{"id":"https://openalex.org/W4312337928","doi":"https://doi.org/10.1109/iscc55528.2022.9912757","title":"MD-Roofline: A Training Performance Analysis Model for Distributed Deep Learning","display_name":"MD-Roofline: A Training Performance Analysis Model for Distributed Deep Learning","publication_year":2022,"publication_date":"2022-06-30","ids":{"openalex":"https://openalex.org/W4312337928","doi":"https://doi.org/10.1109/iscc55528.2022.9912757"},"language":"en","primary_location":{"id":"doi:10.1109/iscc55528.2022.9912757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscc55528.2022.9912757","pdf_url":null,"source":{"id":"https://openalex.org/S4363605780","display_name":"2022 IEEE Symposium on Computers and Communications (ISCC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Symposium on Computers and Communications (ISCC)","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/A5027657960","display_name":"Tianhao Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianhao Miao","raw_affiliation_strings":["Institute of Computing Technology,Chinese Academy of Sciences,China","University of Chinese Academy of Sciences, China","Chinese Academy of Sciences, Institute of Computing Technology, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology,Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Computing Technology, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110367262","display_name":"Qinghua Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210155350","display_name":"Purple Mountain Laboratories","ror":"https://ror.org/04zcbk583","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210155350"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghua Wu","raw_affiliation_strings":["Institute of Computing Technology,Chinese Academy of Sciences,China","Chinese Academy of Sciences, Institute of Computing Technology, China","Purple Mountain Laboratories, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology,Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Computing Technology, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Purple Mountain Laboratories, China","institution_ids":["https://openalex.org/I4210155350"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418133","display_name":"Ting Liu","orcid":"https://orcid.org/0000-0002-4132-5448"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Liu","raw_affiliation_strings":["Institute of Computing Technology,Chinese Academy of Sciences,China","Chinese Academy of Sciences, Institute of Computing Technology, China","University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology,Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Computing Technology, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034694396","display_name":"Penglai Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Penglai Cui","raw_affiliation_strings":["Institute of Computing Technology,Chinese Academy of Sciences,China","Chinese Academy of Sciences, Institute of Computing Technology, China","University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology,Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Computing Technology, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055202226","display_name":"Rui Ren","orcid":"https://orcid.org/0000-0002-6391-4737"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Ren","raw_affiliation_strings":["Institute of Computing Technology,Chinese Academy of Sciences,China","University of Chinese Academy of Sciences, China","Chinese Academy of Sciences, Institute of Computing Technology, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology,Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Computing Technology, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330770","display_name":"Zhenyu Li","orcid":"https://orcid.org/0000-0002-9959-1124"},"institutions":[{"id":"https://openalex.org/I4210155350","display_name":"Purple Mountain Laboratories","ror":"https://ror.org/04zcbk583","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210155350"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Li","raw_affiliation_strings":["Institute of Computing Technology,Chinese Academy of Sciences,China","Purple Mountain Laboratories, China","Chinese Academy of Sciences, Institute of Computing Technology, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology,Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Purple Mountain Laboratories, China","institution_ids":["https://openalex.org/I4210155350"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Computing Technology, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030689390","display_name":"Gaogang Xie","orcid":"https://orcid.org/0000-0003-4964-1135"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaogang Xie","raw_affiliation_strings":["Computer Network Information Center,Chinese Academy of Sciences,China","Chinese Academy of Sciences, Computer Network Information Center, China"],"affiliations":[{"raw_affiliation_string":"Computer Network Information Center,Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210108629","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Computer Network Information Center, China","institution_ids":["https://openalex.org/I4210108629","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5027657960"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.3222,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4588505,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","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"}},"topics":[{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","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/T10036","display_name":"Advanced Neural Network Applications","score":0.9983999729156494,"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":0.9889000058174133,"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/bottleneck","display_name":"Bottleneck","score":0.9338881969451904},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8130819201469421},{"id":"https://openalex.org/keywords/sophistication","display_name":"Sophistication","score":0.7047168612480164},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.552453875541687},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4649824798107147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45581287145614624},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.4372466206550598},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43054407835006714},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.41166141629219055},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.32265520095825195},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1838064193725586},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.17469707131385803},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12092611193656921}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.9338881969451904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8130819201469421},{"id":"https://openalex.org/C168725872","wikidata":"https://www.wikidata.org/wiki/Q991663","display_name":"Sophistication","level":2,"score":0.7047168612480164},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.552453875541687},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4649824798107147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45581287145614624},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.4372466206550598},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43054407835006714},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.41166141629219055},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32265520095825195},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1838064193725586},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.17469707131385803},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12092611193656921},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscc55528.2022.9912757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscc55528.2022.9912757","pdf_url":null,"source":{"id":"https://openalex.org/S4363605780","display_name":"2022 IEEE Symposium on Computers and Communications (ISCC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Symposium on Computers and Communications (ISCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1097869779","display_name":null,"funder_award_id":"62002344","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2317823609","https://openalex.org/W4241263575","https://openalex.org/W3130462184","https://openalex.org/W2595172197","https://openalex.org/W2902287117","https://openalex.org/W4318256508","https://openalex.org/W2401463593","https://openalex.org/W2349808627","https://openalex.org/W2391671934","https://openalex.org/W2097990792"],"abstract_inverted_index":{"Due":[0],"to":[1,24],"the":[2,7,29,33,45,66,76,94,99,108],"bulkiness":[3],"and":[4,21,27,39,82,102,122],"sophistication":[5],"of":[6,85,96],"Distributed":[8],"Deep":[9],"Learning":[10],"(DDL)":[11],"systems,":[12],"it":[13],"leaves":[14],"an":[15],"enormous":[16],"challenge":[17],"for":[18],"AI":[19,100],"researchers":[20,101],"operation":[22,104],"engineers":[23,105],"analyze,":[25],"diagnose":[26],"locate":[28,107],"performance":[30,37,46,50,61,88,130],"bottleneck":[31,137],"during":[32],"training":[34,60,140],"stage.":[35],"Existing":[36],"models":[38],"frameworks":[40],"gain":[41],"little":[42],"insight":[43],"on":[44],"reduction":[47],"that":[48,128],"a":[49,59,83],"straggler":[51],"induces.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"introduce":[57],"MD-Roofline,":[58,98],"analysis":[62,131,138],"model,":[63],"which":[64,111],"extends":[65],"traditional":[67],"rooftine":[68],"model":[69,74,132],"with":[70],"communication":[71,124],"dimension.":[72],"The":[73],"considers":[75],"layer-wise":[77],"attributes":[78],"at":[79,90],"application":[80],"level,":[81],"series":[84],"achievable":[86],"peak":[87],"metrics":[89],"hardware":[91],"level.":[92],"With":[93],"assistance":[95],"our":[97,129],"DDL":[103],"could":[106],"system":[109],"bottleneck,":[110],"contains":[112],"three":[113],"dimensions:":[114],"intra-GPU":[115,118],"computation":[116],"capacity,":[117],"memory":[119],"access":[120],"bandwidth":[121],"inter-GPU":[123],"bandwidth.":[125],"We":[126],"demonstrate":[127],"provides":[133],"great":[134],"insights":[135],"in":[136],"when":[139],"12":[141],"classic":[142],"CNNs.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
