{"id":"https://openalex.org/W4413411834","doi":"https://doi.org/10.1145/3721145.3734528","title":"DR-CircuitGNN: Training Acceleration of Heterogeneous Circuit Graph Neural Network on GPUs","display_name":"DR-CircuitGNN: Training Acceleration of Heterogeneous Circuit Graph Neural Network on GPUs","publication_year":2025,"publication_date":"2025-06-08","ids":{"openalex":"https://openalex.org/W4413411834","doi":"https://doi.org/10.1145/3721145.3734528"},"language":"en","primary_location":{"id":"doi:10.1145/3721145.3734528","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3721145.3734528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.16769","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yuebo Luo","orcid":"https://orcid.org/0009-0005-1738-886X"},"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"]},{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]},{"id":"https://openalex.org/I4210101327","display_name":"Twin Cities Orthopedics","ror":"https://ror.org/01en4s460","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210101327"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuebo Luo","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Minnesota Twin Cities, Minneapolis, Minnesota, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Minnesota Twin Cities, Minneapolis, Minnesota, USA","institution_ids":["https://openalex.org/I4210101327","https://openalex.org/I130238516","https://openalex.org/I2800403580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037171702","display_name":"Shiyang Li","orcid":"https://orcid.org/0000-0003-3046-0414"},"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"]},{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]},{"id":"https://openalex.org/I4210101327","display_name":"Twin Cities Orthopedics","ror":"https://ror.org/01en4s460","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210101327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiyang Li","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Minnesota Twin Cities, Minneapolis, Minnesota, USA and Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Minnesota Twin Cities, Minneapolis, Minnesota, USA and Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I130238516","https://openalex.org/I2800403580","https://openalex.org/I4210101327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junran Tao","orcid":"https://orcid.org/0009-0009-8349-1194"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junran Tao","raw_affiliation_strings":["Stevens Institute of Technology, Hoboken, New Jersey, USA"],"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology, Hoboken, New Jersey, USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kiran Gautam Thorat","orcid":"https://orcid.org/0009-0005-9190-798X"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kiran Gautam Thorat","raw_affiliation_strings":["School of Computing, University of Connecticut, Storrs, CONNECTICUT, USA"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Connecticut, Storrs, CONNECTICUT, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103156629","display_name":"Xi Xie","orcid":"https://orcid.org/0009-0001-7489-2860"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xi Xie","raw_affiliation_strings":["School of Computing, University of Connecticut, Storrs, USA"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Connecticut, Storrs, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045835605","display_name":"Hongwu Peng","orcid":"https://orcid.org/0000-0003-2025-2195"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongwu Peng","raw_affiliation_strings":["School of Computing, University of Connecticut, Storrs, USA"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Connecticut, Storrs, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048064145","display_name":"Nuo Xu","orcid":"https://orcid.org/0000-0001-6148-2830"},"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"]},{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]},{"id":"https://openalex.org/I4210101327","display_name":"Twin Cities Orthopedics","ror":"https://ror.org/01en4s460","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210101327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nuo Xu","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Minnesota Twin Cities, Minneapolis, Minnesota, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Minnesota Twin Cities, Minneapolis, Minnesota, USA","institution_ids":["https://openalex.org/I4210101327","https://openalex.org/I130238516","https://openalex.org/I2800403580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030060072","display_name":"Caiwen Ding","orcid":"https://orcid.org/0000-0003-0891-1231"},"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"]},{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]},{"id":"https://openalex.org/I4210101327","display_name":"Twin Cities Orthopedics","ror":"https://ror.org/01en4s460","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210101327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caiwen Ding","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Minnesota Twin Cities, Minneapolis, Minnesota, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Minnesota Twin Cities, Minneapolis, Minnesota, USA","institution_ids":["https://openalex.org/I4210101327","https://openalex.org/I130238516","https://openalex.org/I2800403580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073345631","display_name":"Shaoyi Huang","orcid":"https://orcid.org/0000-0001-6093-9798"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaoyi Huang","raw_affiliation_strings":["Stevens Institute of Technology, Hoboken, New Jersey, USA"],"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology, Hoboken, New