{"id":"https://openalex.org/W7225168606","doi":"https://doi.org/10.48550/arxiv.2611.03610","title":"A GPU Engine for Sparse Matrix-Vector Products on $k^2$-Tree-Compressed Graphs","display_name":"A GPU Engine for Sparse Matrix-Vector Products on $k^2$-Tree-Compressed Graphs","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225168606","doi":"https://doi.org/10.48550/arxiv.2611.03610"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.03610","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03610","pdf_url":"https://arxiv.org/pdf/2611.03610","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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.03610","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003830291","display_name":"Francesco Tosoni","orcid":"https://orcid.org/0000-0001-8457-3866","observed_orcids":["https://orcid.org/0000-0001-8457-3866"]},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]},{"id":"https://openalex.org/I162290304","display_name":"Scuola Superiore Sant'Anna","ror":"https://ror.org/025602r80","country_code":"IT","type":"education","lineage":["https://openalex.org/I162290304"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Tosoni, Francesco","raw_affiliation_strings":["Department of Computer Science , University of Pisa Pisa , Italy","Sant'Anna School of Advanced Studies , L'EMbeDS Pisa , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Pisa Pisa , Italy","institution_ids":["https://openalex.org/I108290504"]},{"raw_affiliation_string":"Sant'Anna School of Advanced Studies , L'EMbeDS Pisa , Italy","institution_ids":["https://openalex.org/I162290304"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047226405","display_name":"Gabriele Mencagli","orcid":"https://orcid.org/0000-0002-6263-7723","observed_orcids":["https://orcid.org/0000-0002-6263-7723"]},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mencagli, Gabriele","raw_affiliation_strings":["Department of Computer Science , University of Pisa Pisa , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Pisa Pisa , Italy","institution_ids":["https://openalex.org/I108290504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.4884999990463257,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.4884999990463257,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.4738999903202057,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.006300000008195639,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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-vector-multiplication","display_name":"sparse matrix-vector multiplication","score":0.8870000243186951},{"id":"https://openalex.org/keywords/gpu-acceleration","display_name":"GPU acceleration","score":0.5989999771118164},{"id":"https://openalex.org/keywords/boolean-matrix","display_name":"Boolean matrices","score":0.8009999990463257},{"id":"https://openalex.org/keywords/parallel-prefix-sum","display_name":"parallel prefix sum","score":0.7919999957084656},{"id":"https://openalex.org/keywords/boolean-semiring","display_name":"Boolean semiring","score":0.6240000128746033},{"id":"https://openalex.org/keywords/tropical-semiring","display_name":"tropical semiring","score":0.9900000095367432},{"id":"https://openalex.org/keywords/graph-traversal","display_name":"graph traversal","score":0.34299999475479126}],"concepts":[{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.76419997215271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.677299976348877},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.5325999855995178},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.49239999055862427},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4625000059604645},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.44440001249313354},{"id":"https://openalex.org/C50820777","wikidata":"https://www.wikidata.org/wiki/Q213723","display_name":"Hypercube","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.42719998955726624},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.39070001244544983},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C32900221","wikidata":"https://www.wikidata.org/wiki/Q181365","display_name":"Dot product","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3711000084877014},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.33559998869895935},{"id":"https://openalex.org/C187455244","wikidata":"https://www.wikidata.org/wiki/Q942353","display_name":"Boolean function","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3165000081062317},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2833000123500824},{"id":"https://openalex.org/C63553672","wikidata":"https://www.wikidata.org/wiki/Q581168","display_name":"Binary