{"id":"https://openalex.org/W4394998407","doi":"https://doi.org/10.1145/3620665.3640426","title":"MaxK-GNN: Extremely Fast GPU Kernel Design for Accelerating Graph Neural Networks Training","display_name":"MaxK-GNN: Extremely Fast GPU Kernel Design for Accelerating Graph Neural Networks Training","publication_year":2024,"publication_date":"2024-04-22","ids":{"openalex":"https://openalex.org/W4394998407","doi":"https://doi.org/10.1145/3620665.3640426"},"language":"en","primary_location":{"id":"doi:10.1145/3620665.3640426","doi":"https://doi.org/10.1145/3620665.3640426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3620665.3640426","pdf_url":null,"source":{"id":"https://openalex.org/S7407086669","display_name":"International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2312.08656","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045835605","display_name":"Hongwu Peng","orcid":"https://orcid.org/0000-0003-2025-2195","observed_orcids":["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":["University of Connecticut, Storrs, Connecticut, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-2025-2195","affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, Connecticut, United States of America","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","observed_orcids":["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":["University of Connecticut, Storrs, Connecticut, USA"],"raw_orcid":"https://orcid.org/0009-0001-7489-2860","affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087616265","display_name":"Kaustubh Shivdikar","orcid":"https://orcid.org/0000-0002-4449-7974","observed_orcids":["https://orcid.org/0000-0002-4449-7974"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaustubh Shivdikar","raw_affiliation_strings":["Northeastern University, Boston, Massachusetts, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-4449-7974","affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, Massachusetts, United States of America","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078067207","display_name":"Md Amit Hasan","orcid":"https://orcid.org/0000-0001-8774-0228","observed_orcids":["https://orcid.org/0000-0001-8774-0228"]},"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":"Md Amit Hasan","raw_affiliation_strings":["University of Connecticut, Storrs, Connecticut, USA"],"raw_orcid":"https://orcid.org/0000-0001-8774-0228","affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040566649","display_name":"Jiahui Zhao","orcid":"https://orcid.org/0009-0000-0558-5579","observed_orcids":["https://orcid.org/0009-0000-0558-5579"]},"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":"Jiahui Zhao","raw_affiliation_strings":["University of Connecticut, Storrs, Connecticut, USA"],"raw_orcid":"https://orcid.org/0009-0000-0558-5579","affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073345631","display_name":"Shaoyi Huang","orcid":"https://orcid.org/0000-0001-6093-9798","observed_orcids":["https://orcid.org/0000-0001-6093-9798"]},"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":"Shaoyi Huang","raw_affiliation_strings":["University of Connecticut, Storrs, Connecticut, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-6093-9798","affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, Connecticut, United States of America","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048129220","display_name":"Omer Khan","orcid":"https://orcid.org/0000-0001-6293-7403","observed_orcids":["https://orcid.org/0000-0001-6293-7403"]},"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":"Omer Khan","raw_affiliation_strings":["University of Connecticut, Storrs, Connecticut, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-6293-7403","affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, Connecticut, United States of America","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061128237","display_name":"David R Kaeli","orcid":"https://orcid.org/0000-0002-5692-0151","observed_orcids":["https://orcid.org/0000-0002-5692-0151"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kaeli","raw_affiliation_strings":["Northeastern University, Boston, Massachusetts, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-5692-0151","affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, Massachusetts, United States of America","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030060072","display_name":"Caiwen Ding","orcid":"https://orcid.org/0000-0003-0891-1231","observed_orcids":["https://orcid.org/0000-0003-0891-1231"]},"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":"Caiwen Ding","raw_affiliation_strings":["University of Connecticut, Storrs, Connecticut, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-0891-1231","affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, Connecticut, United States of America","institution_ids":["https://openalex.org/I140172145"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.4276,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.99208582,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"683","last_page":"698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.7792999744415283,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.7792999744415283,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.20649999380111694,"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":0.005400000140070915,"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/graph-neural-networks","display_name":"graph neural networks","score":0.9359999895095825},{"id":"https://openalex.org/keywords/sparse-matrix-multiplication","display_name":"sparse matrix multiplication","score":0.5080000162124634},{"id":"https://openalex.org/keywords/memory-traffic","display_name":"memory traffic","score":0.5730000138282776},{"id":"https://openalex.org/keywords/workload-imbalance","display_name":"workload