{"id":"https://openalex.org/W2770297025","doi":"https://doi.org/10.1109/lca.2017.2773055","title":"Partitioning Compute Units in CNN Acceleration for Statistical Memory Traffic Shaping","display_name":"Partitioning Compute Units in CNN Acceleration for Statistical Memory Traffic Shaping","publication_year":2017,"publication_date":"2017-11-14","ids":{"openalex":"https://openalex.org/W2770297025","doi":"https://doi.org/10.1109/lca.2017.2773055","mag":"2770297025"},"language":"en","primary_location":{"id":"doi:10.1109/lca.2017.2773055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2017.2773055","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"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 Computer Architecture Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1806.06541","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102809868","display_name":"Dae-Jin Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Daejin Jung","raw_affiliation_strings":["Department of Transdisciplinary Studies, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Transdisciplinary Studies, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025001772","display_name":"Sunjung Lee","orcid":"https://orcid.org/0000-0002-5177-0916"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sunjung Lee","raw_affiliation_strings":["Department of Transdisciplinary Studies, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Transdisciplinary Studies, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056032525","display_name":"Wonjong Rhee","orcid":"https://orcid.org/0000-0002-2590-8774"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonjong Rhee","raw_affiliation_strings":["Department of Transdisciplinary Studies, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Transdisciplinary Studies, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078262826","display_name":"Jung Ho Ahn","orcid":"https://orcid.org/0000-0003-1733-1394"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung Ho Ahn","raw_affiliation_strings":["Department of Transdisciplinary Studies, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Transdisciplinary Studies, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102809868"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.6474,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79325714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"17","issue":"1","first_page":"72","last_page":"75"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9969000220298767,"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/bottleneck","display_name":"Bottleneck","score":0.8268628120422363},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8228709697723389},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6538978219032288},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6125328540802002},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5710322856903076},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5412267446517944},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5137468576431274},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5049083828926086},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4776157736778259},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.438248872756958},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.43527764081954956},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4289567470550537},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.360352098941803},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3479152321815491},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.1883159577846527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16069436073303223},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11628201603889465}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8268628120422363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8228709697723389},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6538978219032288},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6125328540802002},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5710322856903076},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5412267446517944},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5137468576431274},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5049083828926086},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4776157736778259},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.438248872756958},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.43527764081954956},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4289567470550537},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.360352098941803},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3479152321815491},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.1883159577846527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16069436073303223},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11628201603889465},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lca.2017.2773055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2017.2773055","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"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 