{"id":"https://openalex.org/W4400799121","doi":"https://doi.org/10.1145/3626203.3670589","title":"Preliminary Results of the MLPerf BERT Inference Benchmark on AMD Instinct GPUs","display_name":"Preliminary Results of the MLPerf BERT Inference Benchmark on AMD Instinct GPUs","publication_year":2024,"publication_date":"2024-07-17","ids":{"openalex":"https://openalex.org/W4400799121","doi":"https://doi.org/10.1145/3626203.3670589"},"language":"en","primary_location":{"id":"doi:10.1145/3626203.3670589","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626203.3670589","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626203.3670589","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing 2024: Human Powered Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3626203.3670589","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064530027","display_name":"Z. Jane Wang","orcid":"https://orcid.org/0009-0007-7123-2908"},"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":true,"raw_author_name":"Zixian Wang","raw_affiliation_strings":["Laboratory for Emerging Intelligence, Computer Science and Engineering, University of California, San Diego, USA"],"affiliations":[{"raw_affiliation_string":"Laboratory for Emerging Intelligence, Computer Science and Engineering, University of California, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104422454","display_name":"Khai Vu","orcid":null},"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":"Khai Vu","raw_affiliation_strings":["Computer Science and Engineering, University of California, San Diego, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of California, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089871809","display_name":"Miro Hodak","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miro Hodak","raw_affiliation_strings":["Advanced Micro Devices, Inc., USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc., USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057140370","display_name":"A. Mehrotra","orcid":"https://orcid.org/0009-0003-8577-5162"},"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":"Aarush Mehrotra","raw_affiliation_strings":["Computer Science and Engineering, University of California, San Diego, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of California, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047496804","display_name":"Francisco Ch\u00e1vez Guti\u00e9rrez","orcid":null},"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":"Francisco Gutierrez","raw_affiliation_strings":["Computer Science and Engineering, University of California, San Diego, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of California, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019413667","display_name":"Kyle Smith","orcid":"https://orcid.org/0000-0002-0188-8289"},"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":"Kyle Smith","raw_affiliation_strings":["Computer Science and Engineering, University of California, San Diego, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of California, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111262046","display_name":"G. Seo","orcid":null},"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":"Gloria Seo","raw_affiliation_strings":["Computer Science and Engineering, University of California, San Diego, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of California, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109905147","display_name":"A.R. Garcia","orcid":null},"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":"Austin Garcia","raw_affiliation_strings":["Electrical and Computer Engineering, University of California, San Diego, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of California, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111655973","display_name":"Bryan A. Chin","orcid":null},"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":"Bryan Chin","raw_affiliation_strings":["Computer Science and Engineering, University of California, San Diego, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of California, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113295535","display_name":"Marty Kandes","orcid":null},"institutions":[{"id":"https://openalex.org/I181653535","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07","country_code":"US","type":"facility","lineage":["https://openalex.org/I181653535","https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marty Kandes","raw_affiliation_strings":["San Diego Supercomuter Center, San Diego Supercomputer Center, USA"],"affiliations":[{"raw_affiliation_string":"San Diego Supercomuter Center, San Diego Supercomputer Center, USA","institution_ids":["https://openalex.org/I181653535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013670839","display_name":"Thomas M. Powell","orcid":"https://orcid.org/0000-0001-6035-1935"},"institutions":[{"id":"https://openalex.org/I181653535","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07","country_code":"US","type":"facility","lineage":["https://openalex.org/I181653535","https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary P Thomas","raw_affiliation_strings":["San Diego Supercomuter Center, San Diego Supercomputer Center, USA"],"affiliations":[{"raw_affiliation_string":"San Diego Supercomuter Center, San Diego Supercomputer Center, USA","institution_ids":["https://openalex.org/I181653535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5064530027"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10021283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.996999979019165,"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":0.996999979019165,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9955999851226807,"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"}},{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.975600004196167,"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/instinct","display_name":"Instinct","score":0.7915005087852478},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7557591795921326},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6898065805435181},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6878251433372498},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5145480036735535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29758235812187195},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.09254911541938782},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07636609673500061},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.04646420478820801}],"concepts":[{"id":"https://openalex.org/C3232509","wikidata":"https://www.wikidata.org/wiki/Q18237","display_name":"Instinct","level":2,"score":0.7915005087852478},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7557591795921326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6898065805435181},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6878251433372498},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5145480036735535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29758235812187195},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.09254911541938782},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07636609673500061},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.04646420478820801},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626203.3670589","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626203.3670589","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626203.3670589","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing 2024: Human Powered Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3626203.3670589","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626203.3670589","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626203.3670589","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing 2024: Human Powered Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400799121.pdf"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2963351448","https://openalex.org/W2970971581","https://openalex.org/W3043273434","https://openalex.org/W4200559323","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2357264280","https://openalex.org/W2349142772","https://openalex.org/W2400156683","https://openalex.org/W2906970874","https://openalex.org/W2079365928","https://openalex.org/W2351780972","https://openalex.org/W3112807754","https://openalex.org/W2783471524"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"Artificial":[3],"Intelligence":[4],"(AI)":[5],"has":[6],"reshaped":[7],"various":[8],"facets":[9],"of":[10,21,83,108,114,131,167],"our":[11,53,152],"day-to-day":[12],"lives.":[13],"To":[14,52],"evaluate":[15],"both":[16],"hardware":[17],"and":[18,33,63,94,104,161,180],"software":[19],"deployment":[20],"Machine":[22,37,47],"Learning":[23,38,48],"(ML)":[24],"applications,":[25],"it":[26],"is":[27,56],"necessary":[28],"to":[29,78,88,117],"measure":[30],"system-wide":[31],"performance":[32],"accuracy.":[34],"MLPerf,":[35],"a":[36,43,165],"Benchmark":[39,150],"from":[40,125],"MLCommons,":[41],"provides":[42],"standard":[44],"for":[45,144,178],"measuring":[46],"Performance":[49],"on":[50,61,69,75,90,155],"hardware.":[51],"knowledge,":[54],"there":[55],"little":[57],"known":[58],"public":[59],"effort":[60,77],"porting":[62,107],"optimizing":[64],"these":[65],"inference":[66],"benchmark":[67,110],"models":[68],"AMD":[70,91,156,176],"GPUs.":[71],"This":[72,122],"paper":[73,123],"focuses":[74],"the":[76,84,99,105,109,115,118,132,140,146,159,170],"port":[79],"MLPerf":[80,85,119,147],"BERT,":[81],"one":[82],"Inference":[86,149],"Benchmarks,":[87],"run":[89],"Instinct":[92],"MI210":[93],"MI250":[95,160],"Accelerators.":[96],"We":[97,138],"describe":[98],"challenges":[100],"encountered,":[101],"solutions":[102],"applied,":[103],"successful":[106],"resulting":[111],"in":[112],"submission":[113],"code":[116],"community":[120],"codebase.":[121],"derives":[124],"unpublished":[126],"work":[127],"completed":[128],"as":[129,164],"part":[130],"2023":[133],"Student":[134],"Cluster":[135],"Competition":[136],"(SCC23).":[137],"present":[139],"first":[141],"unofficial":[142],"results":[143],"running":[145],"BERT":[148],"using":[151],"optimization":[153],"strategies":[154],"accelerators,":[157],"specifically":[158],"MI210.":[162],"Additionally,":[163],"result":[166],"this":[168],"effort,":[169],"CM":[171],"Automation":[172],"framework":[173],"now":[174],"supports":[175],"ROCm":[177],"PyTorch":[179],"ONNX":[181],"Runtime":[182],"platforms.":[183]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
