{"id":"https://openalex.org/W7148461932","doi":"https://doi.org/10.1109/hipcw66559.2025.00103","title":"Optimizing BLAS GEMM Kernel Performance: Scalable Multi-Core and Vectorized Design","display_name":"Optimizing BLAS GEMM Kernel Performance: Scalable Multi-Core and Vectorized Design","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7148461932","doi":"https://doi.org/10.1109/hipcw66559.2025.00103"},"language":null,"primary_location":{"id":"doi:10.1109/hipcw66559.2025.00103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipcw66559.2025.00103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 32nd International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5116479486","display_name":"Ragesh Hajela","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ragesh Hajela","raw_affiliation_strings":["Fujitsu Research of India,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research of India,Bangalore,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040654017","display_name":"Masato Nakagawa","orcid":"https://orcid.org/0000-0003-3067-7322"},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Nakagawa","raw_affiliation_strings":["Fujitsu Limited,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Limited,Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112225690","display_name":"A. Nukariya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atsushi Nukariya","raw_affiliation_strings":["Fujitsu Research of India,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research of India,Bangalore,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055425238","display_name":"Kuninori Ishii","orcid":null},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kuninori Ishii","raw_affiliation_strings":["Fujitsu Limited,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Limited,Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116479487","display_name":"Masahiro Doteguchi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masahiro Doteguchi","raw_affiliation_strings":["Fujitsu Research of India,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research of India,Bangalore,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035610545","display_name":"Ikuo Miyoshi","orcid":null},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ikuo Miyoshi","raw_affiliation_strings":["Fujitsu Limited,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Limited,Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132827667","display_name":"Priyanka Sharma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Priyanka Sharma","raw_affiliation_strings":["Fujitsu Research of India,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research of India,Bangalore,India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"297","last_page":"298"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.07419999688863754,"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":0.07419999688863754,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.07419999688863754,"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/T11269","display_name":"Algorithms and Data Compression","score":0.058400001376867294,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/kernel","display_name":"Kernel (algebra)","score":0.5016000270843506},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.47540000081062317},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.3043000102043152},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.2750000059604645},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.27390000224113464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7290999889373779},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5016000270843506},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4828999936580658},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47540000081062317},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44449999928474426},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.30709999799728394},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.25850000977516174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hipcw66559.2025.00103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipcw66559.2025.00103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 32nd International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.4187372326850891}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337495","display_name":"Technology Development","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Basic":[0],"Linear":[1],"Algebra":[2],"Subprograms":[3],"(BLAS)":[4],"are":[5],"core":[6,46],"computational":[7],"building":[8],"blocks":[9],"in":[10,137],"AI":[11],"and":[12,36,44,61],"HPC,":[13,150],"with":[14,70],"General":[15],"Matrix":[16],"Multiplication":[17],"(GEMM)":[18],"being":[19],"among":[20],"the":[21],"most":[22],"compute-intensive":[23],"kernels.":[24],"On":[25],"Arm":[26,139],"CPUs,":[27],"OpenBLAS":[28],"currently":[29],"lacks":[30],"optimized":[31,84],"kernels":[32,52],"for":[33,53,108,148],"small":[34,54],"matrices":[35],"suffers":[37],"from":[38],"inefficient":[39],"multithreading,":[40],"limiting":[41],"both":[42],"parallelism":[43],"CPU":[45,140],"utilization.This":[47],"poster":[48],"presents":[49],"new":[50,71,98,113],"architectural":[51],"GEMM":[55,128,146],"using":[56],"Scalable":[57],"Vector":[58],"Extensions":[59],"(SVE)":[60],"enhanced":[62],"multi-threading":[63],"strategies.":[64],"Newly":[65],"developed":[66],"SVE":[67],"kernels,":[68],"enabled":[69],"macro":[72,99],"GEMM_SMALL_MATRIX_PERMIT,":[73],"deliver":[74],"up":[75],"to":[76],"1.25x":[77],"speedup":[78],"on":[79],"irregular":[80],"matrix":[81],"shapes,":[82],"while":[83],"rectangular":[85],"packing":[86],"improves":[87],"small-K":[88],"workloads":[89],"by":[90],"further":[91,105],"1.20x.":[92],"To":[93],"efficiently":[94],"manage":[95],"DIVIDE_RATE":[96],"threshold,":[97],"GEMM_DIVIDE_LIMIT":[100],"has":[101],"been":[102],"introduced,":[103],"which":[104,119],"boosts":[106],"efficiency":[107],"small-N":[109],"cases.":[110],"Additionally,":[111],"a":[112],"load-balancing":[114],"design":[115],"approach":[116],"is":[117],"proposed":[118],"addresses":[120],"partitioning":[121],"inefficiencies,":[122],"achieving":[123],"smoother,":[124],"more":[125,144],"scalable":[126],"thread-parallel":[127],"execution":[129,147],"across":[130],"cores.Together,":[131],"these":[132],"advances":[133],"represent":[134],"significant":[135],"progress":[136],"unlocking":[138],"potential,":[141],"enabling":[142],"faster,":[143],"efficient":[145],"AI,":[149],"scientific":[151],"computing":[152],"workloads.":[153]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-03T00:00:00"}