imbalance","score":0.6800000071525574},{"id":"https://openalex.org/keywords/training-acceleration","display_name":"training acceleration","score":0.6050000190734863},{"id":"https://openalex.org/keywords/hardware-utilization","display_name":"hardware resource utilization","score":0.4699999988079071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7930091023445129},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.7646500468254089},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.636329710483551},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5829098224639893},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5676220655441284},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5218271613121033},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.512444794178009},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5116193890571594},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49713805317878723},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.42051035165786743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3709754943847656},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3683964014053345},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3039506673812866},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2707091271877289},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.2655870318412781},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.20216432213783264},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13948655128479004},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3620665.3640426","doi":"https://doi.org/10.1145/3620665.3640426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3620665.3640426","pdf_url":null,"source":{"id":"https://openalex.org/S7407086669","display_name":"International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2312.08656","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.08656","pdf_url":"https://arxiv.org/pdf/2312.08656","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},{"id":"doi:10.48550/arxiv.2312.08656","doi":"https://doi.org/10.48550/arxiv.2312.08656","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.08656","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2312.08656","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.08656","pdf_url":"https://arxiv.org/pdf/2312.08656","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7310644176","display_name":"CAREER: Algorithm-Hardware Co-design of Efficient Large Graph Machine Learning for Electronic Design Automation","funder_award_id":"2340273","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394998407.pdf","grobid_xml":"https://content.openalex.org/works/W4394998407.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1980282429","https://openalex.org/W1984772269","https://openalex.org/W2125204570","https://openalex.org/W2142513626","https://openalex.org/W2294567968","https://openalex.org/W2484446135","https://openalex.org/W2519887557","https://openalex.org/W2593390416","https://openalex.org/W2624431344","https://openalex.org/W2792643794","https://openalex.org/W2796649226","https://openalex.org/W2798170643","https://openalex.org/W2805003733","https://openalex.org/W2807021761","https://openalex.org/W2808133870","https://openalex.org/W2918342466","https://openalex.org/W2945827377","https://openalex.org/W2956434358","https://openalex.org/W2961295589","https://openalex.org/W2970971581","https://openalex.org/W2996084050","https://openalex.org/W3021975806","https://openalex.org/W3034628778","https://openalex.org/W3035180000","https://openalex.org/W3035492435","https://openalex.org/W3042746444","https://openalex.org/W3047846843","https://openalex.org/W3090369187","https://openalex.org/W3091862797","https://openalex.org/W3092125438","https://openalex.org/W3097300053","https://openalex.org/W3103168911","https://openalex.org/W3105753905","https://openalex.org/W3110933132","https://openalex.org/W3123909522","https://openalex.org/W3129197243","https://openalex.org/W3130554079","https://openalex.org/W3133969519","https://openalex.org/W3158399077","https://openalex.org/W3200832253","https://openalex.org/W3206743063","https://openalex.org/W4211165432","https://openalex.org/W4214651231","https://openalex.org/W4226137788","https://openalex.org/W4312400543","https://openalex.org/W4318541522","https://openalex.org/W4360831816","https://openalex.org/W4360831960","https://openalex.org/W4367147545","https://openalex.org/W4381894545","https://openalex.org/W7099244549"],"related_works":["https://openalex.org/W4404455164","https://openalex.org/W4384705403","https://openalex.org/W4211165432","https://openalex.org/W7171443037","https://openalex.org/W4408222700","https://openalex.org/W7119360460","https://openalex.org/W4401211761","https://openalex.org/W4318328413","https://openalex.org/W3158399077","https://openalex.org/W4413430518"],"abstract_inverted_index":{"In":[0],"the":[1,8,15,55],"acceleration":[2],"of":[3],"deep":[4],"neural":[5],"network":[6],"training,":[7],"graphics":[9],"processing":[10],"unit":[11],"(GPU)":[12],"has":[13],"become":[14],"mainstream":[16],"platform.":[17],"GPUs":[18],"face":[19],"substantial":[20],"challenges":[21],"on":[22],"Graph":[23],"Neural":[24],"Networks":[25],"(GNNs),":[26],"such":[27,41],"as":[28,42],"workload":[29],"imbalance":[30],"and":[31,47],"memory":[32,56],"access":[33],"irregularities,":[34],"leading":[35],"to":[36],"underutilized":[37],"hardware.":[38],"Existing":[39],"solutions":[40],"PyG,":[43],"DGL":[44],"with":[45,59],"cuSPARSE,":[46],"GNNAdvisor":[48],"frameworks":[49],"partially":[50],"address":[51],"these":[52],"challenges.":[53],"However,":[54],"traffic":[57],"involved":[58],"Sparse-Dense":[60],"Matrix":[61,62],"Multiplication":[63],"(SpMM)":[64],"is":[65],"still":[66],"significant.":[67]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":20}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-04-23T00:00:00"}