{"id":"https://openalex.org/W7162759803","doi":"https://doi.org/10.1007/s11227-026-08606-2","title":"Block-structured matrix reordering for efficient SDDMM on tensor cores","display_name":"Block-structured matrix reordering for efficient SDDMM on tensor cores","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7162759803","doi":"https://doi.org/10.1007/s11227-026-08606-2"},"language":"en","primary_location":{"id":"doi:10.1007/s11227-026-08606-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-026-08606-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-026-08606-2.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11227-026-08606-2.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137328203","display_name":"Chengxing Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chengxing Zou","raw_affiliation_strings":["School of Computer Science and Engineering, Chung-Ang University, 84 Heukseok-ro Dongjak-gu, Seoul, 06974, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Chung-Ang University, 84 Heukseok-ro Dongjak-gu, Seoul, 06974, Republic of Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027442506","display_name":"Changwan Hong","orcid":"https://orcid.org/0000-0001-9069-8374"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changwan Hong","raw_affiliation_strings":["Computer Science & Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar St, Cambridge, MA, 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science & Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar St, Cambridge, MA, 02139, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023057376","display_name":"Gordon Euhyun Moon","orcid":"https://orcid.org/0000-0003-4992-6181"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gordon Euhyun Moon","raw_affiliation_strings":["Department of Computer Science and Engineering, Sogang University, 35 Baekbeom-ro Mapo-gu, Seoul, 04107, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sogang University, 35 Baekbeom-ro Mapo-gu, Seoul, 04107, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676208","display_name":"Jinsung Kim","orcid":"https://orcid.org/0000-0003-3751-8869"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jinsung Kim","raw_affiliation_strings":["School of Computer Science and Engineering, Chung-Ang University, 84 Heukseok-ro Dongjak-gu, Seoul, 06974, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Chung-Ang University, 84 Heukseok-ro Dongjak-gu, Seoul, 06974, Republic of Korea","institution_ids":["https://openalex.org/I67900169"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100676208"],"corresponding_institution_ids":["https://openalex.org/I67900169"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6360341,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"82","issue":"8","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":0.421999990940094,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.421999990940094,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.20020000636577606,"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/T12303","display_name":"Tensor decomposition and applications","score":0.06920000165700912,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7311000227928162},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7264000177383423},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6489999890327454},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.6424999833106995},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6162999868392944},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5339000225067139},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4772000014781952},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46050000190734863},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4291999936103821},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3935000002384186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8100000023841858},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7311000227928162},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7264000177383423},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6489999890327454},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.6424999833106995},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6171000003814697},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6162999868392944},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4772000014781952},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.461899995803833},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46140000224113464},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39500001072883606},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C79470037","wikidata":"https://www.wikidata.org/wiki/Q279748","display_name":"Out-of-core algorithm","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C2780365336","wikidata":"https://www.wikidata.org/wiki/Q25047934","display_name":"Single-core","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C113315163","wikidata":"https://www.wikidata.org/wiki/Q7625159","display_name":"Structure tensor","level":3,"score":0.32589998841285706},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3138999938964844},{"id":"https://openalex.org/C2777749129","wikidata":"https://www.wikidata.org/wiki/Q17148469","display_name":"Robust principal component analysis","level":3,"score":0.2976999878883362},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.2858999967575073},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C48903430","wikidata":"https://www.wikidata.org/wiki/Q491370","display_name":"Graph partition","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.26100000739097595},{"id":"https://openalex.org/C85817219","wikidata":"https://www.wikidata.org/wiki/Q884772","display_name":"Block matrix","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C165443888","wikidata":"https://www.wikidata.org/wiki/Q1482183","display_name":"Transformation matrix","level":3,"score":0.2563999891281128},{"id":"https://openalex.org/C42704193","wikidata":"https://www.wikidata.org/wiki/Q7851097","display_name":"Tucker decomposition","level":4,"score":0.25450000166893005},{"id":"https://openalex.org/C2986737658","wikidata":"https://www.wikidata.org/wiki/Q30103009","display_name":"Tensor decomposition","level":3,"score":0.2542000114917755},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11227-026-08606-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-026-08606-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-026-08606-2.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11227-026-08606-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-026-08606-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-026-08606-2.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1508666556","display_name":null,"funder_award_id":"RS-2024-00416666","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G6386388308","display_name":null,"funder_award_id":"NRF-RS-2024-00416666","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G8526708714","display_name":null,"funder_award_id":"NRF-RS-2024-00359076","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7162759803.pdf","grobid_xml":"https://content.openalex.org/works/W7162759803.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1935978687","https://openalex.org/W1968723134","https://openalex.org/W1986966428","https://openalex.org/W2021197309","https://openalex.org/W2022219663","https://openalex.org/W2032272187","https://openalex.org/W2116341502","https://openalex.org/W2142466236","https://openalex.org/W2169101582","https://openalex.org/W2912064332","https://openalex.org/W2914631005","https://openalex.org/W2979310060","https://openalex.org/W2999347085","https://openalex.org/W3130660608","https://openalex.org/W3173204484","https://openalex.org/W4250981202","https://openalex.org/W4283462727","https://openalex.org/W4285503871","https://openalex.org/W4391986945","https://openalex.org/W4401862084","https://openalex.org/W4408029514","https://openalex.org/W4409133356"],"related_works":[],"abstract_inverted_index":{"Sampled":[0],"Dense-Dense":[1],"Matrix":[2,48],"Multiplication":[3],"is":[4,26],"a":[5,46,70,90,122],"fundamental":[6],"operation":[7],"in":[8,14],"sparse":[9,58,72,103],"linear":[10],"algebra,":[11],"widely":[12],"used":[13],"graph":[15],"neural":[16],"networks":[17],"and":[18,32,79,85,132,146],"scientific":[19],"computing.":[20],"However,":[21],"accelerating":[22],"computations":[23],"on":[24,111],"GPUs":[25],"challenging":[27],"due":[28],"to":[29,99,121],"data":[30],"sparsity":[31],"irregular":[33],"memory":[34,77],"access,":[35],"which":[36],"hinder":[37],"efficient":[38],"use":[39],"of":[40],"Tensor":[41,53,100,129],"Cores.":[42,109],"This":[43],"paper":[44],"introduces":[45],"Block-Structured":[47],"Reordering":[49],"framework":[50],"that":[51,75,116],"improves":[52,76],"Core":[54,130,139],"utilization":[55],"by":[56,107,141],"reorganizing":[57],"matrices":[59],"using":[60],"bi-directional":[61],"reordering":[62],"with":[63],"weighted":[64],"similarity":[65],"metrics.":[66],"We":[67],"also":[68],"propose":[69],"tile-aware":[71],"matrix":[73,95],"format":[74],"access":[78],"task":[80],"scheduling.":[81],"To":[82],"enable":[83],"adaptive":[84],"balanced":[86],"computation,":[87],"we":[88],"employ":[89],"dual-path":[91],"execution":[92],"strategy:":[93],"dense":[94],"blocks":[96,104],"are":[97,105],"assigned":[98],"Cores,":[101],"while":[102],"handled":[106],"CUDA":[108,138],"Experiments":[110],"the":[112,127,136],"RTX":[113],"4090":[114],"demonstrate":[115],"our":[117],"method":[118],"achieves":[119],"up":[120],"$$10.38\\times":[123],"$$":[124,134],"speedup":[125],"over":[126,135],"best":[128,137],"baseline":[131,140],"$$7.31\\times":[133],"producing":[142],"denser":[143],"block":[144],"structures":[145],"enhancing":[147],"parallelism.":[148]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-05-30T00:00:00"}