Jersey, USA","institution_ids":["https://openalex.org/I108468826"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130238516","https://openalex.org/I2800403580","https://openalex.org/I4210101327"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19795305,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"221","last_page":"235"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9954000115394592,"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":0.9954000115394592,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9952999949455261,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9951000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7442250847816467},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.6137943863868713},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5581336617469788},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5460798740386963},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5219823122024536},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47158563137054443},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.41424357891082764},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3638027310371399},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.35911059379577637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.322564959526062},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.20993942022323608},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.199467271566391},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.10499218106269836},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06915849447250366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7442250847816467},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.6137943863868713},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5581336617469788},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5460798740386963},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5219823122024536},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47158563137054443},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.41424357891082764},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3638027310371399},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.35911059379577637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.322564959526062},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.20993942022323608},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.199467271566391},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.10499218106269836},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06915849447250366},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3721145.3734528","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3721145.3734528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.16769","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.16769","pdf_url":"https://arxiv.org/pdf/2508.16769","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.16769","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.16769","pdf_url":"https://arxiv.org/pdf/2508.16769","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2161629461","https://openalex.org/W2626696598","https://openalex.org/W2990138404","https://openalex.org/W2992137891","https://openalex.org/W3013719760","https://openalex.org/W3021182071","https://openalex.org/W3103168911","https://openalex.org/W3105753905","https://openalex.org/W3106620263","https://openalex.org/W3138516171","https://openalex.org/W3171752851","https://openalex.org/W3198511427","https://openalex.org/W3200354549","https://openalex.org/W3211601069","https://openalex.org/W4210938977","https://openalex.org/W4293024038","https://openalex.org/W4312076525","https://openalex.org/W4366957262","https://openalex.org/W4381415966","https://openalex.org/W4396506070","https://openalex.org/W4402352460","https://openalex.org/W4404132963","https://openalex.org/W4408416674"],"related_works":["https://openalex.org/W2565094479","https://openalex.org/W2390829436","https://openalex.org/W1989791859","https://openalex.org/W602859758","https://openalex.org/W1971289376","https://openalex.org/W2379101322","https://openalex.org/W1992553864","https://openalex.org/W2776207444","https://openalex.org/W2146872326","https://openalex.org/W3158825072"],"abstract_inverted_index":{"The":[0],"increasing":[1],"scale":[2],"and":[3,77,94,125,164,191,200,207,231],"complexity":[4,56,93],"of":[5,57,89],"integrated":[6],"circuit":[7,47,69,138],"design":[8,32,119,212],"have":[9,23],"led":[10],"to":[11,29,52,98,132,189,195,215],"increased":[12],"challenges":[13],"in":[14],"Electronic":[15],"Design":[16],"Automation":[17],"(EDA).":[18],"Graph":[19,61],"Neural":[20,62],"Networks":[21,63],"(GNNs)":[22],"emerged":[24],"as":[25,33,39,71],"a":[26,44,105,115,147],"promising":[27],"approach":[28],"assist":[30],"EDA":[31,58,68],"circuits":[34],"can":[35,65,186],"be":[36],"naturally":[37],"represented":[38],"graphs.":[40],"While":[41],"GNNs":[42],"offer":[43],"foundation":[45],"for":[46,198],"analysis,":[48],"they":[49,72],"often":[50],"fail":[51],"capture":[53,73],"the":[54,81,87,183,196,220],"full":[55],"designs.":[59],"Heterogeneous":[60],"(HGNNs)":[64],"better":[66],"interpret":[67],"graphs":[70],"both":[74],"topological":[75],"relationships":[76],"geometric":[78],"features.":[79],"However,":[80],"improved":[82],"representation":[83],"capability":[84],"comes":[85],"at":[86],"cost":[88,96],"even":[90],"higher":[91],"computational":[92],"processing":[95,157],"due":[97],"their":[99],"serial":[100],"module-wise":[101],"message-passing":[102,131],"scheme,":[103],"creating":[104],"significant":[106],"performance":[107],"bottleneck.":[108],"In":[109],"this":[110],"paper,":[111],"we":[112,145],"propose":[113,146],"DR-CircuitGNN,":[114],"fast":[116],"GPU":[117,165],"kernel":[118,166],"by":[120,155],"leveraging":[121],"row-wise":[122],"sparsity-aware":[123],"Dynamic-ReLU":[124],"optimizing":[126],"SpMM":[127],"kernels":[128],"during":[129],"heterogeneous":[130],"accelerate":[133],"HGNNs":[134],"training":[135],"on":[136,175,228],"EDA-related":[137],"graph":[139],"datasets.":[140],"To":[141],"further":[142],"enhance":[143],"performance,":[144],"parallel":[148,211],"optimization":[149],"strategy":[150],"that":[151,174],"maximizes":[152],"CPU-GPU":[153],"concurrency":[154],"concurrently":[156],"independent":[158],"subgraphs":[159],"using":[160],"multi-threaded":[161],"CPU":[162],"initialization":[163],"execution":[167],"via":[168],"multiple":[169],"cudaStreams.":[170],"Our":[171],"experiments":[172],"show":[173],"three":[176],"representative":[177],"CircuitNet":[178,206],"designs":[179],"(small,":[180],"medium,":[181],"large),":[182],"proposed":[184],"method":[185],"achieve":[187],"up":[188,214,218],"3.51x":[190],"4.09x":[192],"speedup":[193],"compared":[194],"SOTA":[197],"forward":[199],"backward":[201],"propagation,":[202],"respectively.":[203],"On":[204],"full-size":[205],"sampled":[208],"Mini-CircuitNet,":[209],"our":[210],"enables":[213],"2.71x":[216],"speed":[217],"over":[219],"official":[221],"DGL":[222],"implementation":[223],"cuSPARSE":[224],"with":[225],"negligible":[226],"impact":[227],"correlation":[229],"scores":[230],"error":[232],"rates.":[233]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}