{"id":"https://openalex.org/W4388102819","doi":"https://doi.org/10.1145/3581784.3607066","title":"Optimizing High-Performance Linpack for Exascale Accelerated Architectures","display_name":"Optimizing High-Performance Linpack for Exascale Accelerated Architectures","publication_year":2023,"publication_date":"2023-10-30","ids":{"openalex":"https://openalex.org/W4388102819","doi":"https://doi.org/10.1145/3581784.3607066"},"language":"en","primary_location":{"id":"doi:10.1145/3581784.3607066","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581784.3607066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","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/A5020250502","display_name":"Noel Chalmers","orcid":"https://orcid.org/0000-0002-1293-7525"},"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":true,"raw_author_name":"Noel Chalmers","raw_affiliation_strings":["Advanced Micro Devices, Inc, Austin, TX, United States of America"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc, Austin, TX, United States of America","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070456582","display_name":"Jakub Kurzak","orcid":"https://orcid.org/0000-0002-9697-0145"},"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":"Jakub Kurzak","raw_affiliation_strings":["Advanced Micro Devices, Inc, Oak Ridge, TN, United States of America"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc, Oak Ridge, TN, United States of America","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006676862","display_name":"Damon McDougall","orcid":"https://orcid.org/0009-0008-5865-9322"},"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":"Damon Mcdougall","raw_affiliation_strings":["Advanced Micro Devices, Inc, Austin, TX, United States of America"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc, Austin, TX, United States of America","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022068252","display_name":"Paul T. Bauman","orcid":"https://orcid.org/0000-0003-3513-8264"},"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":"Paul Bauman","raw_affiliation_strings":["Advanced Micro Devices, Inc, Austin, TX, United States of America"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc, Austin, TX, United States of America","institution_ids":["https://openalex.org/I4210137977"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020250502"],"corresponding_institution_ids":["https://openalex.org/I4210137977"],"apc_list":null,"apc_paid":null,"fwci":3.3832,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93247487,"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":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9998000264167786,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.84965980052948},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.7800301909446716},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7482877969741821},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7464806437492371},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5774425268173218},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.5145801901817322},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4273141026496887},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.41626471281051636},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.40023303031921387},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.39999863505363464},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.19783052802085876},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.09349557757377625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.84965980052948},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.7800301909446716},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7482877969741821},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7464806437492371},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5774425268173218},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.5145801901817322},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4273141026496887},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.41626471281051636},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.40023303031921387},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.39999863505363464},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.19783052802085876},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.09349557757377625},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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:10.1145/3581784.3607066","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581784.3607066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1777209000","https://openalex.org/W1946080187","https://openalex.org/W2087210673","https://openalex.org/W2162626314","https://openalex.org/W2169631286","https://openalex.org/W2170611190","https://openalex.org/W2968304367","https://openalex.org/W3003637776","https://openalex.org/W3137083963","https://openalex.org/W4229524227","https://openalex.org/W4241072847"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W3191490922","https://openalex.org/W2794038527","https://openalex.org/W2327638088","https://openalex.org/W2068975988"],"abstract_inverted_index":{"We":[0,58,95],"detail":[1,59],"the":[2,12,27,33,38,49,70,75,84,104,112],"performance":[3,61,98],"optimizations":[4,90],"made":[5],"in":[6],"rocHPL,":[7],"AMD's":[8],"open-source":[9],"implementation":[10,31,102],"of":[11,78,100,103,111],"High-Performance":[13],"Linpack":[14],"(HPL)":[15],"benchmark":[16,106],"targeting":[17],"accelerated":[18],"node":[19,39,110],"architectures":[20],"designed":[21],"for":[22],"exascale":[23],"systems":[24],"such":[25,63],"as":[26,46,48,64,86,88,122,124],"Frontier":[28,113],"supercomputer.":[29],"The":[30],"leverages":[32],"high-throughput":[34],"GPU":[35],"accelerators":[36],"on":[37,74,83,107],"via":[40],"highly":[41],"optimized":[42],"linear":[43],"algebra":[44],"libraries,":[45],"well":[47,87,123],"entire":[50],"CPU":[51,79],"socket":[52],"to":[53,68,126],"perform":[54],"latency-sensitive":[55],"factorization":[56,72],"phases.":[57],"novel":[60],"improvements":[62],"a":[65,108],"multithreaded":[66],"approach":[67],"computing":[69],"panel":[71],"phase":[73],"CPU,":[76],"time-sharing":[77],"cores":[80],"between":[81],"processes":[82],"node,":[85],"several":[89],"which":[91],"hide":[92],"MPI":[93],"communication.":[94],"present":[96],"some":[97],"results":[99],"this":[101],"HPL":[105],"single":[109],"early":[114],"access":[115],"cluster":[116],"at":[117],"Oak":[118],"Ridge":[119],"National":[120],"Laboratory,":[121],"scaling":[125],"multiple":[127],"nodes.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}