{"id":"https://openalex.org/W4409653046","doi":"https://doi.org/10.1145/3730586","title":"GNNPilot: A Holistic Framework for High-Performance Graph Neural Network Computations on GPUs","display_name":"GNNPilot: A Holistic Framework for High-Performance Graph Neural Network Computations on GPUs","publication_year":2025,"publication_date":"2025-04-22","ids":{"openalex":"https://openalex.org/W4409653046","doi":"https://doi.org/10.1145/3730586"},"language":"en","primary_location":{"id":"doi:10.1145/3730586","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3730586","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1145/3730586","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000331589","display_name":"Zhengding Hu","orcid":"https://orcid.org/0009-0005-8500-6173"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhengding Hu","raw_affiliation_strings":["Computer Science and Technology, University of Science and Technology of China","Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0005-8500-6173","affiliations":[{"raw_affiliation_string":"Computer Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059770282","display_name":"Jingwei Sun","orcid":"https://orcid.org/0000-0001-5098-1503"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210144930","display_name":"Baoshan College","ror":"https://ror.org/04t69c375","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210144930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwei Sun","raw_affiliation_strings":["China and Laoshan Laboratory","Computer Science and Technology, University of Science and Technology of China","Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5098-1503","affiliations":[{"raw_affiliation_string":"China and Laoshan Laboratory","institution_ids":["https://openalex.org/I4210144930"]},{"raw_affiliation_string":"Computer Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100932403","display_name":"Guangzhong Sun","orcid":"https://orcid.org/0000-0002-0794-7681"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangzhong Sun","raw_affiliation_strings":["Computer Science and Technology, University of Science and Technology of China","Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-0794-7681","affiliations":[{"raw_affiliation_string":"Computer Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000331589"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":2.0776,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87640933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"22","issue":"2","first_page":"1","last_page":"26"},"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":0.9997000098228455,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials 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":0.7996783256530762},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.604928731918335},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5200142860412598},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5044869184494019},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5023126602172852},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.454592764377594},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3383439779281616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33160635828971863},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2643839716911316},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15008476376533508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7996783256530762},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.604928731918335},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5200142860412598},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5044869184494019},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5023126602172852},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.454592764377594},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3383439779281616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33160635828971863},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2643839716911316},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15008476376533508}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3730586","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3730586","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3730586","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3730586","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1985312666","https://openalex.org/W2009654791","https://openalex.org/W2024818089","https://openalex.org/W2035080386","https://openalex.org/W2127048411","https://openalex.org/W2141374519","https://openalex.org/W2161902954","https://openalex.org/W2162283062","https://openalex.org/W2484446135","https://openalex.org/W2558460151","https://openalex.org/W2594183968","https://openalex.org/W2734941459","https://openalex.org/W2764075199","https://openalex.org/W2900569176","https://openalex.org/W2914631005","https://openalex.org/W2962711740","https://openalex.org/W2964015378","https://openalex.org/W2964337156","https://openalex.org/W3002330681","https://openalex.org/W3021975806","https://openalex.org/W3102641634","https://openalex.org/W3111142806","https://openalex.org/W3130421533","https://openalex.org/W3132185085","https://openalex.org/W3132616766","https://openalex.org/W3132695675","https://openalex.org/W3158027451","https://openalex.org/W3173204484","https://openalex.org/W3175189837","https://openalex.org/W3205776184","https://openalex.org/W3208099998","https://openalex.org/W4233295136","https://openalex.org/W4288419263","https://openalex.org/W4293024985","https://openalex.org/W4297733535","https://openalex.org/W4302296459","https://openalex.org/W4318541535","https://openalex.org/W4321636644","https://openalex.org/W4321636675","https://openalex.org/W4388103722","https://openalex.org/W4395106472","https://openalex.org/W4395111944","https://openalex.org/W4395116186","https://openalex.org/W4400410919"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W1599154403","https://openalex.org/W1582436825","https://openalex.org/W1996803181","https://openalex.org/W2979588510","https://openalex.org/W1429949169"],"abstract_inverted_index":{"Graph":[0],"Neural":[1],"Networks":[2],"(GNNs)":[3],"have":[4],"emerged":[5],"as":[6,171],"powerful":[7],"tools":[8],"for":[9,53,59,73,177],"graph-based":[10],"machine":[11],"learning":[12],"tasks,":[13],"but":[14],"their":[15],"performance":[16,157],"is":[17],"often":[18],"constrained":[19],"by":[20],"inefficient":[21],"sparse":[22,71],"operators":[23,160],"and":[24,65,86,132,142,161,174],"limited":[25],"hardware":[26],"utilization":[27],"during":[28],"multi-operator":[29,97],"workflows.":[30],"This":[31],"article":[32],"presents":[33],"GNNPilot,":[34],"a":[35,69,87,103],"holistic":[36],"optimization":[37,112],"framework":[38],"that":[39,108,146],"addresses":[40],"these":[41],"challenges":[42],"through":[43],"three":[44],"key":[45],"innovations.":[46],"First,":[47],"we":[48,81,101],"introduce":[49],"two":[50],"packing":[51,58,67],"strategies":[52,113],"gather":[54],"operators,":[55],"including":[56],"neighbor":[57],"load":[60],"balancing":[61],"in":[62,77,154],"sparser":[63],"graphs,":[64],"bin":[66],"with":[68],"new":[70],"format":[72],"enhanced":[74],"data":[75],"locality":[76],"denser":[78],"graphs.":[79],"Second,":[80],"propose":[82],"dynamic":[83],"parallelization":[84],"methods":[85],"novel":[88],"row":[89],"panel-based":[90],"kernel":[91],"fusion":[92],"technique":[93],"to":[94,114,128],"optimize":[95,129],"complex":[96],"GNN":[98,134,140,179],"models.":[99,135],"Third,":[100],"develop":[102],"lightweight":[104],"sampling-based":[105],"auto-tuning":[106],"mechanism":[107],"adapts":[109],"the":[110,126,156,162],"framework\u2019s":[111],"varying":[115],"input":[116],"characteristics.":[117],"Built":[118],"upon":[119],"tensor":[120],"expression-based":[121],"intermediate":[122],"representations,":[123],"GNNPilot":[124,147,170],"maintains":[125],"flexibility":[127],"both":[130,155],"popular":[131],"customized":[133],"Extensive":[136],"experiments":[137],"across":[138],"diverse":[139],"models":[141],"graph":[143],"datasets":[144],"demonstrate":[145],"achieves":[148],"substantial":[149],"speedups":[150],"over":[151],"state-of-the-art":[152],"implementations":[153],"of":[158,164],"single":[159],"efficiency":[163],"end-to-end":[165],"inference.":[166],"These":[167],"results":[168],"establish":[169],"an":[172],"efficient":[173],"adaptive":[175],"solution":[176],"accelerating":[178],"computations":[180],"on":[181],"modern":[182],"GPU":[183],"architectures.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
