{"id":"https://openalex.org/W4224226923","doi":"https://doi.org/10.1145/3539781.3539784","title":"Communication bounds for convolutional neural networks","display_name":"Communication bounds for convolutional neural networks","publication_year":2022,"publication_date":"2022-06-27","ids":{"openalex":"https://openalex.org/W4224226923","doi":"https://doi.org/10.1145/3539781.3539784"},"language":"en","primary_location":{"id":"doi:10.1145/3539781.3539784","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539781.3539784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2204.08279","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101995299","display_name":"Anthony Chen","orcid":"https://orcid.org/0000-0003-0760-8329"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony Chen","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076825233","display_name":"James Demmel","orcid":"https://orcid.org/0000-0003-1145-3745"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Demmel","raw_affiliation_strings":["University of California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055472408","display_name":"Grace Dinh","orcid":"https://orcid.org/0000-0001-9626-098X"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grace Dinh","raw_affiliation_strings":["University of California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042917767","display_name":"Mason Haberle","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mason Haberle","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055605632","display_name":"Olga Holtz","orcid":"https://orcid.org/0000-0003-3420-3423"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olga Holtz","raw_affiliation_strings":["University of California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2031,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.45593891,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8802992105484009},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6699008941650391},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.613154411315918},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.5934884548187256},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.519874095916748},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46131157875061035},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4589252769947052},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.44167348742485046},{"id":"https://openalex.org/keywords/vendor","display_name":"Vendor","score":0.4279125928878784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40339839458465576},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3589010238647461},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16262105107307434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8802992105484009},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6699008941650391},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.613154411315918},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5934884548187256},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.519874095916748},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46131157875061035},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4589252769947052},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.44167348742485046},{"id":"https://openalex.org/C2777338717","wikidata":"https://www.wikidata.org/wiki/Q1762621","display_name":"Vendor","level":2,"score":0.4279125928878784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40339839458465576},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3589010238647461},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16262105107307434},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3539781.3539784","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539781.3539784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2204.08279","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.08279","pdf_url":"https://arxiv.org/pdf/2204.08279","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2204.08279","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.08279","pdf_url":"https://arxiv.org/pdf/2204.08279","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W643803686","https://openalex.org/W1950718439","https://openalex.org/W2041578787","https://openalex.org/W2099611016","https://openalex.org/W2168748809","https://openalex.org/W2194775991","https://openalex.org/W2554941931","https://openalex.org/W2735702203","https://openalex.org/W2884267664","https://openalex.org/W2907172645","https://openalex.org/W2969599742","https://openalex.org/W2984305089","https://openalex.org/W3010757996","https://openalex.org/W3093772369","https://openalex.org/W3192336523","https://openalex.org/W3213528054","https://openalex.org/W4288083528","https://openalex.org/W4293872502"],"related_works":["https://openalex.org/W2478661203","https://openalex.org/W2004830053","https://openalex.org/W3008115697","https://openalex.org/W2349167760","https://openalex.org/W2145175947","https://openalex.org/W3124949371","https://openalex.org/W4287864641","https://openalex.org/W2120643196","https://openalex.org/W2035037799","https://openalex.org/W1971123707"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"are":[4],"important":[5],"in":[6,70],"a":[7,29,36,95,109],"wide":[8],"variety":[9],"of":[10,24,28,45],"machine":[11,96],"learning":[12,97],"tasks":[13],"and":[14,73,106],"applications,":[15],"so":[16,47],"optimizing":[17,53],"their":[18],"performance":[19,91],"is":[20,38,50],"essential.":[21],"Moving":[22],"words":[23],"data":[25,64],"between":[26,33,104],"levels":[27],"memory":[30,76],"hierarchy":[31],"or":[32],"processors":[34],"on":[35,63],"network":[37],"much":[39],"more":[40],"expensive":[41],"than":[42],"the":[43],"cost":[44],"arithmetic,":[46],"minimizing":[48],"communication":[49],"critical":[51],"to":[52],"performance.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58],"present":[59],"new":[60],"lower":[61],"bounds":[62],"movement":[65],"for":[66],"mixed":[67],"precision":[68],"convolutions":[69],"both":[71],"single-processor":[72],"parallel":[74],"distributed":[75],"models,":[77],"as":[78,80,87],"well":[79],"algorithms":[81],"that":[82],"outperform":[83],"current":[84],"implementations":[85],"such":[86],"Im2Col.":[88],"We":[89],"obtain":[90],"figures":[92],"using":[93],"GEMMINI,":[94],"accelerator,":[98],"where":[99],"our":[100],"tiling":[101],"provides":[102],"improvements":[103],"13%":[105],"150%":[107],"over":[108],"vendor":[110],"supplied":[111],"algorithm.":[112]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}