{"id":"https://openalex.org/W4394946188","doi":"https://doi.org/10.1145/3627703.3629560","title":"Minuet: Accelerating 3D Sparse Convolutions on GPUs","display_name":"Minuet: Accelerating 3D Sparse Convolutions on GPUs","publication_year":2024,"publication_date":"2024-04-18","ids":{"openalex":"https://openalex.org/W4394946188","doi":"https://doi.org/10.1145/3627703.3629560"},"language":"en","primary_location":{"id":"doi:10.1145/3627703.3629560","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627703.3629560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth European Conference on Computer Systems","raw_type":"proceedings-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/A5080051493","display_name":"Jiacheng Yang","orcid":"https://orcid.org/0009-0002-9581-9088"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Jiacheng Yang","raw_affiliation_strings":["University of Toronto & Vector Institute"],"affiliations":[{"raw_affiliation_string":"University of Toronto & Vector Institute","institution_ids":["https://openalex.org/I4210127509","https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044162748","display_name":"Christina Giannoula","orcid":"https://orcid.org/0000-0003-0162-4547"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Christina Giannoula","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095776882","display_name":"Jun Wu","orcid":"https://orcid.org/0009-0002-2802-121X"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jun Wu","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031013766","display_name":"Mostafa Elhoushi","orcid":"https://orcid.org/0000-0001-6172-4510"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mostafa Elhoushi","raw_affiliation_strings":["Meta"],"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095776883","display_name":"James Gleeson","orcid":"https://orcid.org/0009-0006-1810-2752"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Gleeson","raw_affiliation_strings":["Samsung AI Centre Toronto"],"affiliations":[{"raw_affiliation_string":"Samsung AI Centre Toronto","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007585346","display_name":"Gennady Pekhimenko","orcid":"https://orcid.org/0000-0002-3839-0919"},"institutions":[{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gennady Pekhimenko","raw_affiliation_strings":["CentML & University of Toronto & Vector Institute"],"affiliations":[{"raw_affiliation_string":"CentML & University of Toronto & Vector Institute","institution_ids":["https://openalex.org/I4210127509"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5080051493"],"corresponding_institution_ids":["https://openalex.org/I185261750","https://openalex.org/I4210127509"],"apc_list":null,"apc_paid":null,"fwci":0.3753,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51710806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"786","last_page":"802"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9939000010490417,"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/computer-science","display_name":"Computer science","score":0.8191723823547363},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7413078546524048},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6332893371582031},{"id":"https://openalex.org/keywords/padding","display_name":"Padding","score":0.5901653170585632},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5288276076316833},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5278018712997437},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5087056756019592},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.4796905219554901},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.4520225524902344},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.44883179664611816},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4104398488998413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14526435732841492},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12475034594535828}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8191723823547363},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7413078546524048},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6332893371582031},{"id":"https://openalex.org/C165435473","wikidata":"https://www.wikidata.org/wiki/Q1509884","display_name":"Padding","level":2,"score":0.5901653170585632},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5288276076316833},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5278018712997437},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5087056756019592},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.4796905219554901},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.4520225524902344},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44883179664611816},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4104398488998413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14526435732841492},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12475034594535828},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627703.3629560","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627703.3629560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth