{"id":"https://openalex.org/W4312726386","doi":"https://doi.org/10.1109/tcad.2022.3232467","title":"A Unified Engine for Accelerating GNN Weighting/Aggregation Operations, With Efficient Load Balancing and Graph-Specific Caching","display_name":"A Unified Engine for Accelerating GNN Weighting/Aggregation Operations, With Efficient Load Balancing and Graph-Specific Caching","publication_year":2022,"publication_date":"2022-12-27","ids":{"openalex":"https://openalex.org/W4312726386","doi":"https://doi.org/10.1109/tcad.2022.3232467"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2022.3232467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2022.3232467","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and 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/A5076919222","display_name":"Sudipta Mondal","orcid":"https://orcid.org/0000-0001-6521-2344"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sudipta Mondal","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA"],"raw_orcid":"https://orcid.org/0000-0001-6521-2344","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004590102","display_name":"Susmita Dey Manasi","orcid":"https://orcid.org/0000-0001-9358-6255"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Susmita Dey Manasi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA"],"raw_orcid":"https://orcid.org/0000-0001-9358-6255","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063963932","display_name":"Kishor Kunal","orcid":"https://orcid.org/0000-0003-3510-9850"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kishor Kunal","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA"],"raw_orcid":"https://orcid.org/0000-0003-3510-9850","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002036272","display_name":"S Ramprasath","orcid":"https://orcid.org/0000-0001-9487-9340"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramprasath S.","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA"],"raw_orcid":"https://orcid.org/0000-0001-9487-9340","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022067893","display_name":"Ziqing Zeng","orcid":"https://orcid.org/0000-0002-6981-2299"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziqing Zeng","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA"],"raw_orcid":"https://orcid.org/0000-0002-6981-2299","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068714995","display_name":"Sachin S. Sapatnekar","orcid":"https://orcid.org/0000-0002-5353-2364"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sachin S. Sapatnekar","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA"],"raw_orcid":"https://orcid.org/0000-0002-5353-2364","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5076919222"],"corresponding_institution_ids":["https://openalex.org/I130238516"],"apc_list":null,"apc_paid":null,"fwci":0.9711,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80310841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"42","issue":"12","first_page":"4844","last_page":"4857"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9968000054359436,"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":0.9797000288963318,"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":0.6998300552368164},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5015206336975098},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4767276346683502},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4659871459007263},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4332059919834137},{"id":"https://openalex.org/keywords/adjacency-matrix","display_name":"Adjacency matrix","score":0.4241962730884552},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.41791489720344543},{"id":"https://openalex.org/keywords/vertex","display_name":"Vertex (graph theory)","score":0.4164005517959595},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4040690064430237},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27106791734695435}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6998300552368164},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5015206336975098},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4767276346683502},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4659871459007263},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4332059919834137},{"id":"https://openalex.org/C180356752","wikidata":"https://www.wikidata.org/wiki/Q727035","display_name":"Adjacency matrix","level":3,"score":0.4241962730884552},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.41791489720344543},{"id":"https://openalex.org/C80899671","wikidata":"https://www.wikidata.org/wiki/Q1304193","display_name":"Vertex (graph