{"id":"https://openalex.org/W4401568712","doi":"https://doi.org/10.23919/date58400.2024.10546765","title":"MACO: Exploring GEMM Acceleration on a Loosely-Coupled Multi-Core Processor","display_name":"MACO: Exploring GEMM Acceleration on a Loosely-Coupled Multi-Core Processor","publication_year":2024,"publication_date":"2024-03-25","ids":{"openalex":"https://openalex.org/W4401568712","doi":"https://doi.org/10.23919/date58400.2024.10546765"},"language":"en","primary_location":{"id":"doi:10.23919/date58400.2024.10546765","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date58400.2024.10546765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Design, Automation & Test in Europe Conference & Exhibition (DATE)","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":"https://openalex.org/A5059001985","display_name":"Bingcai Sui","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":true,"raw_author_name":"Bingcai Sui","raw_affiliation_strings":["School of Computer, National University of Defense Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037428152","display_name":"Junzhong Shen","orcid":"https://orcid.org/0000-0001-6233-6800"},"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":"Junzhong Shen","raw_affiliation_strings":["School of Computer, National University of Defense Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110631223","display_name":"Caixia Sun","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":"Caixia Sun","raw_affiliation_strings":["School of Computer, National University of Defense Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084884735","display_name":"Junhui Wang","orcid":"https://orcid.org/0000-0002-6225-8045"},"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":"Junhui Wang","raw_affiliation_strings":["School of Computer, National University of Defense Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101573079","display_name":"Zhong Zheng","orcid":"https://orcid.org/0000-0002-2029-6107"},"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":"Zhong Zheng","raw_affiliation_strings":["School of Computer, National University of Defense Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101723213","display_name":"Wei Guo","orcid":"https://orcid.org/0000-0002-9769-6045"},"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":"Wei Guo","raw_affiliation_strings":["School of Computer, National University of Defense Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5059001985"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":2.4513,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.90235059,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9986000061035156,"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":0.9986000061035156,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9794999957084656,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9632999897003174,"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/acceleration","display_name":"Acceleration","score":0.7603621482849121},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7183800935745239},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.608945906162262},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5583457946777344},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5510379672050476},{"id":"https://openalex.org/keywords/many-core","display_name":"Many core","score":0.4742949306964874},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3688027858734131},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09732919931411743},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06045326590538025}],"concepts":[{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.7603621482849121},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7183800935745239},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.608945906162262},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5583457946777344},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5510379672050476},{"id":"https://openalex.org/C3020431745","wikidata":"https://www.wikidata.org/wiki/Q25325220","display_name":"Many core","level":2,"score":0.4742949306964874},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3688027858734131},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09732919931411743},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06045326590538025},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date58400.2024.10546765","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date58400.2024.10546765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G8497453205","display_name":null,"funder_award_id":"U23A2030I,6220248I","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2325556328","https://openalex.org/W2896457183","https://openalex.org/W2953212265","https://openalex.org/W2964080840","https://openalex.org/W2979545880","https://openalex.org/W3100023286","https://openalex.org/W3212852614","https://openalex.org/W3213528054","https://openalex.org/W4292779060","https://openalex.org/W4360831840","https://openalex.org/W6630562399","https://openalex.org/W6755207826","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2394430006","https://openalex.org/W4255057712","https://openalex.org/W2384472584","https://openalex.org/W163366574","https://openalex.org/W4251458280","https://openalex.org/W2512412909","https://openalex.org/W1547865754","https://openalex.org/W2126398188","https://openalex.org/W2116570023","https://openalex.org/W4210605172"],"abstract_inverted_index":{"General-purpose":[0],"processor":[1],"vendors":[2],"have":[3],"integrated":[4],"customized":[5],"accelerator":[6],"in":[7],"their":[8],"products":[9],"due":[10],"to":[11,26,37,39,93,137,148],"the":[12,29,40,63,69,78,96],"widespread":[13],"use":[14],"of":[15,33,67,99,118],"General":[16],"Matrix-Matrix":[17],"Multiplication":[18],"(GEMM)":[19],"kernels.":[20],"However,":[21],"it":[22],"remains":[23],"a":[24,51,72],"challenge":[25],"further":[27,94],"improve":[28],"flexibility":[30,66],"and":[31,65,87,89],"scalability":[32],"these":[34],"GEMM-enhanced":[35],"processors":[36],"cater":[38],"emerging":[41],"large-scale":[42],"GEMM":[43,102],"workloads.":[44,103,151],"In":[45],"this":[46],"paper":[47,70,79],"we":[48],"propose":[49],"MACO,":[50,68],"novel":[52],"loosely-coupled":[53],"multi-core":[54],"general-purpose":[55],"archi-tecture":[56],"optimized":[57],"for":[58,101],"GEMM-related":[59],"applications.":[60],"To":[61],"enhance":[62,95],"programmability":[64],"introduces":[71],"tile-based":[73],"instruction":[74],"set":[75],"architecture.":[76],"Additionally,":[77],"presents":[80],"techniques":[81],"such":[82],"as":[83],"hardware-assisted":[84],"data":[85],"prefetching":[86],"locking,":[88],"predictive":[90],"address":[91],"translation":[92],"computational":[97,116,143],"efficiency":[98,117],"MACO":[100,109,133],"The":[104],"experimental":[105],"results":[106],"demonstrate":[107],"that":[108,132],"exhibits":[110],"good":[111],"scalability,":[112],"achieving":[113],"an":[114],"average":[115],"90":[119],"%":[120,142],"across":[121],"multiple":[122],"cores.":[123],"Furthermore,":[124],"evaluations":[125],"on":[126],"state-of-the-art":[127],"deep":[128,149],"neural":[129],"networks":[130],"show":[131],"can":[134],"achieve":[135],"up":[136],"1.1":[138],"TFLOPS":[139],"with":[140],"88":[141],"efficiency,":[144],"indicating":[145],"its":[146],"adaptivity":[147],"learning":[150]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}