{"id":"https://openalex.org/W2904180680","doi":"https://doi.org/10.1109/iiswc.2018.8573521","title":"Profiling DNN Workloads on a Volta-based DGX-1 System","display_name":"Profiling DNN Workloads on a Volta-based DGX-1 System","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2904180680","doi":"https://doi.org/10.1109/iiswc.2018.8573521","mag":"2904180680"},"language":"en","primary_location":{"id":"doi:10.1109/iiswc.2018.8573521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iiswc.2018.8573521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Symposium on Workload Characterization (IISWC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5072286447","display_name":"Saiful A. Mojumder","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saiful A. Mojumder","raw_affiliation_strings":["ECE Department, Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, Boston University","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080221369","display_name":"Marcia S. Louis","orcid":"https://orcid.org/0000-0001-7749-5396"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marcia S Louis","raw_affiliation_strings":["ECE Department, Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, Boston University","institution_ids":["https://openalex.org/I111088046"]}]},{"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":["ECE Department, Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, Northeastern University","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021996030","display_name":"Amir Kavyan Ziabari","orcid":"https://orcid.org/0000-0002-5963-2374"},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Amir Kavyan Ziabari","raw_affiliation_strings":["Advanced Micro Devices"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices","institution_ids":["https://openalex.org/I1311921367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007832959","display_name":"Jos\u00e9 Luis Abell\u00e1n","orcid":"https://orcid.org/0000-0003-3550-720X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jose L. Abellan","raw_affiliation_strings":["CS Department, UCAM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CS Department, UCAM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100698124","display_name":"John Kim","orcid":"https://orcid.org/0000-0003-3958-3891"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"John Kim","raw_affiliation_strings":["School of EE, KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EE, KAIST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]},{"author_position":"middle","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":["ECE Department, Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, Northeastern University","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089428659","display_name":"Ajay Joshi","orcid":"https://orcid.org/0000-0002-3256-9942"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ajay Joshi","raw_affiliation_strings":["ECE Department, Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, Boston University","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"122","last_page":"133"},"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":0.9994999766349792,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8896310329437256},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6658055782318115},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5891906023025513},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4966915249824524},{"id":"https://openalex.org/keywords/residual-neural-network","display_name":"Residual neural network","score":0.4854746162891388},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4792759120464325},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.45441895723342896},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41454166173934937},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3801855146884918},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35958176851272583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35689154267311096},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10764369368553162}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8896310329437256},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6658055782318115},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5891906023025513},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4966915249824524},{"id":"https://openalex.org/C2944601119","wikidata":"https://www.wikidata.org/wiki/Q43744058","display_name":"Residual neural network","level":3,"score":0.4854746162891388},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4792759120464325},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.45441895723342896},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41454166173934937},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3801855146884918},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35958176851272583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35689154267311096},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10764369368553162},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iiswc.2018.8573521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iiswc.2018.8573521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Symposium on Workload Characterization (IISWC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W619799124","https://openalex.org/W753012316","https://openalex.org/W1533861849","https://openalex.org/W1547840952","https://openalex.org/W1598866093","https://openalex.org/W1745334888","https://openalex.org/W1867117070","https://openalex.org/W1969067576","https://openalex.org/W1984020445","https://openalex.org/W2057332538","https://openalex.org/W2060393849","https://openalex.org/W2076063813","https://openalex.org/W2083842231","https://openalex.org/W2087402357","https://openalex.org/W2117499659","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2168231600","https://openalex.org/W2181607856","https://openalex.org/W2186615578","https://openalex.org/W2204075824","https://openalex.org/W2271840356","https://openalex.org/W2332506150","https://openalex.org/W2339765813","https://openalex.org/W2488028880","https://openalex.org/W2513289469","https://openalex.org/W2541249978","https://openalex.org/W2622263826","https://openalex.org/W2626580042","https://openalex.org/W2730150110","https://openalex.org/W2736230459","https://openalex.org/W2741888411","https://openalex.org/W2759465730","https://openalex.org/W2766164908","https://openalex.org/W2777078856","https://openalex.org/W2790501674","https://openalex.org/W2796013597","https://openalex.org/W2911002035","https://openalex.org/W2963674387","https://openalex.org/W2964324519","https://openalex.org/W2964330541","https://openalex.org/W4285719527","https://openalex.org/W4293318097","https://openalex.org/W4297827580","https://openalex.org/W4307068509","https://openalex.org/W6622239757","https://openalex.org/W6631943919","https://openalex.org/W6632552335","https://openalex.org/W6635810480","https://openalex.org/W6665801690","https://openalex.org/W6677756232","https://openalex.org/W6684191040","https://openalex.org/W6684859321","https://openalex.org/W6686045668","https://openalex.org/W6686509673","https://openalex.org/W6687619766","https://openalex.org/W6694517276","https://openalex.org/W6702429100","https://openalex.org/W6725826102","https://openalex.org/W6739554518","https://openalex.org/W6739622702","https://openalex.org/W6744711479","https://openalex.org/W6745410505","https://openalex.org/W6746239207","https://openalex.org/W6747195836","https://openalex.org/W6748636330","https://openalex.org/W6758292540","https://openalex.org/W6765060121","https://openalex.org/W6922689029"],"related_works":["https://openalex.org/W2599472179","https://openalex.org/W3196952692","https://openalex.org/W4323057981","https://openalex.org/W2161444195","https://openalex.org/W4308408209","https://openalex.org/W2589019771","https://openalex.org/W4390187226","https://openalex.org/W2799384463","https://openalex.org/W4221145391","https://openalex.org/W3159619856"],"abstract_inverted_index":{"High":[0],"performance":[1,127],"multi-GPU":[2,32,212],"systems":[3,33],"are":[4],"widely":[5],"used":[6],"to":[7,83,116,192,206],"accelerate":[8,227],"training":[9,24,28,140,157,181,201,229],"of":[10,22,29,69,91,128,147,158,179,199],"deep":[11],"neural":[12],"networks":[13],"(DNNs)":[14],"by":[15,109,113],"exploiting":[16],"the":[17,23,27,63,81,89,94,126,156,177,180,184,189,196,200,208,211,228],"inherently":[18],"massive":[19],"parallel":[20],"nature":[21],"process.":[25],"Typically,":[26],"DNNs":[30,141,161],"in":[31,38,93,210,231],"leverages":[34],"a":[35,40,143],"data-parallel":[36],"model":[37,225],"which":[39,75],"DNN":[41,224],"is":[42,67],"replicated":[43],"on":[44,142],"every":[45],"GPU,":[46],"and":[47,104,111,124,134,154,166,172,188,218,223],"each":[48],"GPU":[49],"performs":[50],"Forward":[51],"Propagation":[52,55],"(FP),":[53],"Backward":[54],"(BP)":[56],"and,":[57],"Weight":[58],"Update":[59],"(WU).":[60],"We":[61,152,175],"analyze":[62,155],"WU":[64,190],"stage":[65,187,191],"that":[66],"composed":[68],"collective":[70],"communication":[71,79,137],"(e.g.,":[72],"allReduce,":[73],"broadcast),":[74],"demands":[76],"very":[77],"efficient":[78],"among":[80],"GPUs":[82,92],"avoid":[84],"diminishing":[85],"returns":[86],"when":[87],"scaling":[88],"number":[90],"system.":[95],"To":[96],"overcome":[97],"this":[98,120],"issue,":[99],"different":[100],"data":[101,131],"transfer":[102,132],"mechanisms":[103],"libraries":[105],"have":[106],"been":[107],"introduced":[108],"NVIDIA,":[110],"adopted":[112],"high-level":[114],"frameworks":[115],"train":[117],"DNNs.":[118,232],"In":[119],"work,":[121],"we":[122],"evaluate":[123],"compare":[125],"peer-to-peer":[129],"(P2P)":[130],"method":[133,138],"NCCL":[135],"library-based":[136],"for":[139],"DGX-1":[144],"system":[145,213],"consisting":[146],"8":[148,173],"NVIDIA":[149],"Volta-based":[150],"GPUs.":[151,174],"profile":[153],"five":[159],"popular":[160],"(GoogLeNet,":[162],"AlexNet,":[163],"Inception-v3,":[164],"ResNet":[165],"LeNet)":[167],"using":[168],"1,":[169],"2,":[170],"4":[171],"show":[176],"breakdown":[178],"time":[182],"across":[183],"FP+":[185],"BP":[186],"provide":[193],"insights":[194],"about":[195],"limiting":[197],"factors":[198],"algorithm":[202],"as":[203,205],"well":[204],"identify":[207],"bottlenecks":[209],"architecture.":[214],"Our":[215],"detailed":[216],"profiling":[217],"analysis":[219],"can":[220],"help":[221],"programmers":[222],"designers":[226],"process":[230]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}