{"id":"https://openalex.org/W2605739168","doi":"https://doi.org/10.1109/asap.2017.7995254","title":"Parallel Multi Channel convolution using General Matrix Multiplication","display_name":"Parallel Multi Channel convolution using General Matrix Multiplication","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2605739168","doi":"https://doi.org/10.1109/asap.2017.7995254","mag":"2605739168"},"language":"en","primary_location":{"id":"doi:10.1109/asap.2017.7995254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2017.7995254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 28th International Conference on Application-specific Systems, Architectures and Processors (ASAP)","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/A5088962315","display_name":"Aravind Vasudevan","orcid":null},"institutions":[{"id":"https://openalex.org/I204442077","display_name":"Trinity College","ror":"https://ror.org/019dhar59","country_code":"CA","type":"education","lineage":["https://openalex.org/I204442077"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Aravind Vasudevan","raw_affiliation_strings":["Trinity College, School of Computer Science and Statistics, Dublin"],"affiliations":[{"raw_affiliation_string":"Trinity College, School of Computer Science and Statistics, Dublin","institution_ids":["https://openalex.org/I204442077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010687192","display_name":"Andrew Anderson","orcid":"https://orcid.org/0000-0002-4357-4739"},"institutions":[{"id":"https://openalex.org/I204442077","display_name":"Trinity College","ror":"https://ror.org/019dhar59","country_code":"CA","type":"education","lineage":["https://openalex.org/I204442077"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Andrew Anderson","raw_affiliation_strings":["Trinity College, School of Computer Science and Statistics, Dublin"],"affiliations":[{"raw_affiliation_string":"Trinity College, School of Computer Science and Statistics, Dublin","institution_ids":["https://openalex.org/I204442077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003800161","display_name":"David Gregg","orcid":"https://orcid.org/0000-0003-3782-4612"},"institutions":[{"id":"https://openalex.org/I204442077","display_name":"Trinity College","ror":"https://ror.org/019dhar59","country_code":"CA","type":"education","lineage":["https://openalex.org/I204442077"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"David Gregg","raw_affiliation_strings":["Trinity College, School of Computer Science and Statistics, Dublin"],"affiliations":[{"raw_affiliation_string":"Trinity College, School of Computer Science and Statistics, Dublin","institution_ids":["https://openalex.org/I204442077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088962315"],"corresponding_institution_ids":["https://openalex.org/I204442077"],"apc_list":null,"apc_paid":null,"fwci":4.0049,"has_fulltext":false,"cited_by_count":141,"citation_normalized_percentile":{"value":0.96367753,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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":0.9993000030517578,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9951000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8107107877731323},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7572571039199829},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.7496809363365173},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6893137693405151},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6877995729446411},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6167852878570557},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.573901355266571},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4630928337574005},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.44097277522087097},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39412832260131836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3496474623680115},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.189021497964859},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11479812860488892}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8107107877731323},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7572571039199829},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.7496809363365173},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6893137693405151},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6877995729446411},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6167852878570557},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.573901355266571},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4630928337574005},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.44097277522087097},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39412832260131836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3496474623680115},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.189021497964859},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11479812860488892},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asap.2017.7995254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2017.7995254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 28th International Conference on Application-specific Systems, Architectures and Processors (ASAP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1530262073","https://openalex.org/W1667652561","https://openalex.org/W1686810756","https://openalex.org/W1988425770","https://openalex.org/W2097117768","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2346804249","https://openalex.org/W2525543902","https://openalex.org/W2562339416","https://openalex.org/W2962835968","https://openalex.org/W4302296459","https://openalex.org/W6631660994","https://openalex.org/W6637151318","https://openalex.org/W6637373629","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W2017990332","https://openalex.org/W2080337923","https://openalex.org/W2964954556","https://openalex.org/W4287593139","https://openalex.org/W1488776355","https://openalex.org/W4244262766","https://openalex.org/W752783541","https://openalex.org/W3019910406","https://openalex.org/W1506547947"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"have":[4,135],"emerged":[5],"as":[6],"one":[7],"of":[8,24,79,139],"the":[9,27,47,76,80,113,119,126,130,152],"most":[10,21,161],"successful":[11],"machine":[12],"learning":[13],"technologies":[14],"for":[15,115],"image":[16,48],"and":[17,54,83,146],"video":[18],"processing.":[19],"The":[20],"computationally-intensive":[22],"parts":[23],"CNNs":[25],"are":[26],"convolutional":[28,42],"layers,":[29],"which":[30],"convolve":[31],"multi-channel":[32],"images":[33,132],"with":[34],"multiple":[35],"kernels.":[36],"A":[37],"common":[38],"approach":[39,94],"to":[40,45,95,124],"implementing":[41],"layers":[43],"is":[44,99,156],"expand":[46],"into":[49],"a":[50,92,143],"column":[51],"matrix":[52,82],"(im2col)":[53],"perform":[55],"Multiple":[56,58],"Channel":[57],"Kernel":[59],"(MCMK)":[60],"convolution":[61,97,127],"using":[62],"an":[63,147],"existing":[64],"parallel":[65],"General":[66,102],"Matrix":[67,103],"Multiplication":[68,104],"(GEMM)":[69],"library.":[70],"This":[71],"im2col":[72,159],"conversion":[73],"greatly":[74],"increases":[75],"memory":[77],"footprint":[78],"input":[81,120,131],"reduces":[84],"data":[85,116],"locality.":[86],"In":[87],"this":[88],"paper":[89],"we":[90],"propose":[91],"new":[93],"MCMK":[96],"that":[98],"based":[100],"on":[101,108,118,129,142],"(GEMM),":[105],"but":[106],"not":[107],"im2col.":[109],"Our":[110],"algorithm":[111,141,155],"eliminates":[112],"need":[114],"replication":[117],"thereby":[121],"enabling":[122],"us":[123],"apply":[125],"kernels":[128],"directly.":[133],"We":[134],"implemented":[136],"several":[137],"variants":[138],"our":[140,154],"CPU":[144],"processor":[145],"embedded":[148],"ARM":[149],"processor.":[150],"On":[151],"CPU,":[153],"faster":[157],"than":[158],"in":[160],"cases.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":1}],"updated_date":"2026-02-11T14:41:00.668223","created_date":"2025-10-10T00:00:00"}