{"id":"https://openalex.org/W7150070620","doi":"https://doi.org/10.3390/computers15040223","title":"AGP-GEMM: Adaptive Grouping and Partitioning Framework for Accelerating Small and Irregular Matrices on CPUs","display_name":"AGP-GEMM: Adaptive Grouping and Partitioning Framework for Accelerating Small and Irregular Matrices on CPUs","publication_year":2026,"publication_date":"2026-04-03","ids":{"openalex":"https://openalex.org/W7150070620","doi":"https://doi.org/10.3390/computers15040223"},"language":"en","primary_location":{"id":"doi:10.3390/computers15040223","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15040223","pdf_url":"https://www.mdpi.com/2073-431X/15/4/223/pdf?version=1775204012","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-431X/15/4/223/pdf?version=1775204012","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046707175","display_name":"Hongzhe Zhou","orcid":"https://orcid.org/0000-0002-2991-5306"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhe Zhou","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132970194","display_name":"Lu Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090512","display_name":"Guangzhou Experimental Station","ror":"https://ror.org/00f2c2516","country_code":"CN","type":"facility","lineage":["https://openalex.org/I107851509","https://openalex.org/I4210090512","https://openalex.org/I4210127390","https://openalex.org/I4210151987"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lu Lu","raw_affiliation_strings":["Pazhou Laboratory, Guangzhou 510005, China","Peng Cheng Laboratory, Shenzhen 518055, China","School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China"],"raw_orcid":"https://orcid.org/0000-0001-6372-7088","affiliations":[{"raw_affiliation_string":"Pazhou Laboratory, Guangzhou 510005, China","institution_ids":["https://openalex.org/I4210090512"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen 518055, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338243","display_name":"Hu Yang","orcid":"https://orcid.org/0000-0001-6589-8534"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibiao Yang","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132988062","display_name":"Yu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5132970194"],"corresponding_institution_ids":["https://openalex.org/I4210090512","https://openalex.org/I4210136793","https://openalex.org/I90610280"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.51785714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"4","first_page":"223","last_page":"223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.7049999833106995,"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":0.7049999833106995,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.08640000224113464,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.034299999475479126,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.660099983215332},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.6068999767303467},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5863999724388123},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5737000107765198},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5393000245094299},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.508400022983551},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5083000063896179},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5080000162124634},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4194999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7444000244140625},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.660099983215332},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6442999839782715},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.6068999767303467},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5863999724388123},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5737000107765198},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5393000245094299},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.508400022983551},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5083000063896179},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5080000162124634},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49639999866485596},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.42489999532699585},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.41119998693466187},{"id":"https://openalex.org/C41431624","wikidata":"https://www.wikidata.org/wiki/Q1053357","display_name":"Block size","level":3,"score":0.366100013256073},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C2780365336","wikidata":"https://www.wikidata.org/wiki/Q25047934","display_name":"Single-core","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.3424000144004822},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C2776003309","wikidata":"https://www.wikidata.org/wiki/Q1988072","display_name":"Adaptive