Computer Architecture Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1806.06541","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.06541","pdf_url":"https://arxiv.org/pdf/1806.06541","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:1806.06541","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.06541","pdf_url":"https://arxiv.org/pdf/1806.06541","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":[{"id":"https://openalex.org/G2385274007","display_name":null,"funder_award_id":"NRF-2017R1E1A1A03070560","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G5595920659","display_name":null,"funder_award_id":"NRF-2017R1A2B2005416","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1985431949","https://openalex.org/W2097117768","https://openalex.org/W2155893237","https://openalex.org/W2194775991","https://openalex.org/W2274287116","https://openalex.org/W2340076492","https://openalex.org/W2433451779","https://openalex.org/W2542189141","https://openalex.org/W2603836393","https://openalex.org/W2606722458","https://openalex.org/W2612387305","https://openalex.org/W2950094539","https://openalex.org/W2953212265","https://openalex.org/W2964350391","https://openalex.org/W4239385313","https://openalex.org/W6637373629","https://openalex.org/W6694260854","https://openalex.org/W6718152450"],"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/W2891987081"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"have":[4,88,110],"become":[5,276],"the":[6,14,29,39,48,68,91,136,151,155,198,203,208,225,229,254,268,274,280,291,302],"default":[7],"choice":[8],"for":[9,35,128,140],"processing":[10],"visual":[11],"information,":[12],"and":[13,55,57,117,157,195,258,285,301,313,326],"design":[15],"complexity":[16],"of":[17,32,44,59,78,126,154,183,223,237,273,282,288,304,336],"CNNs":[18],"has":[19,73],"been":[20,74],"steadily":[21],"increasing":[22],"to":[23,63,150,188,214,244,333],"improve":[24,64],"accuracy.":[25],"To":[26],"cope":[27],"with":[28,113],"massive":[30],"amount":[31],"computation":[33,115,152,189],"needed":[34],"such":[36],"complex":[37],"CNNs,":[38],"latest":[40],"solutions":[41],"utilize":[42],"blocking":[43],"an":[45,129],"image":[46],"over":[47,123,299],"available":[49],"dimensions":[50],"(e.g.,":[51],"horizontal,":[52],"vertical,":[53],"channel,":[54],"kernel)":[56],"batching":[58,119],"multiple":[60],"input":[61,238],"images":[62],"data":[65,82,131,137,216,239,246,310],"reuse":[66,247,311],"in":[67,104,161,185,197,240],"memory":[69,92,162,186,269,293,314,323],"hierarchy.":[70],"While":[71],"there":[72,178],"a":[75,85,141,180,221,235,241,307,340],"large":[76],"collection":[77],"works":[79],"on":[80,90,192,339],"maximizing":[81],"reuse,":[83],"only":[84],"few":[86],"studies":[87],"focused":[89],"bottleneck":[93,100],"problem":[94],"caused":[95],"by":[96,202],"limited":[97],"bandwidth.":[98],"Bandwidth":[99],"can":[101,143,164,331],"easily":[102],"occur":[103],"CNN":[105,108,127,193,262],"acceleration":[106],"as":[107,118],"layers":[109,194,263],"different":[111,249,261],"sizes":[112,272],"varying":[114],"needs":[116],"is":[120],"typically":[121,259],"performed":[122],"each":[124,232],"layer":[125,142,199],"ideal":[130],"reuse.":[132,217],"In":[133,171],"this":[134,172,320],"case,":[135],"transfer":[138],"demand":[139],"be":[144,165,297],"relatively":[145],"low":[146],"or":[147],"high":[148,181],"compared":[149],"requirement":[153],"layer,":[156],"therefore":[158],"temporal":[159],"fluctuations":[160],"access":[163,187,270,294],"induced":[166],"eventually":[167],"causing":[168],"bandwidth":[169,315],"problems.":[170],"paper,":[173],"we":[174,219,327],"first":[175],"show":[176,328],"that":[177,329],"exists":[179],"degree":[182,303],"fluctuation":[184],"ratio":[190],"depending":[191],"functions":[196],"being":[200],"processed":[201],"compute":[204,209,226,283],"units":[205,210,227,284],"(cores),":[206],"where":[207,228],"are":[211],"tightly":[212],"synchronized":[213],"maximize":[215,245],"Then":[218],"propose":[220],"strategy":[222],"partitioning":[224,281,305],"cores":[230],"within":[231],"partition":[233],"process":[234,260],"batch":[236],"synchronous":[242],"manner":[243],"but":[248],"partitions":[250,255,275],"run":[251],"asynchronously.":[252],"Because":[253],"stay":[256],"asynchronous":[257,286],"at":[264],"any":[265],"given":[266],"moment,":[267],"traffic":[271,295,324],"statistically":[277],"shuffled.":[278],"Thus,":[279],"use":[287],"them":[289],"make":[290],"total":[292],"size":[296],"smoothened":[298],"time,":[300],"determines":[306],"tradeoff":[308],"between":[309],"efficiency":[312],"utilization":[316],"efficiency.":[317],"We":[318],"call":[319],"smoothing":[321],"statistical":[322],"shaping,":[325],"it":[330],"lead":[332],"8.0":[334],"percent":[335],"performance":[337],"gain":[338],"commercial":[341],"64-core":[342],"processor":[343],"when":[344],"running":[345],"ResNet-50.":[346]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2017-12-04T00:00:00"}