{"id":"https://openalex.org/W2963140246","doi":"https://doi.org/10.1109/iscas.2018.8351474","title":"Towards a Multi-array Architecture for Accelerating Large-scale Matrix Multiplication on FPGAs","display_name":"Towards a Multi-array Architecture for Accelerating Large-scale Matrix Multiplication on FPGAs","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2963140246","doi":"https://doi.org/10.1109/iscas.2018.8351474","mag":"2963140246"},"language":"en","primary_location":{"id":"doi:10.1109/iscas.2018.8351474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2018.8351474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Symposium on Circuits and Systems (ISCAS)","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/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":true,"raw_author_name":"Junzhong Shen","raw_affiliation_strings":["National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102984199","display_name":"Yuran Qiao","orcid":"https://orcid.org/0000-0002-5488-3545"},"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":"Yuran Qiao","raw_affiliation_strings":["National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101058401","display_name":"You Huang","orcid":"https://orcid.org/0000-0002-9006-1522"},"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":"You Huang","raw_affiliation_strings":["National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101937502","display_name":"Mei Wen","orcid":"https://orcid.org/0000-0002-5875-3297"},"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":"Mei Wen","raw_affiliation_strings":["National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100710936","display_name":"Chunyuan Zhang","orcid":"https://orcid.org/0000-0002-0944-2708"},"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":"Chunyuan Zhang","raw_affiliation_strings":["National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037428152"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":6.3117,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.97335615,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9984999895095825,"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"}},{"id":"https://openalex.org/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9983000159263611,"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/systolic-array","display_name":"Systolic array","score":0.7303796410560608},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7153929471969604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7138398885726929},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6394788026809692},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.622059166431427},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5888053178787231},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.51643967628479},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5085843801498413},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.447458416223526},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.434908926486969},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4327714443206787},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4201269745826721},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.41576242446899414},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35462579131126404},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.33717668056488037},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3311622142791748},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.22865569591522217},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13890957832336426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11886325478553772},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.10921168327331543}],"concepts":[{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.7303796410560608},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7153929471969604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7138398885726929},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6394788026809692},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.622059166431427},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5888053178787231},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.51643967628479},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5085843801498413},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.447458416223526},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.434908926486969},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4327714443206787},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4201269745826721},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.41576242446899414},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35462579131126404},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.33717668056488037},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3311622142791748},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.22865569591522217},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13890957832336426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11886325478553772},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.10921168327331543},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas.2018.8351474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2018.8351474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W114677020","https://openalex.org/W1005811612","https://openalex.org/W1511216606","https://openalex.org/W1582059966","https://openalex.org/W1995812446","https://openalex.org/W2016559894","https://openalex.org/W2061624656","https://openalex.org/W2073510583","https://openalex.org/W2107356030","https://openalex.org/W2108308693","https://openalex.org/W2126069080","https://openalex.org/W2163605009","https://openalex.org/W2344729295","https://openalex.org/W6678722967","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W2022229285","https://openalex.org/W1506547947","https://openalex.org/W46448156","https://openalex.org/W2283084692","https://openalex.org/W2130878144","https://openalex.org/W4206811032","https://openalex.org/W2995605830"],"abstract_inverted_index":{"Large-scale":[0],"floating-point":[1],"matrix":[2,21],"multiplication":[3,22],"is":[4,71],"a":[5,27,41,52,81],"fundamental":[6],"kernel":[7],"in":[8,59],"many":[9],"scientific":[10],"and":[11,43],"engineering":[12],"applications.":[13],"Most":[14],"existing":[15],"work":[16],"only":[17],"focus":[18],"on":[19,23,80],"accelerating":[20],"FPGA":[24],"by":[25,39],"adopting":[26],"linear":[28,65,97],"systolic":[29],"array.":[30],"This":[31],"paper":[32],"towards":[33],"the":[34,57,60,75,92,96],"extension":[35,94],"of":[36,95],"this":[37],"architecture":[38],"proposing":[40],"scalable":[42],"highly":[44],"configurable":[45],"multi-array":[46],"architecture.":[47,99],"In":[48],"addition,":[49],"we":[50,89],"propose":[51],"work-stealing":[53],"scheme":[54],"to":[55,73],"ensure":[56],"equality":[58],"workload":[61],"partition":[62],"among":[63],"multiple":[64],"arrays.":[66],"Furthermore,":[67],"an":[68],"analytical":[69],"model":[70],"developed":[72],"determine":[74],"optimal":[76,93],"design":[77],"parameters.":[78],"Experiments":[79],"real-life":[82],"convolutional":[83],"neural":[84],"network":[85],"(CNN)":[86],"show":[87],"that":[88],"can":[90],"obtain":[91],"array":[98]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}