{"id":"https://openalex.org/W4408846943","doi":"https://doi.org/10.1145/3689031.3717460","title":"Groot: Graph-Centric Row Reordering with Tree for Sparse Matrix Multiplications on Tensor Cores","display_name":"Groot: Graph-Centric Row Reordering with Tree for Sparse Matrix Multiplications on Tensor Cores","publication_year":2025,"publication_date":"2025-03-26","ids":{"openalex":"https://openalex.org/W4408846943","doi":"https://doi.org/10.1145/3689031.3717460"},"language":"en","primary_location":{"id":"doi:10.1145/3689031.3717460","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3689031.3717460","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twentieth European Conference on Computer Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3689031.3717460","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050067045","display_name":"YuAng Chen","orcid":"https://orcid.org/0000-0002-3392-8388"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"YuAng Chen","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102809942","display_name":"Jiadong Xie","orcid":"https://orcid.org/0000-0003-4535-8359"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiadong Xie","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030181826","display_name":"Siyi Teng","orcid":"https://orcid.org/0009-0004-1210-4672"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Siyi Teng","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040965703","display_name":"Weiya Zeng","orcid":"https://orcid.org/0000-0002-9770-6522"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wenqi Zeng","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075642293","display_name":"Jeffrey Xu Yu","orcid":"https://orcid.org/0000-0002-9738-827X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jeffrey Xu Yu","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5050067045"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":2.4362,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87802277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"803","last_page":"817"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.994700014591217,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.994700014591217,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9930999875068665,"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":0.9912999868392944,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5748533010482788},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5086553692817688},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.48871803283691406},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4632372260093689},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.42138975858688354},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3876355290412903},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3299434781074524},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2806606888771057},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.09946352243423462}],"concepts":[{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5748533010482788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5086553692817688},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.48871803283691406},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4632372260093689},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.42138975858688354},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3876355290412903},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3299434781074524},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2806606888771057},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.09946352243423462},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3689031.3717460","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3689031.3717460","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twentieth European Conference on Computer Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3689031.3717460","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3689031.3717460","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twentieth European Conference on Computer Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W626292722","https://openalex.org/W1965680834","https://openalex.org/W2086179657","https://openalex.org/W2110026675","https://openalex.org/W2124509324","https://openalex.org/W2147717514","https://openalex.org/W2427312773","https://openalex.org/W2444127451","https://openalex.org/W2484446135","https://openalex.org/W2734941459","https://openalex.org/W2805763850","https://openalex.org/W2914631005","https://openalex.org/W2949985202","https://openalex.org/W2963265099","https://openalex.org/W2963469388","https://openalex.org/W2964337156","https://openalex.org/W2964357930","https://openalex.org/W2999347085","https://openalex.org/W3011407967","https://openalex.org/W3029693508","https://openalex.org/W3116348227","https://openalex.org/W3132185085","https://openalex.org/W3173204484","https://openalex.org/W3196481040","https://openalex.org/W3208099998","https://openalex.org/W4205983429","https://openalex.org/W4206688953","https://openalex.org/W4241886172","https://openalex.org/W4293024985","https://openalex.org/W4310563332","https://openalex.org/W4381327178","https://openalex.org/W4395106472"],"related_works":["https://openalex.org/W3202552726","https://openalex.org/W2279642117","https://openalex.org/W4387560237","https://openalex.org/W4285148873","https://openalex.org/W2045476623","https://openalex.org/W4287713161","https://openalex.org/W2076468490","https://openalex.org/W2081219400","https://openalex.org/W2805810264","https://openalex.org/W2384787007"],"abstract_inverted_index":{"Sparse":[0],"matrix":[1,26,118],"multiplications":[2],"are":[3,127],"essential":[4],"in":[5,163],"scientific":[6],"computing":[7],"and":[8,23,47,181,191,206],"machine":[9],"learning":[10],"applications.":[11],"Recent":[12],"researches":[13],"offload":[14],"sparse":[15,19,59,117,201],"operations,":[16],"such":[17],"as":[18,129],"matrix-matrix":[20],"multiplication":[21,27],"(SpMM)":[22],"sampled":[24],"dense-dense":[25],"(SDDMM),":[28],"on":[29,61,183,203],"Tensor":[30],"Cores":[31],"(TCs)":[32],"for":[33,142],"improved":[34],"performance.":[35],"However,":[36],"their":[37,71],"performance":[38,196],"is":[39,97],"often":[40],"limited":[41],"by":[42,119],"the":[43,75,94,106,112,116,139,149,154,176,186,195],"matrix's":[44],"inherent":[45],"sparsity":[46],"irregularity.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,77],"find":[53],"row":[54,82,91],"reordering":[55,65,83,167],"can":[56],"potentially":[57],"improve":[58],"operations":[60],"TCs,":[62,184],"but":[63],"existing":[64],"techniques":[66],"exhibit":[67],"limitations":[68],"that":[69,172],"hinder":[70],"effectiveness.":[72],"To":[73,104],"address":[74],"issues,":[76],"propose":[78],"Groot,":[79],"a":[80,101,121,134],"graph-centric":[81],"algorithm":[84],"with":[85,165],"tree.":[86],"Groot":[87,109,147,159,173],"aims":[88],"to":[89,99,152,200],"minimize":[90],"differences":[92],"across":[93],"matrix,":[95],"which":[96],"proved":[98],"be":[100],"NP-hard":[102],"problem.":[103],"approximate":[105],"optimal":[107],"solution,":[108],"firstly":[110],"captures":[111],"local":[113],"structure":[114,144],"of":[115,179,189],"constructing":[120],"k-nearest":[122],"neighbor":[123],"graph,":[124],"where":[125],"rows":[126],"represented":[128],"nodes.":[130],"Then,":[131],"it":[132],"extracts":[133],"minimum":[135],"spanning":[136],"tree":[137,151],"from":[138],"constructed":[140],"graph":[141],"global":[143],"optimization.":[145],"Lastly,":[146],"traverses":[148],"extracted":[150],"obtain":[153],"final":[155],"ordering.":[156],"We":[157],"evaluate":[158],"using":[160],"real-world":[161],"datasets":[162],"comparison":[164],"state-of-the-art":[166],"algorithms.":[168],"Our":[169],"results":[170],"show":[171],"significantly":[174],"enhances":[175],"computational":[177],"intensity":[178],"SpMM":[180],"SDDMM":[182],"delivering":[185],"average":[187],"speedups":[188],"1.8\u00d7":[190],"2.0\u00d7,":[192],"respectively.":[193],"Furthermore,":[194],"gains":[197],"extend":[198],"broadly":[199],"computations":[202],"CUDA":[204],"cores":[205],"GNN":[207],"systems.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}