{"id":"https://openalex.org/W4408092752","doi":"https://doi.org/10.1109/hipcw63042.2024.00086","title":"Maximizing Multi-Core Efficiency in BLAS: A Scalable Architecture for Performance","display_name":"Maximizing Multi-Core Efficiency in BLAS: A Scalable Architecture for Performance","publication_year":2024,"publication_date":"2024-12-18","ids":{"openalex":"https://openalex.org/W4408092752","doi":"https://doi.org/10.1109/hipcw63042.2024.00086"},"language":"en","primary_location":{"id":"doi:10.1109/hipcw63042.2024.00086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipcw63042.2024.00086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 31st International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW)","raw_type":"proceedings-article"},"type":"article","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":null,"display_name":"Shivam Gautam","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shivam Gautam","raw_affiliation_strings":["Fujitsu Research of India,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"Fujitsu Research of India,Bangalore,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116479485","display_name":"Deeksha Goplani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deeksha Goplani","raw_affiliation_strings":["Fujitsu Research of India,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"Fujitsu Research of India,Bangalore,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038031993","display_name":"Darshan Patel","orcid":"https://orcid.org/0000-0003-1370-2864"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Darshan Patel","raw_affiliation_strings":["Fujitsu Research of India,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"Fujitsu Research of India,Bangalore,India","institution_ids":[]}]},{"author_position":"middle","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"],"affiliations":[{"raw_affiliation_string":"Fujitsu Research of India,Bangalore,India","institution_ids":[]}]},{"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"],"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"],"affiliations":[{"raw_affiliation_string":"Fujitsu Limited,Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100454771","display_name":"Priyanka Sharma","orcid":"https://orcid.org/0000-0003-2156-9952"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Priyanka Sharma","raw_affiliation_strings":["Fujitsu Research of India,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"Fujitsu Research of India,Bangalore,India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"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":0.30281164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"217","last_page":"218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9660999774932861,"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":0.9660999774932861,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.902999997138977,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7426027655601501},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.6777125597000122},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6460546851158142},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.590009331703186},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5347396731376648},{"id":"https://openalex.org/keywords/many-core","display_name":"Many core","score":0.522075355052948},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.47109872102737427},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.43486273288726807},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18160811066627502},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1133081316947937}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7426027655601501},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.6777125597000122},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6460546851158142},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.590009331703186},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5347396731376648},{"id":"https://openalex.org/C3020431745","wikidata":"https://www.wikidata.org/wiki/Q25325220","display_name":"Many core","level":2,"score":0.522075355052948},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.47109872102737427},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43486273288726807},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18160811066627502},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1133081316947937},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hipcw63042.2024.00086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipcw63042.2024.00086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 31st International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321034","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2264746079","https://openalex.org/W2093601330","https://openalex.org/W3023876411","https://openalex.org/W2174522811","https://openalex.org/W123152114","https://openalex.org/W2394430006","https://openalex.org/W4255057712","https://openalex.org/W1516700698","https://openalex.org/W2384472584","https://openalex.org/W163366574"],"abstract_inverted_index":{"Basic":[0],"Linear":[1],"Algebra":[2],"Subprograms":[3],"(BLAS)":[4],"operations":[5],"are":[6],"fundamental":[7],"computational":[8,74],"building":[9],"blocks":[10],"widely":[11],"used":[12],"in":[13,51,94],"machine":[14],"learning":[15],"models":[16],"and":[17,45,83,91,112,136],"AI":[18],"libraries.":[19],"Among":[20],"BLAS":[21,55,99],"routines,":[22],"General":[23],"Matrix":[24],"multiplication(GEMM)":[25],"is":[26],"one":[27],"of":[28,63,76,128,134],"the":[29,72,116],"most":[30],"computationally":[31],"intensive":[32],"tasks,":[33],"making":[34],"it":[35],"crucial":[36],"to":[37,70,120],"leverage":[38],"multi-core":[39],"CPU":[40,84],"systems":[41],"for":[42,59,131],"enhanced":[43,92],"efficiency":[44],"speed.":[46],"The":[47],"existing":[48],"threading":[49],"architecture":[50,93],"OpenBLAS,":[52,121],"a":[53,60,66,89,139],"popular":[54],"library,":[56],"only":[57],"allows":[58],"single":[61],"execution":[62],"GEMM":[64],"at":[65],"time,":[67],"which":[68],"fails":[69],"meet":[71],"extensive":[73],"requirements":[75],"modern":[77],"applications.":[78],"This":[79],"limitation":[80],"restricts":[81],"parallelism":[82],"core":[85,113],"utilization.This":[86],"poster":[87],"introduces":[88],"scalable":[90],"OpenBLAS":[95],"that":[96],"facilitates":[97],"parallel":[98],"executions":[100],"with":[101],"loosely":[102],"coupled":[103],"synchronization":[104],"using":[105],"POSIX":[106],"conditional":[107],"variables,":[108],"thereby":[109],"boosting":[110],"performance":[111],"utilization.":[114],"With":[115],"proposed":[117],"algorithmic":[118],"changes":[119],"we":[122],"have":[123],"observed":[124],"an":[125],"average":[126],"improvement":[127],"30":[129],"%":[130],"matrix":[132],"sizes":[133],"128":[135],"256":[137],"on":[138],"64-core":[140],"AWS":[141],"Graviton3":[142],"instance.":[143]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}