{"id":"https://openalex.org/W3015963989","doi":"https://doi.org/10.1109/pmbs49563.2019.00017","title":"Performance Analysis of Deep Learning Workloads on Leading-edge Systems","display_name":"Performance Analysis of Deep Learning Workloads on Leading-edge Systems","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3015963989","doi":"https://doi.org/10.1109/pmbs49563.2019.00017","mag":"3015963989"},"language":"en","primary_location":{"id":"doi:10.1109/pmbs49563.2019.00017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pmbs49563.2019.00017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1571428","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013719267","display_name":"Yihui Ren","orcid":"https://orcid.org/0000-0002-5750-6964"},"institutions":[{"id":"https://openalex.org/I200870766","display_name":"Brookhaven National Laboratory","ror":"https://ror.org/02ex6cf31","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I200870766","https://openalex.org/I39565521","https://openalex.org/I4210142672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yihui Ren","raw_affiliation_strings":["Computational Science Initiative, Brookhaven National Laboratory, Upton, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Science Initiative, Brookhaven National Laboratory, Upton, NY, USA","institution_ids":["https://openalex.org/I200870766"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048176207","display_name":"Shinjae Yoo","orcid":"https://orcid.org/0000-0003-4378-6448"},"institutions":[{"id":"https://openalex.org/I200870766","display_name":"Brookhaven National Laboratory","ror":"https://ror.org/02ex6cf31","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I200870766","https://openalex.org/I39565521","https://openalex.org/I4210142672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinjae Yoo","raw_affiliation_strings":["Computational Science Initiative, Brookhaven National Laboratory, Upton, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Science Initiative, Brookhaven National Laboratory, Upton, NY, USA","institution_ids":["https://openalex.org/I200870766"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072223736","display_name":"Adolfy Hoisie","orcid":"https://orcid.org/0000-0001-7812-2946"},"institutions":[{"id":"https://openalex.org/I200870766","display_name":"Brookhaven National Laboratory","ror":"https://ror.org/02ex6cf31","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I200870766","https://openalex.org/I39565521","https://openalex.org/I4210142672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adolfy Hoisie","raw_affiliation_strings":["Computational Science Initiative, Brookhaven National Laboratory, Upton, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Science Initiative, Brookhaven National Laboratory, Upton, NY, USA","institution_ids":["https://openalex.org/I200870766"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5253,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.86927425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"103","last_page":"113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9980000257492065,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.993399977684021,"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":0.8366252183914185},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.815951943397522},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7571781873703003},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7081581354141235},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5415783524513245},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.485099196434021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4832349717617035},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4817890524864197},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.42778605222702026},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.41692298650741577},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.4140753746032715},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37612754106521606},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3733140826225281},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3722658157348633},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3717442750930786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8366252183914185},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.815951943397522},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7571781873703003},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7081581354141235},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5415783524513245},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.485099196434021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4832349717617035},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4817890524864197},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.42778605222702026},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.41692298650741577},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.4140753746032715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37612754106521606},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3733140826225281},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3722658157348633},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3717442750930786},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"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/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/pmbs49563.2019.00017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pmbs49563.2019.00017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1571428","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1571428","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1571428","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1571428","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1635512741","https://openalex.org/W1667652561","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2120432001","https://openalex.org/W2122002474","https://openalex.org/W2141125852","https://openalex.org/W2142416747","https://openalex.org/W2143612262","https://openalex.org/W2153579005","https://openalex.org/W2163605009","https://openalex.org/W2170973209","https://openalex.org/W2194775991","https://openalex.org/W2340076492","https://openalex.org/W2515080096","https://openalex.org/W2763421725","https://openalex.org/W2777078856","https://openalex.org/W2896457183","https://openalex.org/W2899771611","https://openalex.org/W2903901007","https://openalex.org/W2952729433","https://openalex.org/W2963112338","https://openalex.org/W2963159690","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963748441","https://openalex.org/W3105753409","https://openalex.org/W4205130185","https://openalex.org/W4294170691","https://openalex.org/W4302296459","https://openalex.org/W4385245566","https://openalex.org/W6637151318","https://openalex.org/W6682691769","https://openalex.org/W6684191040","https://openalex.org/W6685158001","https://openalex.org/W6739901393","https://openalex.org/W6745245109","https://openalex.org/W6755207826","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W3154796165","https://openalex.org/W4322761281","https://openalex.org/W4238233472","https://openalex.org/W4313463218","https://openalex.org/W4312996489","https://openalex.org/W3111395152","https://openalex.org/W4313526662","https://openalex.org/W3106131444","https://openalex.org/W3216099748","https://openalex.org/W4205963435"],"abstract_inverted_index":{"This":[0],"work":[1],"examines":[2],"the":[3,14,42,52,55,70,87,93,104,114],"performance":[4],"of":[5,44,54,65,69,100,103],"leading-edge":[6],"systems":[7,88],"designed":[8],"for":[9,86],"machine":[10],"learning":[11,39,78,106],"computing,":[12],"including":[13],"NVIDIA":[15],"DGX-2,":[16],"Amazon":[17],"Web":[18],"Services":[19],"(AWS)":[20],"P3,":[21],"IBM":[22],"Power":[23],"System":[24],"Accelerated":[25],"Compute":[26],"Server":[27],"AC922,":[28],"and":[29,47,73,75,91,108],"a":[30,63],"consumer-grade":[31],"Exxact":[32],"TensorEX":[33],"TS4":[34],"GPU":[35],"server.":[36],"Representative":[37],"deep":[38,77,105],"workloads":[40],"from":[41],"fields":[43],"computer":[45],"vision":[46],"natural":[48],"language":[49],"processing":[50],"are":[51,80,96],"focus":[53],"analysis.":[56,115],"Performance":[57,68],"analysis":[58],"is":[59,111],"performed":[60],"along":[61],"with":[62],"number":[64],"important":[66],"dimensions.":[67],"communication":[71],"interconnects":[72],"large":[74],"high-throughput":[76],"models":[79,85,107],"considered.":[81],"Different":[82],"potential":[83],"use":[84],"as":[89],"standalone":[90],"in":[92,113],"cloud":[94],"also":[95],"examined.":[97],"The":[98],"effect":[99],"various":[101],"optimization":[102],"system":[109],"configurations":[110],"included":[112]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}