{"id":"https://openalex.org/W3030955037","doi":"https://doi.org/10.1145/3397125.3397140","title":"A Design of GEMM Parallel Computing Accelerator Based on Vector SIMD Technology","display_name":"A Design of GEMM Parallel Computing Accelerator Based on Vector SIMD Technology","publication_year":2020,"publication_date":"2020-04-14","ids":{"openalex":"https://openalex.org/W3030955037","doi":"https://doi.org/10.1145/3397125.3397140","mag":"3030955037"},"language":"en","primary_location":{"id":"doi:10.1145/3397125.3397140","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397125.3397140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 6th International Conference on Computer and Technology Applications","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/A5020072616","display_name":"Yunping Zhao","orcid":"https://orcid.org/0000-0002-5600-3740"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"YunPing Zhao","raw_affiliation_strings":["Natl Univ Def Technol, Coll Comp, Changsha, Hunan, Peoples R China"],"affiliations":[{"raw_affiliation_string":"Natl Univ Def Technol, Coll Comp, Changsha, Hunan, Peoples R China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068184856","display_name":"Lu Jianzhuang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"JianZhuang Lu","raw_affiliation_strings":["Natl Univ Def Technol, Coll Comp, Changsha, Hunan, Peoples R China"],"affiliations":[{"raw_affiliation_string":"Natl Univ Def Technol, Coll Comp, Changsha, Hunan, Peoples R China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101792763","display_name":"Xiaowen Chen","orcid":"https://orcid.org/0000-0003-2558-8800"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"XiaoWen Chen","raw_affiliation_strings":["Natl Univ Def Technol, Coll Comp, Changsha, Hunan, Peoples R China"],"affiliations":[{"raw_affiliation_string":"Natl Univ Def Technol, Coll Comp, Changsha, Hunan, Peoples R China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020072616"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06431475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":null,"first_page":"122","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983999729156494,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8099477291107178},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.795548141002655},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7586318254470825},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.57759028673172},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.48642897605895996},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4464706778526306},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.44023871421813965},{"id":"https://openalex.org/keywords/vector-processor","display_name":"Vector processor","score":0.4368308484554291},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4255087375640869},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.41644710302352905},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.374557226896286},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17897722125053406}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8099477291107178},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.795548141002655},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7586318254470825},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.57759028673172},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.48642897605895996},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4464706778526306},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.44023871421813965},{"id":"https://openalex.org/C161824985","wikidata":"https://www.wikidata.org/wiki/Q919509","display_name":"Vector processor","level":2,"score":0.4368308484554291},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4255087375640869},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.41644710302352905},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.374557226896286},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17897722125053406},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3397125.3397140","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397125.3397140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 6th International Conference on Computer and Technology Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8799999952316284,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2056882228","https://openalex.org/W2903669223","https://openalex.org/W3000926397"],"related_works":["https://openalex.org/W2099629705","https://openalex.org/W1560663560","https://openalex.org/W2565725308","https://openalex.org/W2972668081","https://openalex.org/W3091978438","https://openalex.org/W4226248541","https://openalex.org/W7941220","https://openalex.org/W1982528625","https://openalex.org/W2038729084","https://openalex.org/W1577790836"],"abstract_inverted_index":{"Large-scale":[0],"floating-point":[1,122],"matrix":[2,81,161],"multiplication":[3],"is":[4,12,22,43,72,82,117,255,262,269],"widely":[5],"used":[6],"in":[7,162],"large-scale":[8],"scientific":[9],"computation.":[10],"It":[11],"a":[13,33,170,240],"typical":[14],"representative":[15],"of":[16,27,35,136,152,158,190,195,224,235],"fetch-intensive":[17],"and":[18,20,70,103,130,148,199,211,265],"computation-intensive,":[19],"it":[21],"the":[23,46,50,56,62,65,76,79,89,95,99,110,133,150,156,163,183,193,207,213,218,222,233,236,246,252,257,266],"key":[24],"that":[25,232],"improve":[26],"system":[28,215],"performance.":[29],"In":[30],"this":[31],"paper,":[32],"design":[34,234],"GEMM":[36,57],"accelerator":[37,63,237],"based":[38,108,114,177],"on":[39,109,115,178,229],"vector":[40,51],"SIMD":[41,52],"technology":[42,53],"proposed.":[44],"Combining":[45],"block":[47],"algorithm":[48],"with":[49,245],"to":[54,61,140,143,205,221],"realize":[55,192],"calculation":[58,164,198,267],"by":[59,84,91,155],"mapping":[60],"structure,":[64],"parallel":[66,112],"performance":[67,261],"both":[68],"MMPU":[69,107],"PE":[71],"fully":[73],"utilized.":[74],"At":[75],"same":[77],"time,":[78,210],"Kernel-level":[80],"calculated":[83],"row,":[85],"which":[86,119,180],"avoids":[87],"access":[88,101],"data":[90,173,184,201,208],"column":[92],"or":[93],"transposes":[94],"matrix,":[96],"thereby":[97],"improving":[98],"memory":[100],"efficiency":[102,268],"operation":[104],"efficiency.":[105],"The":[106,226],"extended":[111],"structure":[113],"Systolic":[116],"proposed,":[118],"can":[120,181,238],"avoid":[121],"addition":[123],"between":[124,187],"PEs":[125],"while":[126],"ensuring":[127],"high":[128,145],"parallelism":[129],"independence,":[131],"reduce":[132,149],"additional":[134],"overhead":[135,186],"inner":[137],"loop":[138,142],"flow":[139],"outer":[141],"achieve":[144,239],"efficient":[146],"flow,":[147],"burden":[151],"bandwidth":[153],"caused":[154],"handling":[157],"intermediate":[159],"value":[160],"process.":[165],"This":[166],"paper":[167],"also":[168],"proposes":[169],"double":[171],"buffer":[172],"moving":[174,185,209],"optimization":[175],"strategy":[176],"DMA,":[179],"smooth":[182],"all":[188],"levels":[189],"storage,":[191],"overlapping":[194],"kernel":[196],"level":[197],"DMA":[200],"moving,":[202],"so":[203],"as":[204],"hide":[206],"make":[212],"whole":[214],"run":[216],"at":[217],"speed":[219],"close":[220],"peak":[223],"PE.":[225],"experimental":[227],"results":[228],"FPGA":[230],"show":[231],"good":[241],"acceleration":[242,253],"effect.":[243],"Compared":[244],"arm":[247],"Cortex-A75":[248],"dual":[249],"core":[250],"processor,":[251],"ratio":[254],"8.3,":[256],"unit":[258],"power":[259],"consumption":[260],"13.01":[263],"GFLOPS/W,":[264],"over":[270],"99%.":[271]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}