{"id":"https://openalex.org/W2800891657","doi":"https://doi.org/10.1587/elex.15.20180286","title":"MALMM: A multi-array architecture for large-scale matrix multiplication on FPGA","display_name":"MALMM: A multi-array architecture for large-scale matrix multiplication on FPGA","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2800891657","doi":"https://doi.org/10.1587/elex.15.20180286","mag":"2800891657"},"language":"en","primary_location":{"id":"doi:10.1587/elex.15.20180286","is_oa":true,"landing_page_url":"https://doi.org/10.1587/elex.15.20180286","pdf_url":"https://www.jstage.jst.go.jp/article/elex/15/10/15_15.20180286/_pdf","source":{"id":"https://openalex.org/S207433681","display_name":"IEICE Electronics Express","issn_l":"1349-2543","issn":["1349-2543","1349-9467"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Electronics Express","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/elex/15/10/15_15.20180286/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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":true,"raw_author_name":"You Huang","raw_affiliation_strings":["College of Computer, National University of Defense Technology","National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology","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":["College of Computer, National University of Defense Technology","National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology","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":["College of Computer, National University of Defense Technology","National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology","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":["College of Computer, National University of Defense Technology","National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology","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":["College of Computer, National University of Defense Technology","National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101058401"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":1.2623,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7781716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"15","issue":"10","first_page":"20180286","last_page":"20180286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9915000200271606,"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7301831245422363},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6826055645942688},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6684699058532715},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6607702970504761},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.651333212852478},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6271275281906128},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4846244752407074},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4790812134742737},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.47014859318733215},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4176592528820038},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35200488567352295},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.33645665645599365},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2474338412284851},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15796974301338196}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7301831245422363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6826055645942688},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6684699058532715},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6607702970504761},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.651333212852478},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6271275281906128},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4846244752407074},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4790812134742737},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.47014859318733215},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4176592528820038},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35200488567352295},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.33645665645599365},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2474338412284851},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15796974301338196},{"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/elex.15.20180286","is_oa":true,"landing_page_url":"https://doi.org/10.1587/elex.15.20180286","pdf_url":"https://www.jstage.jst.go.jp/article/elex/15/10/15_15.20180286/_pdf","source":{"id":"https://openalex.org/S207433681","display_name":"IEICE Electronics Express","issn_l":"1349-2543","issn":["1349-2543","1349-9467"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Electronics Express","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/elex.15.20180286","is_oa":true,"landing_page_url":"https://doi.org/10.1587/elex.15.20180286","pdf_url":"https://www.jstage.jst.go.jp/article/elex/15/10/15_15.20180286/_pdf","source":{"id":"https://openalex.org/S207433681","display_name":"IEICE Electronics Express","issn_l":"1349-2543","issn":["1349-2543","1349-9467"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Electronics Express","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2800891657.pdf","grobid_xml":"https://content.openalex.org/works/W2800891657.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1005811612","https://openalex.org/W1509966554","https://openalex.org/W1582059966","https://openalex.org/W1686810756","https://openalex.org/W1995812446","https://openalex.org/W2016559894","https://openalex.org/W2061624656","https://openalex.org/W2097117768","https://openalex.org/W2108308693","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2404540148","https://openalex.org/W2963140246"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W4206811032","https://openalex.org/W2995605830","https://openalex.org/W4239424132","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2086123442"],"abstract_inverted_index":{"Large-scale":[0],"floating-point":[1],"matrix":[2,25,77],"multiplication":[3,26,78],"is":[4,69],"widely":[5],"used":[6],"in":[7,57],"many":[8],"scientific":[9],"and":[10,41],"engineering":[11],"applications.":[12],"Most":[13],"existing":[14],"works":[15],"focus":[16],"on":[17,27,81],"designing":[18],"a":[19,39,50],"linear":[20,63,97],"array":[21,98],"architecture":[22,36],"for":[23,76],"accelerating":[24],"FPGAs.":[28],"This":[29],"paper":[30],"towards":[31],"the":[32,55,58,73,92,96],"extension":[33,94],"of":[34,95],"this":[35],"by":[37],"proposing":[38],"scalable":[40],"highly":[42],"configurable":[43],"multi-array":[44],"architecture.":[45,99],"In":[46],"addition,":[47],"we":[48,89],"present":[49],"work-stealing":[51],"scheme":[52],"to":[53,71],"ensure":[54],"equality":[56],"workload":[59],"partition":[60],"among":[61],"multiple":[62],"arrays.":[64],"Furthermore,":[65],"an":[66],"analytical":[67],"model":[68],"developed":[70],"determine":[72],"optimal":[74,93],"parameters":[75],"acceleration.":[79],"Experiments":[80],"real-life":[82],"convolutional":[83],"neural":[84],"networks":[85],"(CNNs)":[86],"show":[87],"that":[88],"can":[90],"obtain":[91]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
