{"id":"https://openalex.org/W3212496770","doi":"https://doi.org/10.1145/3493229.3493305","title":"Efficient Application of Tensor Core Units for Convolving Images","display_name":"Efficient Application of Tensor Core Units for Convolving Images","publication_year":2021,"publication_date":"2021-11-01","ids":{"openalex":"https://openalex.org/W3212496770","doi":"https://doi.org/10.1145/3493229.3493305","mag":"3212496770"},"language":"en","primary_location":{"id":"doi:10.1145/3493229.3493305","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3493229.3493305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Workshop on Software and Compilers for Embedded Systems","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/A5016048097","display_name":"Stefan Groth","orcid":"https://orcid.org/0000-0002-9043-0746"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Groth","raw_affiliation_strings":["Hardware/Software Co-Design, Department of Computer Science Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU) Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hardware/Software Co-Design, Department of Computer Science Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU) Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076672029","display_name":"J\u00fcrgen Teich","orcid":"https://orcid.org/0000-0001-6285-5862"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00fcrgen Teich","raw_affiliation_strings":["Hardware/Software Co-Design, Department of Computer Science Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU) Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hardware/Software Co-Design, Department of Computer Science Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU) Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072039340","display_name":"Frank Hannig","orcid":"https://orcid.org/0000-0003-3663-6484"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frank Hannig","raw_affiliation_strings":["Hardware/Software Co-Design, Department of Computer Science Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU) Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hardware/Software Co-Design, Department of Computer Science Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU) Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5822,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.69321463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9980000257492065,"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":0.9980000257492065,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9954000115394592,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9918000102043152,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7825897932052612},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6137532591819763},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5459517240524292},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.536514937877655},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.4970548450946808},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49398308992385864},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4806000888347626},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.45466700196266174},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.45457738637924194},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.4261527359485626},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.39898237586021423},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.32711872458457947},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32276737689971924},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.23145627975463867},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11430776119232178},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.09162652492523193}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7825897932052612},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6137532591819763},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5459517240524292},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.536514937877655},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.4970548450946808},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49398308992385864},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4806000888347626},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.45466700196266174},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.45457738637924194},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4261527359485626},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39898237586021423},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32711872458457947},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32276737689971924},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.23145627975463867},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11430776119232178},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.09162652492523193},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3493229.3493305","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3493229.3493305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Workshop on Software and Compilers for Embedded Systems","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":17,"referenced_works":["https://openalex.org/W1983389993","https://openalex.org/W2075745057","https://openalex.org/W2111308925","https://openalex.org/W2155942864","https://openalex.org/W2194775991","https://openalex.org/W2623389408","https://openalex.org/W2946289095","https://openalex.org/W3028780355","https://openalex.org/W3044913359","https://openalex.org/W3091170309","https://openalex.org/W3132558499","https://openalex.org/W3149570512","https://openalex.org/W3174843332","https://openalex.org/W4234143480","https://openalex.org/W4251147723","https://openalex.org/W4302296459","https://openalex.org/W6637151318"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4321487865","https://openalex.org/W4313906399","https://openalex.org/W4239306820","https://openalex.org/W4391266461","https://openalex.org/W2590798552","https://openalex.org/W2811106690","https://openalex.org/W2947043951","https://openalex.org/W4399188509","https://openalex.org/W4312417841"],"abstract_inverted_index":{"Tensor":[0],"Core":[1],"Units":[2],"(TCUs)":[3],"are":[4,33,65],"a":[5,16,58,73,137],"domain-specific":[6],"architecture":[7],"capable":[8],"of":[9,39,49,76,87,91,116,124],"executing":[10],"small":[11,74],"Matrix":[12],"Multiply-Accumulates":[13],"(MMAs)":[14],"in":[15,67],"single":[17,59],"clock":[18],"cycle,":[19],"showing":[20],"significant":[21],"performance":[22,123],"improvements":[23],"over":[24],"other":[25,68],"optimized":[26],"implementations.":[27],"When":[28],"Convolutional":[29],"Neural":[30],"Networks":[31],"(CNNs)":[32],"accelerated":[34],"using":[35,57,136],"TCUs,":[36],"the":[37,40,85,93,122],"layout":[38],"input":[41],"image":[42,56,139],"is":[43],"transformed":[44],"to":[45,51,54,104,133],"allow":[46],"large":[47,60],"amounts":[48],"filters":[50],"be":[52],"applied":[53],"an":[55,99,109],"matrix-matrix":[61],"multiplication.":[62],"However,":[63],"there":[64],"applications":[66],"domains":[69],"that":[70,101],"only":[71],"require":[72],"number":[75],"filters.":[77],"To":[78],"accommodate":[79],"such":[80],"applications,":[81],"we":[82,97,112,120],"first":[83],"show":[84],"inappropriateness":[86],"this":[88,117],"standard":[89],"technique":[90],"transforming":[92],"data":[94],"layout.":[95],"Subsequently,":[96],"propose":[98],"approach":[100,126],"uses":[102],"TCUs":[103],"convolve":[105],"one":[106],"filter":[107],"with":[108],"image.":[110],"Further,":[111],"introduce":[113],"several":[114],"optimizations":[115,129],"method.":[118],"Finally,":[119],"evaluate":[121],"our":[125],"and":[127],"its":[128],"by":[130],"comparing":[131],"it":[132],"code":[134],"generated":[135],"state-of-the-art":[138],"processing":[140],"language.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}