European Conference on Computer Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W217217970","https://openalex.org/W1932888261","https://openalex.org/W2024794876","https://openalex.org/W2059966434","https://openalex.org/W2085248745","https://openalex.org/W2092095701","https://openalex.org/W2190691619","https://openalex.org/W2211722331","https://openalex.org/W2460657278","https://openalex.org/W2560609797","https://openalex.org/W2590246587","https://openalex.org/W2624503621","https://openalex.org/W2737444374","https://openalex.org/W2793187686","https://openalex.org/W2902906695","https://openalex.org/W2934185149","https://openalex.org/W2939201152","https://openalex.org/W2963182550","https://openalex.org/W2971142047","https://openalex.org/W2989818952","https://openalex.org/W3046305366","https://openalex.org/W3202803696","https://openalex.org/W3203926124","https://openalex.org/W4220701587","https://openalex.org/W4224319921","https://openalex.org/W4318541538","https://openalex.org/W4318541647","https://openalex.org/W4327911434","https://openalex.org/W4386113258","https://openalex.org/W6746340260","https://openalex.org/W6748408460","https://openalex.org/W6765299845","https://openalex.org/W6771790678","https://openalex.org/W6775162103","https://openalex.org/W6779712747","https://openalex.org/W6780536331","https://openalex.org/W6787910462","https://openalex.org/W6801065500","https://openalex.org/W6802350252","https://openalex.org/W6802693339","https://openalex.org/W6839901555","https://openalex.org/W6856169528"],"related_works":["https://openalex.org/W2142641794","https://openalex.org/W4384947563","https://openalex.org/W2946726629","https://openalex.org/W4231428344","https://openalex.org/W4322753435","https://openalex.org/W4243974052","https://openalex.org/W4315882065","https://openalex.org/W4244331477","https://openalex.org/W4236539272","https://openalex.org/W2077912189"],"abstract_inverted_index":{"Sparse":[0],"Convolution":[1],"(SC)":[2],"is":[3,242],"widely":[4],"used":[5,110],"for":[6,99,205],"processing":[7],"3D":[8],"point":[9,26,207],"clouds":[10],"that":[11,51,124,154,179,191],"are":[12],"inherently":[13],"sparse.":[14],"Different":[15],"from":[16],"dense":[17],"convolution,":[18],"SC":[19,40,88,96,165,196,231],"preserves":[20],"the":[21,24,53,83,107,112,127,140,144,150,157,160,234],"sparsity":[22],"of":[23,85,131,149,163,240],"input":[25],"cloud":[27,208],"by":[28,198,222],"only":[29],"allowing":[30],"outputs":[31],"to":[32,46,60,71,104,138,155,159,203,227],"specific":[33],"locations.":[34],"To":[35],"efficiently":[36],"compute":[37],"SC,":[38],"prior":[39,86,195,230],"engines":[41,197,232],"first":[42],"use":[43,67,134],"hash":[44,108],"tables":[45,109],"build":[47],"a":[48,68,93,116,135,174],"kernel":[49,185],"map":[50],"stores":[52],"necessary":[54],"General":[55],"Matrix":[56],"Multiplication":[57],"(GEMM)":[58],"operations":[59,75,148],"be":[61],"executed":[62],"(Map":[63],"step),":[64],"and":[65,90,146,168,171,184],"then":[66],"Gather-GEMM-Scatter":[69],"process":[70],"execute":[72],"these":[73],"GEMM":[74,176],"(GMaS":[76],"step).":[77],"In":[78],"this":[79],"work,":[80],"we":[81],"analyze":[82],"shortcomings":[84],"state-of-the-art":[87],"engines,":[89],"propose":[91],"Minuet,":[92],"novel":[94,117,212],"memory-efficient":[95],"engine":[97],"tailored":[98],"modern":[100],"GPUs.":[101],"Minuet":[102,192,241],"proposes":[103],"(i)":[105],"replace":[106],"in":[111,143,233],"Map":[113,235],"step":[114],"with":[115],"segmented":[118,213],"sorting":[119,214],"double-traversed":[120,215],"binary":[121,216],"search":[122,217],"algorithm":[123,218],"highly":[125],"utilizes":[126],"on-chip":[128],"memory":[129,182],"hierarchy":[130],"GPUs,":[132],"(ii)":[133],"lightweight":[136],"scheme":[137],"autotune":[139],"tile":[141],"size":[142],"Gather":[145],"Scatter":[147],"GMaS":[151],"step,":[152],"such":[153],"adapt":[156],"execution":[158],"particular":[161],"characteristics":[162],"each":[164],"layer,":[166],"dataset,":[167],"GPU":[169],"architecture,":[170],"(iii)":[172],"employ":[173],"padding-efficient":[175],"grouping":[177],"approach":[178],"reduces":[180],"both":[181],"padding":[183],"launching":[186],"overheads.":[187],"Our":[188,211],"evaluations":[189],"show":[190],"significantly":[193],"outperforms":[194],"on":[199,224],"average":[200,225],"1.74\u00d7":[201],"(up":[202,226],"2.22\u00d7)":[204],"end-to-end":[206],"network":[209],"executions.":[210],"achieves":[219],"superior":[220],"speedups":[221],"15.8\u00d7":[223],"26.8\u00d7)":[228],"over":[229],"step.":[236],"The":[237],"source":[238],"code":[239],"publicly":[243],"available":[244],"at":[245],"https://github.com/UofT-EcoSystem/Minuet.":[246]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}