{"id":"https://openalex.org/W4399254180","doi":"https://doi.org/10.1145/3652963.3655087","title":"Thorough Characterization and Analysis of Large Transformer Model Training At-Scale","display_name":"Thorough Characterization and Analysis of Large Transformer Model Training At-Scale","publication_year":2024,"publication_date":"2024-06-01","ids":{"openalex":"https://openalex.org/W4399254180","doi":"https://doi.org/10.1145/3652963.3655087"},"language":"en","primary_location":{"id":"doi:10.1145/3652963.3655087","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3652963.3655087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Abstracts of the 2024 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems","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/A5035702201","display_name":"S. H. Cheng","orcid":"https://orcid.org/0000-0001-9954-7986"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Scott Cheng","raw_affiliation_strings":["The Pennsylvania State University, State College, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, State College, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002465188","display_name":"Jun-Liang Lin","orcid":"https://orcid.org/0000-0001-5105-7574"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun-Liang Lin","raw_affiliation_strings":["The Pennsylvania State University, State College, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, State College, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014448094","display_name":"Murali Emani","orcid":"https://orcid.org/0000-0002-6279-0007"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murali Emani","raw_affiliation_strings":["Argonne National Laboratory, Lemont, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039783562","display_name":"Siddhisanket Raskar","orcid":"https://orcid.org/0000-0002-4832-0834"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhisanket Raskar","raw_affiliation_strings":["Argonne National Laboratory, Lemont, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028293798","display_name":"Xiao-Yong Jin","orcid":"https://orcid.org/0000-0002-9981-0876"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Foreman","raw_affiliation_strings":["Argonne National Laboratory, Lemont, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037768390","display_name":"Zhen Xie","orcid":"https://orcid.org/0000-0003-3516-2192"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhen Xie","raw_affiliation_strings":["Binghamton University, Vestal, USA"],"affiliations":[{"raw_affiliation_string":"Binghamton University, Vestal, USA","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075500139","display_name":"Venkatram Vishwanath","orcid":"https://orcid.org/0000-0001-7248-6116"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkatram Vishwanath","raw_affiliation_strings":["Argonne National Laboratory, Lemont, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007116603","display_name":"Mahmut Kandemir","orcid":"https://orcid.org/0000-0002-9940-9951"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahmut T. Kandemir","raw_affiliation_strings":["The Pennsylvania State University, State College, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, State College, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5035702201"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05444103,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14276","display_name":"Power Systems and Technologies","score":0.951200008392334,"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/T14276","display_name":"Power Systems and Technologies","score":0.951200008392334,"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/T11372","display_name":"Hydraulic and Pneumatic Systems","score":0.9466999769210815,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T14474","display_name":"Industrial Technology and Control Systems","score":0.9092000126838684,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.6515057682991028},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5293772220611572},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16415488719940186},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09553560614585876},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05341199040412903}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6515057682991028},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5293772220611572},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16415488719940186},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09553560614585876},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05341199040412903}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652963.3655087","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3652963.3655087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Abstracts of the 2024 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W3204998121","https://openalex.org/W3205803342"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Large":[0],"transformer":[1,20,63],"models":[2,64],"have":[3],"recently":[4],"achieved":[5],"great":[6],"success":[7],"across":[8],"various":[9,57],"domains.":[10],"With":[11],"a":[12,18,47,73,81,105],"growing":[13],"number":[14],"of":[15,36,49,62,80],"model":[16,21,26,31,38,50,89],"parameters,":[17],"large":[19],"training":[22,39,94],"today":[23],"typically":[24],"involves":[25],"sharding,":[27],"data":[28,87],"parallelism,":[29],"and":[30,52,88],"parallelism.":[32],"Thus,":[33],"the":[34,43,78],"throughput":[35],"large-scale":[37],"depends":[40],"heavily":[41],"on":[42,65,96],"network":[44],"bandwidth":[45],"since":[46],"combination":[48],"sharding":[51],"multiple":[53],"parallelism":[54,90],"strategies":[55],"incurs":[56],"costs.":[58],"However,":[59],"prior":[60],"characterizations":[61],"high-bandwidth":[66],"DGX":[67],"machines":[68],"that":[69],"use":[70],"TFLOPS":[71],"as":[72],"metric":[74],"may":[75],"not":[76],"reflect":[77],"performance":[79],"system":[82,98],"with":[83],"lower":[84],"bandwidth.":[85],"Furthermore,":[86],"reveal":[91],"significantly":[92],"distinct":[93],"profiles":[95],"different":[97],"bandwidths":[99],"at":[100],"scale":[101],"and,":[102],"thus,":[103],"need":[104],"thorough":[106],"study.":[107]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
