{"id":"https://openalex.org/W3000434371","doi":"https://doi.org/10.1109/tcsii.2020.2965154","title":"Optimizing Hardware Accelerated General Matrix-Matrix Multiplication for CNNs on FPGAs","display_name":"Optimizing Hardware Accelerated General Matrix-Matrix Multiplication for CNNs on FPGAs","publication_year":2020,"publication_date":"2020-01-09","ids":{"openalex":"https://openalex.org/W3000434371","doi":"https://doi.org/10.1109/tcsii.2020.2965154","mag":"3000434371"},"language":"en","primary_location":{"id":"doi:10.1109/tcsii.2020.2965154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsii.2020.2965154","pdf_url":null,"source":{"id":"https://openalex.org/S93916849","display_name":"IEEE Transactions on Circuits & Systems II Express Briefs","issn_l":"1549-7747","issn":["1549-7747","1558-3791"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems II: Express Briefs","raw_type":"journal-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/A5060826708","display_name":"Afzal Ahmad","orcid":"https://orcid.org/0000-0003-4491-5440"},"institutions":[{"id":"https://openalex.org/I207789805","display_name":"Lahore University of Management Sciences","ror":"https://ror.org/05b5x4a35","country_code":"PK","type":"education","lineage":["https://openalex.org/I207789805"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Afzal Ahmad","raw_affiliation_strings":["Department of Electrical Engineering, Syed Babar Ali School of Science and Engineering, Lahore University of Management Sciences, Lahore, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Syed Babar Ali School of Science and Engineering, Lahore University of Management Sciences, Lahore, Pakistan","institution_ids":["https://openalex.org/I207789805"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069432255","display_name":"Muhammad Adeel Pasha","orcid":"https://orcid.org/0000-0001-9892-5201"},"institutions":[{"id":"https://openalex.org/I207789805","display_name":"Lahore University of Management Sciences","ror":"https://ror.org/05b5x4a35","country_code":"PK","type":"education","lineage":["https://openalex.org/I207789805"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Adeel Pasha","raw_affiliation_strings":["Department of Electrical Engineering, Syed Babar Ali School of Science and Engineering, Lahore University of Management Sciences, Lahore, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Syed Babar Ali School of Science and Engineering, Lahore University of Management Sciences, Lahore, Pakistan","institution_ids":["https://openalex.org/I207789805"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060826708"],"corresponding_institution_ids":["https://openalex.org/I207789805"],"apc_list":null,"apc_paid":null,"fwci":2.5555,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.91203158,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"67","issue":"11","first_page":"2692","last_page":"2696"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9944000244140625,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9936000108718872,"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8468737602233887},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8231749534606934},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.663702130317688},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6162770390510559},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6088873147964478},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.5953105688095093},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5486463308334351},{"id":"https://openalex.org/keywords/gate-array","display_name":"Gate array","score":0.5205796360969543},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4714471101760864},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4516271650791168},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.44917601346969604},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4441894292831421},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3681463599205017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26086854934692383},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22289946675300598}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8468737602233887},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8231749534606934},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.663702130317688},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6162770390510559},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6088873147964478},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.5953105688095093},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5486463308334351},{"id":"https://openalex.org/C114237110","wikidata":"https://www.wikidata.org/wiki/Q114901","display_name":"Gate array","level":3,"score":0.5205796360969543},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4714471101760864},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4516271650791168},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.44917601346969604},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4441894292831421},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3681463599205017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26086854934692383},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22289946675300598},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsii.2020.2965154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsii.2020.2965154","pdf_url":null,"source":{"id":"https://openalex.org/S93916849","display_name":"IEEE Transactions on Circuits & Systems II Express Briefs","issn_l":"1549-7747","issn":["1549-7747","1558-3791"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems II: Express Briefs","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2604814848","https://openalex.org/W2612445135","https://openalex.org/W2627042741","https://openalex.org/W2796160902","https://openalex.org/W2907579173","https://openalex.org/W2951898149","https://openalex.org/W2963125010","https://openalex.org/W4297775537","https://openalex.org/W6737664043"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W2017990332","https://openalex.org/W2080337923","https://openalex.org/W4287593139","https://openalex.org/W1488776355","https://openalex.org/W4244262766","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W4206811032","https://openalex.org/W2995605830"],"abstract_inverted_index":{"Convolution":[0],"is":[1,22],"inarguably":[2],"the":[3,15,27,121,139],"most":[4],"complex":[5,155],"operation":[6],"utilized":[7,98],"in":[8,45,160],"Convolutional":[9],"Neural":[10],"Networks":[11],"(convnets).":[12],"Owing":[13],"to":[14,66,99,119],"billions":[16],"of":[17,30,33,123,126,143],"independent":[18],"multiply-adds":[19],"involved,":[20],"convolution":[21],"being":[23,97],"massively":[24],"parallelized":[25],"by":[26],"simultaneous":[28],"utilization":[29],"many":[31],"cores":[32],"Graphical":[34],"Processing":[35],"Units":[36],"(GPUs).":[37],"Although":[38],"GPUs":[39],"have":[40,76],"shown":[41],"significant":[42,135],"performance":[43,136],"improvements":[44,137],"both":[46,60,144],"training":[47],"and":[48,62,84,154],"inference":[49],"stages,":[50],"they":[51,95],"are":[52,96,148,158],"not":[53],"well-suited":[54],"for":[55,103,114],"mobile":[56,151],"vision":[57,152],"applications":[58],"where":[59],"energy":[61,90],"real-time":[63],"constraints":[64],"need":[65],"be":[67],"satisfied.":[68],"In":[69,106],"contrast,":[70],"Field":[71],"Programmable":[72],"Gate":[73],"Arrays":[74],"(FPGAs)":[75],"demonstrated":[77],"massive":[78],"parallelization":[79],"capabilities,":[80],"with":[81],"fast":[82],"DSPs":[83],"on-chip":[85],"memory,":[86],"at":[87],"a":[88],"lower":[89],"cost":[91],"than":[92],"GPUs.":[93],"Hence,":[94],"design":[100,110],"convnet":[101,130],"accelerators":[102],"embedded":[104],"applications.":[105,162],"this":[107],"brief,":[108],"we":[109],"an":[111,128],"FPGA-based":[112,141],"accelerator":[113],"general":[115],"matrix-matrix":[116],"multiplication":[117],"(GeMM)":[118],"improve":[120],"efficiency":[122],"convolutional":[124],"layers":[125],"Shufflenet,":[127],"efficient":[129,145],"architecture.":[131],"Experimental":[132],"results":[133],"show":[134],"against":[138],"state-of-the-art":[140],"implementations":[142],"convnets":[146,156],"that":[147,157],"tailored":[149],"towards":[150],"applications,":[153],"used":[159],"traditional":[161]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}