algorithm","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2953000068664551},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C150495011","wikidata":"https://www.wikidata.org/wiki/Q128392","display_name":"Concurrent computing","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C85817219","wikidata":"https://www.wikidata.org/wiki/Q884772","display_name":"Block matrix","level":3,"score":0.2515000104904175},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/computers15040223","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15040223","pdf_url":"https://www.mdpi.com/2073-431X/15/4/223/pdf?version=1775204012","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:97e0dd5d5d544e3391808263cdd77c30","is_oa":true,"landing_page_url":"https://doaj.org/article/97e0dd5d5d544e3391808263cdd77c30","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computers, Vol 15, Iss 4, p 223 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/computers15040223","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15040223","pdf_url":"https://www.mdpi.com/2073-431X/15/4/223/pdf?version=1775204012","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7353797023","display_name":null,"funder_award_id":"2024A1515010204","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7150070620.pdf","grobid_xml":"https://content.openalex.org/works/W7150070620.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1502558230","https://openalex.org/W2092283255","https://openalex.org/W2096504919","https://openalex.org/W2097930379","https://openalex.org/W2149294210","https://openalex.org/W2896652512","https://openalex.org/W2898890919","https://openalex.org/W2919115771","https://openalex.org/W2952256223","https://openalex.org/W2968108410","https://openalex.org/W2968935608","https://openalex.org/W3005429556","https://openalex.org/W3033356834","https://openalex.org/W3038313908","https://openalex.org/W3174431351","https://openalex.org/W3175909698","https://openalex.org/W3195800062","https://openalex.org/W3209046823","https://openalex.org/W3209398607","https://openalex.org/W4233509487","https://openalex.org/W4244254628","https://openalex.org/W4254405132","https://openalex.org/W4312910656","https://openalex.org/W4360831960","https://openalex.org/W4382051162","https://openalex.org/W4389259732","https://openalex.org/W4399019103","https://openalex.org/W4401568674","https://openalex.org/W4404520889","https://openalex.org/W4408018269","https://openalex.org/W4409311612","https://openalex.org/W4409477836","https://openalex.org/W4414444306"],"related_works":[],"abstract_inverted_index":{"General":[0],"Matrix":[1],"Multiplication":[2],"(GEMM)":[3],"is":[4,28],"a":[5,62,80,140],"fundamental":[6],"computational":[7,53],"kernel":[8],"in":[9,21,164],"scientific":[10],"computing,":[11],"serving":[12],"as":[13],"the":[14,24,36,105,119,125,134,156,161],"foundation":[15],"for":[16],"numerous":[17],"complex":[18],"tasks.":[19],"However,":[20],"practical":[22],"applications,":[23],"performance":[25,130],"of":[26,38,76,143,151,160],"GEMM":[27,49,63],"often":[29],"constrained":[30],"by":[31],"irregular":[32,47,168],"matrix":[33,106,169],"dimensions":[34],"and":[35,46,91,112,147,158,167],"diversity":[37],"hardware":[39],"architectures.":[40],"In":[41],"particular,":[42],"when":[43],"processing":[44],"small":[45,166],"matrices,":[48],"typically":[50],"exhibits":[51],"reduced":[52],"efficiency.":[54],"To":[55],"address":[56],"these":[57],"challenges,":[58],"this":[59],"paper":[60],"proposes":[61],"acceleration":[64,142],"method":[65,74,127],"based":[66],"on":[67,118],"an":[68,92,148],"adaptive":[69,93],"core":[70,81],"grouping":[71,82],"strategy.":[72],"The":[73],"consists":[75],"two":[77],"key":[78],"components:":[79],"mechanism":[83],"that":[84,97,124],"alleviates":[85],"workload":[86],"imbalance":[87],"among":[88],"multi-core":[89],"CPUs,":[90],"block":[94],"partitioning":[95],"algorithm":[96],"dynamically":[98],"selects":[99],"optimal":[100],"tiling":[101],"schemes":[102],"according":[103],"to":[104,133,145],"dimensions,":[107],"achieving":[108],"both":[109],"load":[110],"balance":[111],"cache-friendly":[113],"data":[114],"access.":[115],"Experimental":[116],"results":[117,154],"Kunpeng":[120,135],"CPU":[121],"platform":[122],"demonstrate":[123],"proposed":[126,162],"achieves":[128],"significant":[129],"improvements":[131],"compared":[132],"KML":[136],"math":[137],"library,":[138],"reaching":[139],"peak":[141],"up":[144],"2.1\u00d7":[146],"average":[149],"speedup":[150],"1.64\u00d7.":[152],"These":[153],"validate":[155],"effectiveness":[157],"efficiency":[159],"approach":[163],"handling":[165],"computation":[170],"scenarios.":[171]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-04-06T00:00:00"}
