{"id":"https://openalex.org/W2796013597","doi":"https://doi.org/10.1145/3184407.3184423","title":"Characterizing the Microarchitectural Implications of a Convolutional Neural Network (CNN) Execution on GPUs","display_name":"Characterizing the Microarchitectural Implications of a Convolutional Neural Network (CNN) Execution on GPUs","publication_year":2018,"publication_date":"2018-03-30","ids":{"openalex":"https://openalex.org/W2796013597","doi":"https://doi.org/10.1145/3184407.3184423","mag":"2796013597"},"language":"en","primary_location":{"id":"doi:10.1145/3184407.3184423","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3184407.3184423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM/SPEC International Conference on Performance Engineering","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/A5101947049","display_name":"Shi Dong","orcid":"https://orcid.org/0000-0001-7144-7190"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shi Dong","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057421794","display_name":"Xiang Gong","orcid":"https://orcid.org/0000-0002-0170-2982"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Gong","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041025969","display_name":"Yifan Sun","orcid":"https://orcid.org/0000-0003-3532-6521"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Sun","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000058073","display_name":"Trinayan Baruah","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trinayan Baruah","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061128237","display_name":"David Kaeli","orcid":"https://orcid.org/0000-0002-5692-0151"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kaeli","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":4.7504,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.9604246,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"96","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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/speedup","display_name":"Speedup","score":0.8942803144454956},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8838493227958679},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.717908501625061},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.595055103302002},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5934056639671326},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5817756056785583},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5506876111030579},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.52815842628479},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.47311851382255554},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43563398718833923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2447095513343811}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8942803144454956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8838493227958679},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.717908501625061},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.595055103302002},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5934056639671326},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5817756056785583},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5506876111030579},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.52815842628479},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.47311851382255554},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43563398718833923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2447095513343811},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3184407.3184423","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3184407.3184423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM/SPEC International Conference on Performance Engineering","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":19,"referenced_works":["https://openalex.org/W1576278180","https://openalex.org/W1667652561","https://openalex.org/W2065562952","https://openalex.org/W2110195531","https://openalex.org/W2153190325","https://openalex.org/W2155893237","https://openalex.org/W2172654076","https://openalex.org/W2186615578","https://openalex.org/W2271840356","https://openalex.org/W2384495648","https://openalex.org/W2513383847","https://openalex.org/W2562773490","https://openalex.org/W2587914027","https://openalex.org/W2618530766","https://openalex.org/W2736230459","https://openalex.org/W2919115771","https://openalex.org/W2963674387","https://openalex.org/W2964174152","https://openalex.org/W2998200364"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W2132808802","https://openalex.org/W2107267576","https://openalex.org/W2145523143","https://openalex.org/W2055979713","https://openalex.org/W2950074507","https://openalex.org/W2257508639","https://openalex.org/W3091730480"],"abstract_inverted_index":{"GPUs":[0,89],"have":[1,25,60],"become":[2],"a":[3,37,69,76,113,120,133,161,167,187,191],"very":[4,199],"popular":[5,19],"platform":[6],"for":[7,190],"accelerating":[8],"the":[9,48,95,109,125,130,147,156],"processing":[10],"involved":[11],"in":[12,68,129,146,202],"deep":[13],"learning":[14],"applications.":[15],"One":[16],"class":[17,103],"of":[18,78,104,112,132,159,169,204,215],"variants,":[20],"Convolutional":[21],"Neural":[22],"Networks":[23],"(CNNs),":[24],"been":[26],"widely":[27],"deployed":[28],"to":[29,46,186],"run":[30,84],"on":[31,85,100,119,217],"GPUs.":[32],"In":[33,71],"many":[34],"application":[35,205,213],"settings,":[36],"GPU":[38,135],"has":[39],"sufficient":[40],"computing":[41],"power":[42],"and":[43,123,177],"memory":[44,126,136],"space":[45],"accommodate":[47],"dense":[49],"matrix":[50],"operations":[51],"performed":[52],"during":[53],"CNN":[54,81,114,148],"training.":[55],"However,":[56],"few":[57],"characterization":[58,77],"studies":[59],"considered":[61],"how":[62],"CNNs":[63],"can":[64,183],"impact":[65,96],"microarchitectural":[66,117],"structures":[67],"GPU.":[70,163],"this":[72,101],"paper,":[73],"we":[74,107,165],"perform":[75],"one":[79],"selected":[80],"workload":[82],"as":[83,173],"two":[86],"different":[87],"NVIDIA":[88],"from":[90],"distinct":[91],"microarchitecture":[92,98],"families,":[93],"highlighting":[94],"that":[97],"plays":[99],"important":[102],"workload.":[105],"First,":[106],"analyze":[108],"performance":[110],"implications":[111],"model":[115],"using":[116,160],"details":[118],"layer-by-layer":[121],"basis,":[122],"characterize":[124],"access":[127],"behavior":[128],"context":[131],"typical":[134],"hierarchy,":[137],"considering":[138,155],"hardware":[139],"resource":[140],"utilization":[141],"associated":[142],"with":[143],"each":[144],"primitive":[145],"model.":[149],"We":[150],"identify":[151],"major":[152],"bottlenecks":[153],"by":[154],"potential":[157],"limits":[158],"single":[162,192],"Additionally,":[164],"evaluate":[166],"number":[168],"optimization":[170],"approaches,":[171],"such":[172],"L1":[174,180,196],"cache":[175,181,197],"bypassing":[176,182],"kernel":[178,208],"fusion.":[179],"achieve":[184],"up":[185],"6.2%":[188],"speedup":[189,214],"layer,":[193],"but":[194],"manipulating":[195],"provides":[198,210],"limited":[200],"benefits":[201],"terms":[203],"speedup,":[206],"while":[207],"fusion":[209],"an":[211],"overall":[212],"4.0%,":[216],"average.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}