{"id":"https://openalex.org/W4386585089","doi":"https://doi.org/10.1145/3569951.3593601","title":"Performance of Distributed Deep Learning Workloads on a Composable Cyberinfrastructure","display_name":"Performance of Distributed Deep Learning Workloads on a Composable Cyberinfrastructure","publication_year":2023,"publication_date":"2023-07-23","ids":{"openalex":"https://openalex.org/W4386585089","doi":"https://doi.org/10.1145/3569951.3593601"},"language":"en","primary_location":{"id":"doi:10.1145/3569951.3593601","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3569951.3593601","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3569951.3593601","source":{"id":"https://openalex.org/S4306523034","display_name":"Practice and Experience in Advanced Research Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3569951.3593601","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090685598","display_name":"Zhenhua He","orcid":"https://orcid.org/0000-0003-1706-3561"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhenhua He","raw_affiliation_strings":["Texas A&M University, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005821351","display_name":"Aditi Saluja","orcid":"https://orcid.org/0009-0003-8930-3365"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditi Saluja","raw_affiliation_strings":["Texas A&M University, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039844494","display_name":"Richard Lawrence","orcid":"https://orcid.org/0000-0002-1451-0277"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Lawrence","raw_affiliation_strings":["Texas A&M University, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063166697","display_name":"Dhruva K. Chakravorty","orcid":"https://orcid.org/0000-0001-7739-3701"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhruva Chakravorty","raw_affiliation_strings":["Texas A&M University, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067331242","display_name":"Francis Dang","orcid":"https://orcid.org/0009-0008-9494-7639"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Francis Dang","raw_affiliation_strings":["Texas A&M University, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070232707","display_name":"Lisa M. P\u00e9rez","orcid":"https://orcid.org/0000-0003-1176-1027"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lisa Perez","raw_affiliation_strings":["Texas A&M University, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043257503","display_name":"Honggao Liu","orcid":"https://orcid.org/0009-0002-2942-9014"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Honggao Liu","raw_affiliation_strings":["Texas A&M University, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5090685598"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":1.8449,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.88587482,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"60","last_page":"67"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/cyberinfrastructure","display_name":"Cyberinfrastructure","score":0.9845484495162964},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8537306189537048},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.817055881023407},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6465373635292053},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5272093415260315},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46805140376091003},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4457027018070221},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4015347361564636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32372763752937317},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21021240949630737},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10782265663146973}],"concepts":[{"id":"https://openalex.org/C2776397876","wikidata":"https://www.wikidata.org/wiki/Q1450531","display_name":"Cyberinfrastructure","level":2,"score":0.9845484495162964},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8537306189537048},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817055881023407},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6465373635292053},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5272093415260315},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46805140376091003},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4457027018070221},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4015347361564636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32372763752937317},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21021240949630737},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10782265663146973}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3569951.3593601","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3569951.3593601","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3569951.3593601","source":{"id":"https://openalex.org/S4306523034","display_name":"Practice and Experience in Advanced Research Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3569951.3593601","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3569951.3593601","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3569951.3593601","source":{"id":"https://openalex.org/S4306523034","display_name":"Practice and Experience in Advanced Research Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G3494106745","display_name":null,"funder_award_id":"2112356","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3668617436","display_name":null,"funder_award_id":"1925764","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4831022539","display_name":null,"funder_award_id":"2019129","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5644288026","display_name":null,"funder_award_id":"2019136","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5921281487","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386585089.pdf","grobid_xml":"https://content.openalex.org/works/W4386585089.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2783840310","https://openalex.org/W2886259097","https://openalex.org/W2896457183","https://openalex.org/W2974875810","https://openalex.org/W2975059944","https://openalex.org/W2978017171","https://openalex.org/W4284975144","https://openalex.org/W4289827730","https://openalex.org/W4386585035"],"related_works":["https://openalex.org/W273500195","https://openalex.org/W2043019925","https://openalex.org/W4236056781","https://openalex.org/W4293768956","https://openalex.org/W2773781927","https://openalex.org/W2184477657","https://openalex.org/W90628286","https://openalex.org/W1696735061","https://openalex.org/W2152811545","https://openalex.org/W1999096178"],"abstract_inverted_index":{"The":[0],"next":[1],"generation":[2],"of":[3,60,96,116],"computing":[4,126],"systems":[5],"are":[6,145],"likely":[7],"to":[8,22,68,83,86],"rely":[9],"on":[10,89,99,120,141],"disaggregated":[11,77],"resources":[12,35,65,78,91],"that":[13,28,62],"can":[14],"be":[15],"dynamically":[16],"reconfigured":[17],"and":[18,25,92,114,123,138],"customized":[19],"for":[20],"researchers":[21],"support":[23],"scientific":[24],"engineering":[26],"workflows":[27,88],"require":[29],"different":[30],"cyberinfrastructure":[31],"(CI)":[32],"technologies.":[33,43],"These":[34],"would":[36,45],"include":[37],"memory,":[38],"accelerators,":[39],"co-processors":[40],"among":[41],"other":[42],"This":[44],"represent":[46],"a":[47,69],"significant":[48],"shift":[49],"in":[50],"High":[51],"Performance":[52],"Computing":[53],"(HPC)":[54],"from":[55,129],"the":[56,94,112,133],"now":[57],"typical":[58],"model":[59],"clusters":[61],"have":[63],"these":[64,90,142],"permanently":[66],"connected":[67],"single":[70],"server.":[71],"While":[72],"composing":[73],"hardware":[74],"frameworks":[75],"with":[76,136],"holds":[79],"promise,":[80],"we":[81,110],"need":[82],"understand":[84],"how":[85],"situate":[87],"evaluate":[93],"impact":[95],"this":[97,107],"approach":[98],"workflow":[100],"performance":[101,115],"against":[102],"\u201ctraditional\u201d":[103],"clusters.":[104],"Toward":[105],"developing":[106],"knowledge":[108],"framework,":[109],"study":[111],"applicability":[113],"deep":[117],"learning":[118],"workloads":[119],"GPU-enabled":[121],"composable":[122],"traditional":[124],"HPC":[125,143],"platforms.":[127],"Results":[128],"tests":[130],"performed":[131],"using":[132],"Horovod":[134],"framework":[135],"TensorFlow":[137],"PyTorch":[139],"models":[140],"environments":[144],"presented":[146],"here.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}