{"id":"https://openalex.org/W2598419480","doi":"https://doi.org/10.1145/3029580.3029585","title":"MTP-Caffe","display_name":"MTP-Caffe","publication_year":2017,"publication_date":"2017-01-25","ids":{"openalex":"https://openalex.org/W2598419480","doi":"https://doi.org/10.1145/3029580.3029585","mag":"2598419480"},"language":"en","primary_location":{"id":"doi:10.1145/3029580.3029585","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3029580.3029585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop and 6th Workshop on Parallel Programming and Run-Time Management Techniques for Many-core Architectures and Design Tools and Architectures for Multicore Embedded Computing Platforms","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/A5062131020","display_name":"Yu Yang","orcid":"https://orcid.org/0000-0003-2396-3590"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Y. Yang","raw_affiliation_strings":["Royal Institute of Technology, Sweden"],"affiliations":[{"raw_affiliation_string":"Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110761812","display_name":"Syed M. A. H. Jafri","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Syed M. A. H. Jafri","raw_affiliation_strings":["Royal Institute of Technology, Sweden"],"affiliations":[{"raw_affiliation_string":"Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026355063","display_name":"Ahmed Hemani","orcid":"https://orcid.org/0000-0003-0565-9376"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"A. Hemani","raw_affiliation_strings":["Royal Institute of Technology, Sweden"],"affiliations":[{"raw_affiliation_string":"Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048826742","display_name":"Dimitrios Stathis","orcid":"https://orcid.org/0000-0002-5697-4272"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"D. Stathis","raw_affiliation_strings":["Royal Institute of Technology, Sweden"],"affiliations":[{"raw_affiliation_string":"Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062131020"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02242821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9986000061035156,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8183068037033081},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7521089315414429},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7364574670791626},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6242952942848206},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5313858389854431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5253303050994873},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.47204598784446716},{"id":"https://openalex.org/keywords/cellular-neural-network","display_name":"Cellular neural network","score":0.46648648381233215},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.4304671883583069},{"id":"https://openalex.org/keywords/transformation-matrix","display_name":"Transformation matrix","score":0.4119185209274292},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.354587584733963},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.33902278542518616}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8183068037033081},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7521089315414429},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7364574670791626},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6242952942848206},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5313858389854431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5253303050994873},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47204598784446716},{"id":"https://openalex.org/C812465","wikidata":"https://www.wikidata.org/wiki/Q5058375","display_name":"Cellular neural network","level":3,"score":0.46648648381233215},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.4304671883583069},{"id":"https://openalex.org/C165443888","wikidata":"https://www.wikidata.org/wiki/Q1482183","display_name":"Transformation matrix","level":3,"score":0.4119185209274292},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.354587584733963},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.33902278542518616},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3029580.3029585","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3029580.3029585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop and 6th Workshop on Parallel Programming and Run-Time Management Techniques for Many-core Architectures and Design Tools and Architectures for Multicore Embedded Computing Platforms","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":29,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W629759988","https://openalex.org/W753012316","https://openalex.org/W1487583988","https://openalex.org/W1872489089","https://openalex.org/W1943732115","https://openalex.org/W1993356715","https://openalex.org/W2016881569","https://openalex.org/W2067523571","https://openalex.org/W2094756095","https://openalex.org/W2097117768","https://openalex.org/W2112796928","https://openalex.org/W2152839228","https://openalex.org/W2155893237","https://openalex.org/W2159504848","https://openalex.org/W2163605009","https://openalex.org/W2266946669","https://openalex.org/W2442974303","https://openalex.org/W2553286638","https://openalex.org/W2604272474","https://openalex.org/W2618530766","https://openalex.org/W2906043559","https://openalex.org/W2950094539","https://openalex.org/W2950179405","https://openalex.org/W2950656546","https://openalex.org/W2963542991","https://openalex.org/W4285719527","https://openalex.org/W6639260565","https://openalex.org/W6674914833"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W1488881018"],"abstract_inverted_index":{"In":[0],"the":[1,4,20,35,38,42,60,65,70,72,98,102,124],"recent":[2],"past,":[3],"Convolutional":[5],"Neural":[6],"Networks":[7],"(CNNs)":[8],"have":[9,26],"attracted":[10],"intense":[11],"research.":[12],"The":[13],"high":[14],"processing":[15],"requirements":[16],"(of":[17],"CNNs)":[18],"and":[19,74,93,101,135],"availability":[21],"of":[22,64],"efficient":[23],"mapping":[24,39],"tools":[25,40],"made":[27],"GPUs":[28],"a":[29,107],"popular":[30],"CNN":[31,99,108],"accelerator.":[32],"To":[33,78],"extract":[34],"maximum":[36],"performance,":[37],"transform":[41],"unsupported":[43],"convolutions":[44],"to":[45,105,132,137],"GPU":[46,66,103,114],"supported":[47],"matrix":[48],"multiplications.":[49],"However,":[50],"this":[51,80],"transformation":[52,71],"incurs":[53],"significant":[54],"memory":[55,126],"overheads":[56,127],"(3-5X).":[57],"Furthermore,":[58],"since":[59],"tool":[61],"is":[62,76],"unaware":[63],"architecture,":[67],"even":[68],"after":[69],"performance":[73],"power":[75,94],"sub-optimal.":[77],"tackle":[79],"problem":[81],"we":[82],"present":[83],"MTP-Caffe":[84,120],"that":[85,119],"complements":[86],"Caffe":[87],"by":[88],"making":[89],"it":[90],"memory,":[91],"timing,":[92],"aware.":[95],"It":[96],"analyses":[97],"structure":[100],"architecture":[104],"convert":[106],"into":[109],"smaller":[110],"parts,":[111],"tailored":[112],"for":[113],"resources.":[115],"Simulation":[116],"results":[117],"reveal":[118],"not":[121],"only":[122],"eliminates":[123],"additional":[125],"but":[128],"also":[129],"provides":[130],"up":[131,136],"21%":[133],"speedup":[134],"23.5%":[138],"less":[139],"power.":[140]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2017-04-07T00:00:00"}