295963406562805},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32411840558052063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3114428222179413},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10109817981719971}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7334250211715698},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6897302865982056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6700190305709839},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5706323385238647},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3295963406562805},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32411840558052063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3114428222179413},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10109817981719971}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsusc.2025.3575285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsusc.2025.3575285","pdf_url":null,"source":{"id":"https://openalex.org/S4210221417","display_name":"IEEE Transactions on Sustainable Computing","issn_l":"2377-3782","issn":["2377-3782","2377-3790"],"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 Sustainable Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1985818188","https://openalex.org/W2034822545","https://openalex.org/W2116341502","https://openalex.org/W2153959628","https://openalex.org/W2162630660","https://openalex.org/W2168190036","https://openalex.org/W2234584938","https://openalex.org/W2285660444","https://openalex.org/W2907492528","https://openalex.org/W2980104813","https://openalex.org/W3003265726","https://openalex.org/W3011667710","https://openalex.org/W3016507252","https://openalex.org/W3017228913","https://openalex.org/W3105753905","https://openalex.org/W3152893301","https://openalex.org/W3157609068","https://openalex.org/W3159222787","https://openalex.org/W3188178661","https://openalex.org/W3193327410","https://openalex.org/W3206743063","https://openalex.org/W4205993941","https://openalex.org/W4241140669","https://openalex.org/W4244395536","https://openalex.org/W4360831975","https://openalex.org/W4384159553","https://openalex.org/W4386764109","https://openalex.org/W4390783039","https://openalex.org/W4396941334"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W2965083567","https://openalex.org/W4235240664","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W2889616422","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385","https://openalex.org/W2357523926"],"abstract_inverted_index":{"Graph":[0],"Convolutional":[1],"Networks":[2],"(GCNs)":[3],"have":[4],"been":[5],"proposed":[6],"to":[7,57,82,131,165,204,261],"extend":[8],"machine":[9],"learning":[10],"techniques":[11],"for":[12,65,112,172,213],"graphrelated":[13],"applications.":[14],"A":[15],"typical":[16],"GCN":[17,54,113,198],"model":[18],"consists":[19],"of":[20,41,94,126,136,230,242,251],"multiple":[21,122],"layers,":[22],"each":[23,125],"including":[24,145],"an":[25,157],"aggregation":[26,139],"phase,":[27,34,144],"which":[28,35,71,127],"is":[29,36],"communication-intensive,":[30],"and":[31,61,69,74,97,108,150,168,189,197,210,216,248,266],"a":[32,105,161],"combination":[33,143],"computation-intensive.":[37],"As":[38],"the":[39,84,133,138,142,186,194,207],"size":[40],"real-world":[42,222],"graphs":[43,196,223],"increases":[44],"exponentially,":[45],"current":[46,79],"customized":[47],"accelerators":[48],"face":[49],"challenges":[50,86],"in":[51,92],"efficiently":[52],"performing":[53],"inference":[55,114],"due":[56],"limited":[58],"on-chip":[59],"buffers":[60],"other":[62,169],"hardware":[63,170],"resources":[64],"both":[66],"data":[67,174],"computation":[68,187],"communication,":[70],"degrades":[72],"performance":[73,215],"energy":[75,117,217,249],"efficiency.":[76,118,218],"Additionally,":[77,176],"scaling":[78],"monolithic":[80],"designs":[81],"address":[83],"aforementioned":[85],"will":[87],"introduce":[88],"significant":[89,228],"cost-effectiveness":[90],"issues":[91],"terms":[93],"power,":[95],"area,":[96],"yield.":[98],"To":[99],"this":[100],"end,":[101],"we":[102],"propose":[103],"HS-GCN,":[104],"high-performance,":[106],"sustainable,":[107],"scalable":[109],"chiplet-based":[110],"accelerator":[111],"with":[115,160,237],"muchimproved":[116],"Specifically,":[119],"HS-GCN":[120,155,177,226],"integrates":[121],"reconfigurable":[123],"chiplets,":[124],"can":[128],"be":[129],"configured":[130],"perform":[132],"main":[134],"computations":[135],"either":[137],"phase":[140],"or":[141],"Sparse-dense":[146],"matrix":[147],"multiplication":[148,153],"(SpMM)":[149],"General":[151],"matrix-matrix":[152],"(GeMM).":[154],"implements":[156],"active":[158],"interposer":[159],"flexible":[162],"interconnection":[163,211],"fabric":[164,212],"connect":[166],"chiplets":[167],"components":[171],"efficient":[173],"communication.":[175],"introduces":[178],"two":[179],"system-level":[180],"control":[181],"algorithms":[182],"that":[183,225],"dynamically":[184],"determine":[185],"order":[188],"corresponding":[190],"dataflow":[191],"based":[192],"on":[193,257],"input":[195],"models.":[199],"These":[200],"selections":[201],"are":[202],"used":[203],"further":[205],"configure":[206],"chiplet":[208],"array":[209],"much-improved":[214],"Evaluation":[219],"results":[220],"using":[221],"demonstrate":[224],"achieves":[227],"speedups":[229],"26.7\u00d7,":[231],"11.2\u00d7,":[232],"3.9\u00d7,":[233],"4.7\u00d7,":[234],"3.1\u00d7,":[235],"along":[236],"substantial":[238],"memory":[239],"access":[240],"savings":[241,250],"94%,":[243],"89%,":[244],"64%,":[245],"85%,":[246],"54%,":[247],"87%,":[252],"84%,":[253],"49%,":[254],"78%,":[255],"41%":[256],"average,":[258],"as":[259],"compared":[260],"HyGCN,":[262],"AWB-GCN,":[263],"GCNAX,":[264],"I-GCN,":[265],"SGCN,":[267],"respectively.":[268]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}