theory)","level":3,"score":0.4164005517959595},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4040690064430237},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27106791734695435}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2022.3232467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2022.3232467","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.44999998807907104,"display_name":"Affordable and clean energy"}],"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":35,"referenced_works":["https://openalex.org/W2034861439","https://openalex.org/W2042519306","https://openalex.org/W2153959628","https://openalex.org/W2155729921","https://openalex.org/W2282294254","https://openalex.org/W2289252105","https://openalex.org/W2484446135","https://openalex.org/W2612654866","https://openalex.org/W2623629680","https://openalex.org/W2884496840","https://openalex.org/W2950656546","https://openalex.org/W2962865652","https://openalex.org/W3016507252","https://openalex.org/W3017228913","https://openalex.org/W3047846843","https://openalex.org/W3091862797","https://openalex.org/W3105753905","https://openalex.org/W3157609068","https://openalex.org/W3162147375","https://openalex.org/W3213228850","https://openalex.org/W3214431650","https://openalex.org/W3214705685","https://openalex.org/W4205993941","https://openalex.org/W4241140669","https://openalex.org/W4287829537","https://openalex.org/W6637178625","https://openalex.org/W6638659379","https://openalex.org/W6720006811","https://openalex.org/W6726873649","https://openalex.org/W6738901727","https://openalex.org/W6738964360","https://openalex.org/W6754929296","https://openalex.org/W6774097426","https://openalex.org/W6795324226","https://openalex.org/W6797677657"],"related_works":["https://openalex.org/W4377019474","https://openalex.org/W2317245370","https://openalex.org/W4249323025","https://openalex.org/W198851386","https://openalex.org/W2030310580","https://openalex.org/W947442053","https://openalex.org/W1980160788","https://openalex.org/W4281939267","https://openalex.org/W2148915962","https://openalex.org/W2283866686"],"abstract_inverted_index":{"Graph":[0],"neural":[1],"networks":[2,172,176],"(GNNs)":[3],"analysis":[4],"engines":[5],"are":[6],"vital":[7],"for":[8,17,205],"real-world":[9,124],"problems":[10],"that":[11,119],"use":[12],"large":[13],"graph":[14,43,125,170,174],"models.":[15],"Challenges":[16],"a":[18,28,82,107,114,153,164],"GNN":[19],"hardware":[20],"platform":[21],"include":[22],"the":[23,42,47,59],"ability":[24],"to":[25,80,123,138,183],"1)":[26,92],"host":[27],"variety":[29],"of":[30,61,85,144,191,215],"GNNs;":[31],"2)":[32,99],"handle":[33],"high":[34,66],"sparsity":[35,67],"in":[36,58],"input":[37],"vertex":[38,70,94],"feature":[39,95],"vectors":[40],"and":[41,46,53,68,101,104,133,155,180,208],"adjacency":[44],"matrix":[45],"accompanying":[48],"random":[49,135],"memory":[50,136],"access":[51,137],"patterns;":[52],"3)":[54,105],"maintain":[55],"load-balanced":[56],"computation":[57],"face":[60],"uneven":[62],"workloads,":[63],"induced":[64],"by":[65,91],"power-law":[69],"degree":[71],"distributions.":[72],"This":[73],"article":[74],"proposes":[75],"GNNIE,":[76],"an":[77,188,212],"accelerator":[78],"designed":[79],"run":[81],"broad":[83],"range":[84],"GNNs.":[86],"It":[87,112],"tackles":[88],"workload":[89],"imbalance":[90],"splitting":[93],"operands":[96],"into":[97],"blocks;":[98],"reordering":[100],"redistributing":[102],"computations;":[103],"using":[106,230],"novel":[108],"flexible":[109],"MAC":[110],"architecture.":[111],"adopts":[113],"graph-specific,":[115],"degree-aware":[116],"caching":[117],"policy":[118,128],"is":[120],"well":[121],"suited":[122],"characteristics.":[126],"The":[127],"enhances":[129],"on-chip":[130],"data":[131],"reuse":[132],"avoids":[134],"DRAM.":[139],"GNNIE":[140,186,210],"achieves":[141,187,211],"average":[142,189,213],"speedups":[143],"<inline-formula":[145,156,192,216,231],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[146,157,193,217,232],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[147,158,194,218,233],"<tex-math":[148,159,195,219,234],"notation=\"LaTeX\">$7197\\times":[149],"$":[150,161,197,221,236],"</tex-math></inline-formula>":[151,162,198,222,237],"over":[152,163,166,199,223],"CPU":[154],"notation=\"LaTeX\">$17.81\\times":[160],"GPU":[165],"multiple":[167],"datasets":[168],"on":[169],"attention":[171],"(GATs),":[173],"convolutional":[175],"(GCNs),":[177],"GraphSAGE,":[178,207],"GINConv,":[179],"DiffPool.":[181],"Compared":[182],"prior":[184],"approaches,":[185],"speedup":[190,214],"notation=\"LaTeX\">$5\\times":[196],"HyGCN":[200],"(which":[201,225],"cannot":[202],"implement":[203],"GATs)":[204],"GCN,":[206],"GINConv.":[209],"notation=\"LaTeX\">$1.3\\times":[220],"AWB-GCN":[224],"runs":[226],"only":[227],"GCNs),":[228],"despite":[229],"notation=\"LaTeX\">$3.4\\times":[235],"fewer":[238],"processing":[239],"units.":[240]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}