{"id":"https://openalex.org/W7153628711","doi":"https://doi.org/10.1145/3803422","title":"A Memory-Aware Sparse Matrix-Matrix Multiplication on Multicore Architectures","display_name":"A Memory-Aware Sparse Matrix-Matrix Multiplication on Multicore Architectures","publication_year":2026,"publication_date":"2026-04-11","ids":{"openalex":"https://openalex.org/W7153628711","doi":"https://doi.org/10.1145/3803422"},"language":"en","primary_location":{"id":"doi:10.1145/3803422","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3803422","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/10.1145/3803422","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101323434","display_name":"Deshun Bi","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deshun Bi","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":"https://orcid.org/0009-0009-4488-5473","affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124116904","display_name":"Shengguo Li","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengguo Li","raw_affiliation_strings":["College of Computer Science, National University of Defense Technology"],"raw_orcid":"https://orcid.org/0000-0001-7827-6304","affiliations":[{"raw_affiliation_string":"College of Computer Science, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036679136","display_name":"Haozhong Qiu","orcid":"https://orcid.org/0009-0009-0434-8075"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haozhong Qiu","raw_affiliation_strings":["National University of Defense Technology College of Computer Science and Technology"],"raw_orcid":"https://orcid.org/0009-0009-0434-8075","affiliations":[{"raw_affiliation_string":"National University of Defense Technology College of Computer Science and Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122922443","display_name":"Chuanfu Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanfu Xu","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":"https://orcid.org/0000-0002-4876-2368","affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaojian Yang","orcid":"https://orcid.org/0009-0007-9821-171X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojian Yang","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":"https://orcid.org/0009-0007-9821-171X","affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102221431","display_name":"Fan Yuan","orcid":"https://orcid.org/0009-0003-9022-0727"},"institutions":[{"id":"https://openalex.org/I4610292","display_name":"Xiangtan University","ror":"https://ror.org/00xsfaz62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4610292"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yuan","raw_affiliation_strings":["Xiangtan University"],"raw_orcid":"https://orcid.org/0009-0003-9022-0727","affiliations":[{"raw_affiliation_string":"Xiangtan University","institution_ids":["https://openalex.org/I4610292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006729432","display_name":"Dezun Dong","orcid":"https://orcid.org/0000-0001-6243-8479"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dezun Dong","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":"https://orcid.org/0000-0001-6243-8479","affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088839819","display_name":"Tiaojie Xiao","orcid":"https://orcid.org/0000-0002-8378-5530"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiaojie Xiao","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology"],"raw_orcid":"https://orcid.org/0000-0002-8378-5530","affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jie Liu","orcid":"https://orcid.org/0000-0003-3745-7541"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology"],"raw_orcid":"https://orcid.org/0000-0003-3745-7541","affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.46257074,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"2","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8763999938964844,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8763999938964844,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.03500000014901161,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.027300000190734863,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/locality","display_name":"Locality","score":0.7196000218391418},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.6818000078201294},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6046000123023987},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5662999749183655},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5444999933242798},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5189999938011169},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4952000081539154},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47780001163482666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8769999742507935},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.7196000218391418},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.6818000078201294},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6784999966621399},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6046000123023987},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5662999749183655},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5444999933242798},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4952000081539154},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47780001163482666},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.46070000529289246},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37389999628067017},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3472000062465668},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C79470037","wikidata":"https://www.wikidata.org/wiki/Q279748","display_name":"Out-of-core algorithm","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C11799548","wikidata":"https://www.wikidata.org/wiki/Q6675847","display_name":"Loop tiling","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3803422","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3803422","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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:10.1145/3803422","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3803422","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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":[{"id":"https://openalex.org/G4796081990","display_name":null,"funder_award_id":"62032023, 42104078, 62502048, and 61902411","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G980296975","display_name":null,"funder_award_id":"2023YFB3001702","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1506342804","https://openalex.org/W1980140364","https://openalex.org/W1990808267","https://openalex.org/W2035080386","https://openalex.org/W2480854438","https://openalex.org/W2807021761","https://openalex.org/W2808128431","https://openalex.org/W2957142384","https://openalex.org/W2963530710","https://openalex.org/W2983719957","https://openalex.org/W2999347085","https://openalex.org/W3166510811","https://openalex.org/W4321466355","https://openalex.org/W4389495241","https://openalex.org/W4391985182","https://openalex.org/W4395106472","https://openalex.org/W4405755653","https://openalex.org/W4405755887","https://openalex.org/W4406548153","https://openalex.org/W4408029514","https://openalex.org/W4411670560"],"related_works":[],"abstract_inverted_index":{"Sparse":[0],"matrix\u2013matrix":[1],"multiplication":[2],"(SpMM)":[3],"is":[4,18,28],"a":[5,19,60,69],"fundamental":[6],"operation":[7],"in":[8,31,91],"scientific":[9],"computing":[10],"with":[11,68],"broad":[12],"applications":[13,93],"across":[14],"numerous":[15],"domains.":[16],"Tiling":[17],"key":[20],"optimization":[21],"technique":[22],"for":[23,50,131],"improving":[24],"data":[25,37,51,71,81],"locality":[26,82],"and":[27,111,140,159],"widely":[29],"adopted":[30],"high-performance":[32],"computing.":[33],"However,":[34],"the":[35,127],"irregular":[36],"access":[38],"patterns":[39],"inherent":[40],"to":[41,46,79,107,117,151],"SpMM":[42,62],"make":[43],"it":[44],"challenging":[45],"exploit":[47],"tiling":[48,67],"effectively":[49],"reuse.":[52],"In":[53],"this":[54],"article,":[55],"we":[56,96,120],"propose":[57],"MaSpMM":[58,73],",":[59],"memory-aware":[61],"framework":[63],"that":[64,102,144],"integrates":[65],"cache-aware":[66],"segment-oriented":[70],"layout.":[72],"stores":[74],"matrices":[75,90,106],"as":[76],"continuous":[77],"segments":[78],"enhance":[80],"within":[83],"each":[84,132],"tile.":[85],"Moreover,":[86],"since":[87],"many":[88],"sparse":[89],"real-world":[92],"exhibit":[94],"symmetry,":[95],"further":[97,112],"develop":[98],"MaSpMM-Sym,":[99],"an":[100],"extension":[101],"recursively":[103],"partitions":[104],"symmetric":[105],"eliminate":[108],"write":[109],"conflicts":[110],"improve":[113],"locality.":[114],"To":[115],"adapt":[116],"diverse":[118],"scenarios,":[119],"finally":[121],"introduce":[122],"MaSpMM-Adap,":[123],"which":[124],"adaptively":[125],"selects":[126],"most":[128],"suitable":[129],"approach":[130],"input":[133],"matrix.":[134],"Comprehensive":[135],"evaluations":[136],"on":[137],"both":[138],"x86":[139],"ARM":[141],"CPUs":[142],"demonstrate":[143],"MaSpMM-Adap":[145],"achieves":[146],"average":[147],"speedups":[148],"of":[149],"up":[150],"1.86\u00d7":[152],"over":[153,157,161],"Intel":[154],"oneMKL,":[155],"1.84\u00d7":[156],"ASpT,":[158],"1.75\u00d7":[160],"J-Stream.":[162]},"counts_by_year":[],"updated_date":"2026-06-27T06:13:17.587685","created_date":"2026-04-12T00:00:00"}
