{"id":"https://openalex.org/W4390683800","doi":"https://doi.org/10.1145/3636480.3637097","title":"First Impressions of the NVIDIA Grace CPU Superchip and NVIDIA Grace Hopper Superchip for Scientific Workloads","display_name":"First Impressions of the NVIDIA Grace CPU Superchip and NVIDIA Grace Hopper Superchip for Scientific Workloads","publication_year":2024,"publication_date":"2024-01-08","ids":{"openalex":"https://openalex.org/W4390683800","doi":"https://doi.org/10.1145/3636480.3637097"},"language":"en","primary_location":{"id":"doi:10.1145/3636480.3637097","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3636480.3637097","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 on High Performance Computing in Asia-Pacific Region Workshops","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/A5059317345","display_name":"Nikolay A. Simakov","orcid":"https://orcid.org/0000-0001-6131-5979"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nikolay A. Simakov","raw_affiliation_strings":["Center for Computational Research, SUNY University at Buffalo, United States"],"raw_orcid":"https://orcid.org/0000-0001-6131-5979","affiliations":[{"raw_affiliation_string":"Center for Computational Research, SUNY University at Buffalo, United States","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014096956","display_name":"Matthew D. Jones","orcid":"https://orcid.org/0000-0001-7293-226X"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew D. Jones","raw_affiliation_strings":["Center for Computational Research, SUNY University at Buffalo, United States"],"raw_orcid":"https://orcid.org/0000-0001-7293-226X","affiliations":[{"raw_affiliation_string":"Center for Computational Research, SUNY University at Buffalo, United States","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086695342","display_name":"Thomas R. Furlani","orcid":"https://orcid.org/0000-0002-4683-0814"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas R. Furlani","raw_affiliation_strings":["Center for Computational Research, SUNY University at Buffalo, United States"],"raw_orcid":"https://orcid.org/0000-0002-4683-0814","affiliations":[{"raw_affiliation_string":"Center for Computational Research, SUNY University at Buffalo, United States","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056470242","display_name":"Eva Siegmann","orcid":"https://orcid.org/0000-0003-1216-1576"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eva Siegmann","raw_affiliation_strings":["Stony Brook University, United States"],"raw_orcid":"https://orcid.org/0000-0003-1216-1576","affiliations":[{"raw_affiliation_string":"Stony Brook University, United States","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010174060","display_name":"Robert J. Harrison","orcid":"https://orcid.org/0000-0002-8777-7466"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert J. Harrison","raw_affiliation_strings":["Stony Brook University, United States"],"raw_orcid":"https://orcid.org/0000-0002-8777-7466","affiliations":[{"raw_affiliation_string":"Stony Brook University, United States","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059317345"],"corresponding_institution_ids":["https://openalex.org/I63190737"],"apc_list":null,"apc_paid":null,"fwci":8.5383,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.98581207,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9991000294685364,"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/T11478","display_name":"Caching and Content Delivery","score":0.9908999800682068,"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":0.7672958374023438},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7422078847885132},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.7117172479629517},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6951202154159546},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.5518348217010498},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4326569736003876},{"id":"https://openalex.org/keywords/cpu-shielding","display_name":"CPU shielding","score":0.41893160343170166},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.34041285514831543},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24190592765808105},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.11860531568527222}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7672958374023438},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7422078847885132},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.7117172479629517},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6951202154159546},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.5518348217010498},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4326569736003876},{"id":"https://openalex.org/C180613757","wikidata":"https://www.wikidata.org/wiki/Q5013757","display_name":"CPU shielding","level":3,"score":0.41893160343170166},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.34041285514831543},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24190592765808105},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.11860531568527222},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3636480.3637097","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3636480.3637097","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 on High Performance Computing in Asia-Pacific Region Workshops","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8999999761581421,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G2675421721","display_name":null,"funder_award_id":"2137603 and 1927880","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1895692106","https://openalex.org/W1977627991","https://openalex.org/W2096339900","https://openalex.org/W2100986500","https://openalex.org/W2115110170","https://openalex.org/W2121047119","https://openalex.org/W2151316504","https://openalex.org/W2913716454","https://openalex.org/W3035762603","https://openalex.org/W3092054218","https://openalex.org/W3093105492","https://openalex.org/W3097636320","https://openalex.org/W3103156673","https://openalex.org/W3186737188","https://openalex.org/W4297097368","https://openalex.org/W4319067047","https://openalex.org/W4319067155"],"related_works":["https://openalex.org/W2387982802","https://openalex.org/W1896942098","https://openalex.org/W1991061790","https://openalex.org/W2088078730","https://openalex.org/W2400763249","https://openalex.org/W1482063109","https://openalex.org/W2043940072","https://openalex.org/W2249399447","https://openalex.org/W2745443495","https://openalex.org/W2904030423"],"abstract_inverted_index":{"The":[0,22,28,41,164],"engineering":[1],"samples":[2],"of":[3,79,158],"the":[4,76,91,132,185],"NVIDIA":[5,10,55,97,133,187,192],"Grace":[6,11,80,98,134,188,193],"CPU":[7,99,135,194],"Superchip":[8,100,136,190,195,196],"and":[9,19,26,39,51,90,120,151,155,191,199],"Hopper":[12,189],"Superchips":[13],"were":[14],"tested":[15,180],"using":[16],"different":[17],"benchmarks":[18,23],"scientific":[20,130],"applications.":[21],"include":[24],"HPCC":[25,73],"HPCG.":[27],"real":[29],"application-based":[30],"benchmark":[31,74],"includes":[32],"AI-Benchmark-Alpha":[33],"(a":[34],"TensorFlow":[35],"benchmark),":[36],"Gromacs,":[37,145],"OpenFOAM,":[38,150],"ROMS.":[40,163],"performance":[42,78,104,137,167],"was":[43,63],"compared":[44],"to":[45,83,101,106,142,175],"multiple":[46],"Intel,":[47],"AMD,":[48],"ARM":[49],"CPUs":[50],"several":[52],"x86":[53],"with":[54,110],"GPU":[56,182],"systems.":[57],"A":[58],"brief":[59],"energy":[60],"efficiency":[61],"estimate":[62],"performed":[64],"based":[65],"on":[66],"TDP":[67],"values.":[68],"We":[69],"found":[70],"that":[71],"in":[72,115,125,144,149,162,168],"tests,":[75],"per-core":[77],"is":[81,138,170],"similar":[82,105],"or":[84],"faster":[85,124,146,172],"than":[86,178],"AMD":[87],"Milan":[88],"cores,":[89],"high":[92],"core":[93],"count":[94],"often":[95],"allows":[96],"have":[102],"per-node":[103],"Intel":[107,159],"Sapphire":[108,160],"Rapids":[109,161],"High":[111],"Bandwidth":[112],"Memory:":[113],"slower":[114,139],"matrix":[116],"multiplication":[117],"(by":[118,122,127,173],"17%)":[119],"FFT":[121],"6%),":[123],"Linpack":[126],"9%)).":[128],"In":[129],"applications,":[131],"by":[140,147],"6%":[141],"18%":[143],"7%":[148],"right":[152],"between":[153],"HBM":[154],"DDR":[156],"modes":[157],"combined":[165],"CPU-GPU":[166],"Gromacs":[169],"significantly":[171],"20%":[174],"117%":[176],"faster)":[177],"any":[179],"x86-NVIDIA":[181],"system.":[183],"Overall,":[184],"new":[186],"are":[197],"high-performance":[198],"most":[200],"likely":[201],"energy-efficient":[202],"solutions":[203],"for":[204],"HPC":[205],"centers.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
