{"id":"https://openalex.org/W4284975144","doi":"https://doi.org/10.1145/3491418.3530772","title":"Benchmarking the Performance of Accelerators on National Cyberinfrastructure Resources for Artificial Intelligence / Machine Learning Workloads","display_name":"Benchmarking the Performance of Accelerators on National Cyberinfrastructure Resources for Artificial Intelligence / Machine Learning Workloads","publication_year":2022,"publication_date":"2022-07-08","ids":{"openalex":"https://openalex.org/W4284975144","doi":"https://doi.org/10.1145/3491418.3530772"},"language":"en","primary_location":{"id":"doi:10.1145/3491418.3530772","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3491418.3530772","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013964237","display_name":"Abhinand Nasari","orcid":"https://orcid.org/0009-0004-3309-5509"},"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":"Abhinand Nasari","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/A5079693009","display_name":"Hieu Trung Le","orcid":"https://orcid.org/0000-0003-2510-073X"},"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":"Hieu Le","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/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":false,"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/A5100635997","display_name":"Xin Yang","orcid":"https://orcid.org/0000-0003-0445-6497"},"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":"Xin Yang","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/A5048746854","display_name":"Mario Michael Krell","orcid":"https://orcid.org/0000-0002-7823-3336"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mario Krell","raw_affiliation_strings":["Graphcore Inc., USA"],"affiliations":[{"raw_affiliation_string":"Graphcore Inc., USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014565735","display_name":"Alex Tsyplikhin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Tsyplikhin","raw_affiliation_strings":["Graphcore Inc., USA"],"affiliations":[{"raw_affiliation_string":"Graphcore Inc., USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069831701","display_name":"Mahidhar Tatineni","orcid":"https://orcid.org/0009-0003-0709-090X"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahidhar Tatineni","raw_affiliation_strings":["University of California San Diego, USA"],"affiliations":[{"raw_affiliation_string":"University of California San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004379411","display_name":"T.M. Cockerill","orcid":"https://orcid.org/0000-0002-1548-1922"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Cockerill","raw_affiliation_strings":["University of Texas at Austin, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"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":"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":"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":12,"corresponding_author_ids":["https://openalex.org/A5013964237"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":8.7653,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.97105535,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9970999956130981,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.8065947890281677},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6522831320762634},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.637180507183075},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5729334950447083},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5696784853935242},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5616834759712219},{"id":"https://openalex.org/keywords/cyberinfrastructure","display_name":"Cyberinfrastructure","score":0.5526342391967773},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47373998165130615},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46332141757011414},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.45820096135139465},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4542939066886902},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4530661702156067},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3401150405406952},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.28464028239250183},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.21900278329849243},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17834323644638062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8065947890281677},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6522831320762634},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.637180507183075},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5729334950447083},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5696784853935242},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5616834759712219},{"id":"https://openalex.org/C2776397876","wikidata":"https://www.wikidata.org/wiki/Q1450531","display_name":"Cyberinfrastructure","level":2,"score":0.5526342391967773},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47373998165130615},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46332141757011414},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.45820096135139465},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4542939066886902},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4530661702156067},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3401150405406952},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.28464028239250183},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.21900278329849243},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17834323644638062},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3491418.3530772","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3491418.3530772","pdf_url":null,"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":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3668617436","display_name":null,"funder_award_id":"1925764","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W16184363","https://openalex.org/W1997162567","https://openalex.org/W2024585065","https://openalex.org/W2071039340","https://openalex.org/W2618530766","https://openalex.org/W3185531724","https://openalex.org/W4238820826"],"related_works":["https://openalex.org/W2428494321","https://openalex.org/W4281488864","https://openalex.org/W2148010638","https://openalex.org/W2593649365","https://openalex.org/W2442273404","https://openalex.org/W3214520715","https://openalex.org/W2950577464","https://openalex.org/W3098379356","https://openalex.org/W3214188003","https://openalex.org/W4226055497"],"abstract_inverted_index":{"Upcoming":[0],"regional":[1],"and":[2,42,59,85,109,121,165,172,186],"National":[3],"Science":[4],"Foundation":[5],"(NSF)-funded":[6],"Cyberinfrastructure":[7],"(CI)":[8],"resources":[9],"will":[10,51,189],"give":[11],"researchers":[12,33],"opportunities":[13],"to":[14,38,46,117,139,157],"run":[15,144],"their":[16,44],"artificial":[17],"intelligence":[18],"/":[19],"machine":[20],"learning":[21],"(AI/ML)":[22],"workflows":[23,45],"on":[24,65,204],"accelerators.":[25],"To":[26],"effectively":[27],"leverage":[28,103],"this":[29,177],"burgeoning":[30],"CI-rich":[31],"landscape,":[32],"need":[34],"extensive":[35],"benchmark":[36],"data":[37,50],"maximize":[39],"performance":[40,72,120],"gains":[41],"map":[43],"appropriate":[47],"architectures.":[48,127,198],"This":[49,167],"further":[52],"assist":[53],"CI":[54,60],"administrators,":[55],"NSF":[56],"program":[57],"officers,":[58],"allocation-reviewers":[61],"make":[62],"informed":[63],"determinations":[64],"CI-resource":[66],"allocations.":[67],"Here,":[68],"we":[69],"compare":[70],"the":[71,78,86,104,110],"of":[73,89,98,106,112,181,196,201],"two":[74],"very":[75],"different":[76,170],"architectures:":[77],"commonly":[79],"used":[80],"Graphical":[81],"Processing":[82,91],"Units":[83,92],"(GPUs)":[84],"new":[87],"generation":[88],"Intelligence":[90],"(IPUs),":[93],"by":[94],"running":[95],"training":[96,129,164],"benchmarks":[97],"common":[99],"AI/ML":[100],"models.":[101],"We":[102],"maturity":[105],"software":[107],"stacks,":[108],"ease":[111],"migration":[113],"among":[114],"these":[115,197,202],"platforms":[116],"learn":[118],"that":[119,137],"scaling":[122],"are":[123],"similar":[124],"for":[125],"both":[126],"Exploring":[128],"parameters,":[130],"such":[131,179],"as":[132,174],"batch":[133,148,155],"size,":[134],"however":[135],"finds":[136],"owing":[138],"memory":[140],"processing":[141],"structures,":[142],"IPUs":[143],"efficiently":[145],"with":[146,169],"smaller":[147],"sizes,":[149],"while":[150],"GPUs":[151],"benefit":[152],"from":[153],"large":[154],"sizes":[156],"extract":[158],"sufficient":[159],"parallelism":[160,185],"in":[161,176,193],"neural":[162],"network":[163],"inference.":[166],"comes":[168],"advantages":[171],"disadvantages":[173],"discussed":[175],"paper.As":[178],"considerations":[180],"inference":[182],"latency,":[183],"inherent":[184],"model":[187,209],"accuracy":[188],"play":[190],"a":[191,205],"role":[192],"researcher":[194],"selection":[195],"The":[199],"impact":[200],"choices":[203],"representative":[206],"image":[207],"compression":[208],"system":[210],"is":[211],"discussed.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}