{"id":"https://openalex.org/W2963382388","doi":"https://doi.org/10.1145/3337821.3337905","title":"Performance, Energy, and Scalability Analysis and Improvement of Parallel Cancer Deep Learning CANDLE Benchmarks","display_name":"Performance, Energy, and Scalability Analysis and Improvement of Parallel Cancer Deep Learning CANDLE Benchmarks","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2963382388","doi":"https://doi.org/10.1145/3337821.3337905","mag":"2963382388"},"language":"en","primary_location":{"id":"doi:10.1145/3337821.3337905","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3337821.3337905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Conference on Parallel Processing","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/A5072646801","display_name":"Xingfu Wu","orcid":"https://orcid.org/0000-0001-8150-5171"},"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"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xingfu Wu","raw_affiliation_strings":["Argonne National Laboratory, University of Chicago"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, University of Chicago","institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028916710","display_name":"Valerie Taylor","orcid":"https://orcid.org/0000-0001-6061-0191"},"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"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Valerie Taylor","raw_affiliation_strings":["Argonne National Laboratory, University of Chicago"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, University of Chicago","institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020776475","display_name":"Justin M. Wozniak","orcid":"https://orcid.org/0000-0002-2441-2048"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]},{"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":"Justin M. Wozniak","raw_affiliation_strings":["Argonne National Laboratory, University of Chicago"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, University of Chicago","institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053682943","display_name":"Rick Stevens","orcid":"https://orcid.org/0000-0002-4268-4020"},"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"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rick Stevens","raw_affiliation_strings":["Argonne National Laboratory, University of Chicago"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, University of Chicago","institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046675967","display_name":"Thomas Brettin","orcid":"https://orcid.org/0000-0001-9301-9760"},"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"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Brettin","raw_affiliation_strings":["Argonne National Laboratory, University of Chicago"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, University of Chicago","institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049471852","display_name":"Fangfang Xia","orcid":"https://orcid.org/0000-0001-6567-0564"},"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"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fangfang Xia","raw_affiliation_strings":["Argonne National Laboratory, University of Chicago"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, University of Chicago","institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I40347166"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5072646801"],"corresponding_institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":1.3159,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.8441658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9972000122070312,"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":0.9972000122070312,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.8012063503265381},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7463385462760925},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6954525709152222},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6574342250823975},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5801448822021484},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5577199459075928},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5385928750038147},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.4451269507408142},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4390679597854614},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.43612784147262573},{"id":"https://openalex.org/keywords/frequency-scaling","display_name":"Frequency scaling","score":0.4142223000526428},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.38801366090774536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.376669704914093},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.370480477809906},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36114072799682617},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.2508769631385803},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1414162516593933},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.10277524590492249}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8012063503265381},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7463385462760925},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6954525709152222},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6574342250823975},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5801448822021484},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5577199459075928},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5385928750038147},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4451269507408142},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4390679597854614},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.43612784147262573},{"id":"https://openalex.org/C157742956","wikidata":"https://www.wikidata.org/wiki/Q3237776","display_name":"Frequency scaling","level":3,"score":0.4142223000526428},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.38801366090774536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.376669704914093},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.370480477809906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36114072799682617},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2508769631385803},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1414162516593933},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.10277524590492249},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3337821.3337905","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3337821.3337905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8799999952316284,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2092528372","https://openalex.org/W2536542975","https://openalex.org/W2766126457","https://openalex.org/W2788193959","https://openalex.org/W2903697572","https://openalex.org/W2962747323","https://openalex.org/W6600118084","https://openalex.org/W6829887170"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W2068975988","https://openalex.org/W4318615513"],"abstract_inverted_index":{"Training":[0],"scientific":[1],"deep":[2,56],"learning":[3,45,57,78],"models":[4],"requires":[5],"the":[6,19,23,26,39,49,54,62,86,94,100,113,125,141,156,162,166,170,177,186,260,264],"significant":[7],"compute":[8,149],"power":[9],"of":[10,22,99,106,144,165],"high-performance":[11],"computing":[12],"systems.":[13],"In":[14],"this":[15],"paper,":[16],"we":[17,237],"analyze":[18],"performance":[20,172,178,196,218,242],"characteristics":[21],"benchmarks":[24,103,153,188],"from":[25],"exploratory":[27],"research":[28],"project":[29],"CANDLE":[30,63,102],"(Cancer":[31],"Distributed":[32],"Learning":[33],"Environment)":[34],"with":[35,76,185],"a":[36],"focus":[37],"on":[38,112,189,208,230,254],"hyperparameters":[40],"epochs,":[41,145],"batch":[42,74,146],"sizes,":[43,147],"and":[44,73,89,97,109,124,148,159,174,179,198,213,220,244],"rates.":[46],"We":[47,65,168],"present":[48],"parallel":[50,101],"methodology":[51],"that":[52],"uses":[53],"distributed":[55],"framework":[58],"Horovod":[59],"to":[60,81,139,154,160,193,200,210,215,222,232,240,246,256],"parallelize":[61],"benchmarks.":[64,167],"then":[66,175],"use":[67],"scaling":[68,80,108,111,207,229,253],"strategies":[69],"for":[70,151,181],"both":[71],"epochs":[72],"size":[75],"linear":[77],"rate":[79],"investigate":[82],"how":[83,138],"they":[84],"impact":[85],"execution":[87,163],"time":[88,164],"accuracy":[90,158],"as":[91,93],"well":[92],"power,":[95],"energy,":[96],"scalability":[98],"under":[104,205,227,251],"conditions":[105],"strong":[107,206,252],"weak":[110,228],"IBM":[114],"Power9":[115],"heterogeneous":[116],"system":[117],"Summit":[118,190],"at":[119,129],"Oak":[120],"Ridge":[121],"National":[122,131],"Laboratory":[123],"Cray":[126],"XC40":[127],"Theta":[128],"Argonne":[130],"Laboratory.":[132],"This":[133],"study":[134],"provides":[135],"insights":[136],"into":[137],"set":[140],"proper":[142],"numbers":[143],"resources":[150],"these":[152],"preserve":[155],"high":[157],"reduce":[161],"identify":[169],"data-loading":[171],"bottleneck":[173],"improve":[176],"energy":[180,203,225,249],"better":[182],"scalability.":[183],"Results":[184],"modified":[187],"indicate":[191],"up":[192,199,209,214,221,231,239,245,255],"78.25%":[194],"in":[195,202,217,224,248],"improvement":[197,219,243],"78%":[201],"saving":[204,226,250],"384":[211,257],"GPUs,":[212],"79.5%":[216],"77.11%":[223],"3,072":[233],"GPUs.":[234],"On":[235],"Theta,":[236],"achieve":[238],"45.22%":[241],"41.78%":[247],"nodes.":[258],"Moreover,":[259],"modification":[261],"dramatically":[262],"reduces":[263],"broadcast":[265],"overhead.":[266]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}