{"id":"https://openalex.org/W2946048183","doi":"https://doi.org/10.23919/date.2019.8714915","title":"Improving the DRAM Access Efficiency for Matrix Multiplication on Multicore Accelerators","display_name":"Improving the DRAM Access Efficiency for Matrix Multiplication on Multicore Accelerators","publication_year":2019,"publication_date":"2019-03-01","ids":{"openalex":"https://openalex.org/W2946048183","doi":"https://doi.org/10.23919/date.2019.8714915","mag":"2946048183"},"language":"en","primary_location":{"id":"doi:10.23919/date.2019.8714915","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date.2019.8714915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Design, Automation &amp; Test in Europe Conference &amp; 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/A5100760813","display_name":"Sheng Ma","orcid":"https://orcid.org/0000-0003-1710-4060"},"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":"Sheng Ma","raw_affiliation_strings":["State Key Laboratory of High Performance Computing, National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of High Performance Computing, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100720832","display_name":"Yang Guo","orcid":"https://orcid.org/0000-0001-9050-0866"},"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":"Yang Guo","raw_affiliation_strings":["State Key Laboratory of High Performance Computing, National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of High Performance Computing, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083377397","display_name":"Shenggang Chen","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":"Shenggang Chen","raw_affiliation_strings":["State Key Laboratory of High Performance Computing, National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of High Performance Computing, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044840341","display_name":"Libo Huang","orcid":"https://orcid.org/0000-0001-7878-3998"},"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":"Libo Huang","raw_affiliation_strings":["State Key Laboratory of High Performance Computing, National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of High Performance Computing, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457904","display_name":"Zhiying Wang","orcid":"https://orcid.org/0009-0003-6888-3890"},"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":"Zhiying Wang","raw_affiliation_strings":["State Key Laboratory of High Performance Computing, National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of High Performance Computing, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100760813"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.2461,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.47521346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1058","last_page":"1063"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7898015379905701},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.7450753450393677},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6895114183425903},{"id":"https://openalex.org/keywords/memory-controller","display_name":"Memory controller","score":0.6260444521903992},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5580692291259766},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.5068262219429016},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.49846768379211426},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4796764850616455},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4681644141674042},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.45842280983924866},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4486503601074219},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.439103901386261},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.434295654296875},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.352192223072052},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.09072768688201904}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7898015379905701},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.7450753450393677},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6895114183425903},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.6260444521903992},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5580692291259766},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5068262219429016},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.49846768379211426},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4796764850616455},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4681644141674042},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.45842280983924866},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4486503601074219},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.439103901386261},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.434295654296875},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.352192223072052},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.09072768688201904},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date.2019.8714915","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date.2019.8714915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Design, Automation &amp; Test in Europe Conference &amp; Exhibition (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.9100000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1848142254","https://openalex.org/W2039747889","https://openalex.org/W2043275593","https://openalex.org/W2059807497","https://openalex.org/W2073061372","https://openalex.org/W2093608182","https://openalex.org/W2114440707","https://openalex.org/W2115172404","https://openalex.org/W2155503253","https://openalex.org/W2156355519","https://openalex.org/W2170996201","https://openalex.org/W2238307037","https://openalex.org/W2252007067","https://openalex.org/W2293640271","https://openalex.org/W2340076492","https://openalex.org/W4242759096","https://openalex.org/W6639079118"],"related_works":["https://openalex.org/W1976244802","https://openalex.org/W4293430534","https://openalex.org/W2335743642","https://openalex.org/W4297812927","https://openalex.org/W2800412005","https://openalex.org/W2122646225","https://openalex.org/W2154976966","https://openalex.org/W2547220881","https://openalex.org/W1603816627","https://openalex.org/W2542815272"],"abstract_inverted_index":{"The":[0,14],"parallelization":[1],"of":[2,43],"matrix":[3,10],"multiplication":[4],"on":[5],"multicore":[6],"accelerators":[7],"divides":[8],"a":[9,68,84],"into":[11],"several":[12],"partitions.":[13],"existing":[15],"design":[16,33],"deploys":[17],"an":[18,118],"independent":[19],"DMA":[20,46],"transfer":[21,59],"for":[22,100,106],"each":[23,50],"core":[24],"to":[25,60,71,76],"access":[26,37,41,80],"its":[27],"own":[28],"partition":[29],"from":[30],"DRAM.":[31],"This":[32],"has":[34],"poor":[35],"memory":[36,40,120],"efficiency,":[38],"since":[39],"streams":[42],"multiple":[44],"concurrent":[45],"transfers":[47],"interfere":[48],"with":[49,83],"other.":[51],"We":[52],"propose":[53],"Distributed-DMA":[54],"(D-DMA),":[55],"which":[56],"invokes":[57],"one":[58],"serve":[61],"all":[62],"cores.":[63],"D-DMA":[64,87,115],"accesses":[65],"data":[66],"in":[67],"row-major":[69],"manner":[70],"efficiently":[72],"exploit":[73],"inter-partition":[74],"locality":[75],"improve":[77],"the":[78,89,107],"DRAM":[79,95],"efficiency.":[81],"Compared":[82],"baseline":[85],"design,":[86],"improves":[88],"bandwidth":[90],"by":[91,98],"84.8%":[92],"and":[93],"reduces":[94],"energy":[96],"consumption":[97],"43.1%":[99],"micro-benchmarks.":[101],"It":[102],"achieves":[103],"higher":[104],"performance":[105],"GEMM":[108],"benchmark.":[109],"With":[110],"much":[111],"lower":[112],"hardware":[113],"cost,":[114],"significantly":[116],"outperforms":[117],"out-of-order":[119],"controller.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}