logarithm","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.2685999870300293},{"id":"https://openalex.org/C141796577","wikidata":"https://www.wikidata.org/wiki/Q837479","display_name":"Boolean circuit","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2581999897956848},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.25589999556541443}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.03610","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03610","pdf_url":"https://arxiv.org/pdf/2611.03610","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.2611.03610","doi":"https://doi.org/10.48550/arxiv.2611.03610","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.03610","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:2611.03610","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03610","pdf_url":"https://arxiv.org/pdf/2611.03610","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":[],"funders":[{"id":"https://openalex.org/F4320306151","display_name":"Alfred P. Sloan Foundation","ror":"https://ror.org/052csg198"},{"id":"https://openalex.org/F4320312538","display_name":"Wikimedia Foundation","ror":"https://ror.org/032q98j12"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225168606.pdf","grobid_xml":"https://content.openalex.org/works/W7225168606.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7171722037","https://openalex.org/W2765734369","https://openalex.org/W3137131725","https://openalex.org/W4414454333","https://openalex.org/W2043105874","https://openalex.org/W2095836023","https://openalex.org/W7146244166","https://openalex.org/W2571103886","https://openalex.org/W1893178273","https://openalex.org/W2163449859"],"abstract_inverted_index":{"The":[0,134,245],"$k^2$-tree":[1,251],"is":[2,129,197,247,252,262],"a":[3,41,49,88,94,100,127,146,183,188,213,230,233],"compact":[4],"representation":[5],"of":[6,14,35,43,76,103,119,126,175,203,219,255],"Boolean":[7,151,189],"matrices:":[8],"it":[9,132],"stores":[10],"the":[11,33,63,66,72,74,77,83,113,117,120,123,149,157,195,201,217,222,227,239,250,253,263],"recursive":[12],"hierarchy":[13],"their":[15],"non-empty":[16],"submatrices,":[17],"with":[18,166,207],"neither":[19],"values":[20],"nor":[21],"coordinates,":[22],"and":[23,26,90,139,152,163,172,187,205,224],"serves":[24],"rows":[25],"columns":[27],"alike.":[28],"Its":[29],"traversal,":[30],"however,":[31],"locates":[32],"children":[34,78],"each":[36],"node":[37],"by":[38,116],"rank":[39],"queries,":[40],"chain":[42],"dependent":[44],"irregular":[45],"loads":[46],"that":[47,194],"leaves":[48],"GPU":[50,185],"waiting":[51],"on":[52,60,71,159,221,226,238],"memory.":[53],"We":[54,155],"implement":[55],"sparse":[56],"matrix-vector":[57],"multiplication":[58],"(SpMV)":[59],"$k^2$-trees":[61],"for":[62,142],"GPU.":[64],"Since":[65],"traversal":[67,136],"does":[68],"not":[69,260],"depend":[70],"vector,":[73],"positions":[75],"are":[79],"static:":[80],"we":[81],"descend":[82],"tree":[84,196],"one":[85,143],"level":[86,211],"at":[87],"time":[89,218],"obtain":[91],"them":[92],"from":[93,99],"parallel":[95],"prefix":[96],"sum":[97],"or":[98,145],"sampled":[101],"directory":[102],"about":[104],"0.1":[105],"bits":[106],"per":[107],"node.":[108],"Descending":[109],"in":[110],"tiles":[111],"bounds":[112],"temporary":[114],"memory":[115,125,248],"depth":[118],"tree,":[121],"so":[122],"device":[124,258],"product":[128,214,234],"known":[130],"before":[131],"runs.":[133],"same":[135],"computes":[137],"right":[138,223],"left":[140],"products,":[141],"vector":[144],"batch,":[147],"over":[148],"plus-times,":[150],"tropical":[153],"semirings.":[154],"evaluate":[156],"engine":[158,186,246],"an":[160,164],"NVIDIA":[161],"GB10":[162],"H100":[165],"fourteen":[167],"Wikidata,":[168],"Software":[169],"Heritage,":[170],"web":[171],"social":[173],"graphs":[174],"up":[176],"to":[177],"1.2":[178],"billion":[179],"edges,":[180],"against":[181],"cuSPARSE,":[182],"grammar-compressed":[184],"CSR.":[190],"Our":[191],"results":[192],"show":[193],"2.3-27x":[198],"smaller":[199],"than":[200,243],"CSR":[202],"cuSPARSE":[204,220],"that,":[206],"its":[208],"last":[209],"internal":[210],"cached,":[212],"takes":[215],"0.7-2.4x":[216],"0.27-2.6x":[225],"left.":[228],"On":[229],"1.2-billion-edge":[231],"graph,":[232],"needs":[235],"1.1":[236],"GB":[237],"device,":[240],"9x":[241],"less":[242],"cuSPARSE.":[244],"bounded:":[249],"format":[254],"choice":[256],"when":[257],"memory,":[259],"time,":[261],"constraint.":[264]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-04T00:00:00"}