{"id":"https://openalex.org/W7119511510","doi":"https://doi.org/10.1145/3773656.3773680","title":"GPU Partitioning, Power, and Performance of the AMD MI300A","display_name":"GPU Partitioning, Power, and Performance of the AMD MI300A","publication_year":2026,"publication_date":"2026-01-09","ids":{"openalex":"https://openalex.org/W7119511510","doi":"https://doi.org/10.1145/3773656.3773680"},"language":null,"primary_location":{"id":"doi:10.1145/3773656.3773680","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3773656.3773680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region","raw_type":"proceedings-article"},"type":"conference-paper","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/A5116901233","display_name":"Amr Akmal Abouelmagd","orcid":null},"institutions":[{"id":"https://openalex.org/I63920570","display_name":"Tennessee Technological University","ror":"https://ror.org/05drmrq39","country_code":"US","type":"education","lineage":["https://openalex.org/I63920570"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amr Abouelmagd","raw_affiliation_strings":["Tennessee Technological University, Cookeville, USA"],"raw_orcid":"https://orcid.org/0009-0001-0303-2871","affiliations":[{"raw_affiliation_string":"Tennessee Technological University, Cookeville, USA","institution_ids":["https://openalex.org/I63920570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109547820","display_name":"David Boehme","orcid":null},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Boehme","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, USA"],"raw_orcid":"https://orcid.org/0000-0002-4159-1519","affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010860138","display_name":"Stephanie Brink","orcid":"https://orcid.org/0000-0002-1458-8453"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephanie Brink","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, USA"],"raw_orcid":"https://orcid.org/0000-0002-1458-8453","affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079015680","display_name":"Jason Burmark","orcid":"https://orcid.org/0009-0005-3036-0108"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Burmark","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, USA"],"raw_orcid":"https://orcid.org/0009-0005-3036-0108","affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091836403","display_name":"Michael McKinsey","orcid":"https://orcid.org/0009-0001-7201-5733"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael McKinsey","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, USA"],"raw_orcid":"https://orcid.org/0009-0001-7201-5733","affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026440046","display_name":"Anthony Skjellum","orcid":"https://orcid.org/0000-0001-5252-6600"},"institutions":[{"id":"https://openalex.org/I63920570","display_name":"Tennessee Technological University","ror":"https://ror.org/05drmrq39","country_code":"US","type":"education","lineage":["https://openalex.org/I63920570"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony Skjellum","raw_affiliation_strings":["Tennessee Technological University, Cookeville, USA"],"raw_orcid":"https://orcid.org/0000-0001-5252-6600","affiliations":[{"raw_affiliation_string":"Tennessee Technological University, Cookeville, USA","institution_ids":["https://openalex.org/I63920570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012779678","display_name":"Olga Pearce","orcid":"https://orcid.org/0000-0002-1904-9627"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olga Pearce","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, USA"],"raw_orcid":"https://orcid.org/0000-0002-1904-9627","affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"215","last_page":"227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9232000112533569,"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":0.9232000112533569,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.031300000846385956,"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/T14347","display_name":"Big Data and Digital Economy","score":0.011300000362098217,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.6808000206947327},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.6309999823570251},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5171999931335449},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.49079999327659607},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4505999982357025},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4478999972343445},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.42879998683929443},{"id":"https://openalex.org/keywords/time-sharing","display_name":"Time-sharing","score":0.3995000123977661},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.39899998903274536},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.37299999594688416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8116000294685364},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.6808000206947327},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6309999823570251},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5242000222206116},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5171999931335449},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.49079999327659607},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C38725249","wikidata":"https://www.wikidata.org/wiki/Q913876","display_name":"Time-sharing","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3700999915599823},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C173061102","wikidata":"https://www.wikidata.org/wiki/Q478819","display_name":"Bandwidth throttling","level":3,"score":0.34549999237060547},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C19012869","wikidata":"https://www.wikidata.org/wiki/Q578372","display_name":"Response time","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.31029999256134033},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.30640000104904175},{"id":"https://openalex.org/C51332947","wikidata":"https://www.wikidata.org/wiki/Q1172305","display_name":"Shared resource","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C2982832238","wikidata":"https://www.wikidata.org/wiki/Q5531640","display_name":"General purpose","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.287200003862381},{"id":"https://openalex.org/C154556556","wikidata":"https://www.wikidata.org/wiki/Q192969","display_name":"Computer multitasking","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C176553487","wikidata":"https://www.wikidata.org/wiki/Q7855819","display_name":"Turnaround time","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C2777242750","wikidata":"https://www.wikidata.org/wiki/Q31351","display_name":"Slowdown","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2574000060558319},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3773656.3773680","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3773656.3773680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1967491301","https://openalex.org/W1988888548","https://openalex.org/W2030167104","https://openalex.org/W2078794610","https://openalex.org/W2129471558","https://openalex.org/W2996807164","https://openalex.org/W3195293013","https://openalex.org/W4289828024","https://openalex.org/W4385623175","https://openalex.org/W4401211711","https://openalex.org/W4406157145","https://openalex.org/W4415381540","https://openalex.org/W7116345625"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"GPUs":[1],"play":[2],"a":[3,8,103],"crucial":[4],"role":[5],"in":[6,92,110,127,130,179],"accelerating":[7],"wide":[9,104],"range":[10,105],"of":[11,22,46,88,106,148,175],"computational":[12,107],"workloads.":[13],"It":[14],"is":[15],"important":[16],"to":[17,28,32,120,124,156,181],"understand":[18],"the":[19,86,89,99,111,122,139,144,149,154,162,168,176],"performance":[20,79,87,100],"limitations":[21],"these":[23],"workloads":[24],"on":[25,167],"specific":[26],"hardware":[27,117],"optimize":[29,71],"them":[30],"or":[31,37],"choose":[33],"more":[34],"appropriate":[35],"configurations":[36],"algorithms.":[38],"The":[39,54],"world\u2019s":[40],"fastest":[41],"supercomputer,":[42],"El":[43],"Capitan,":[44],"consists":[45],"11,520":[47],"AMD":[48],"MI300A":[49,55,90],"Accelerated":[50],"Processing":[51],"Units":[52],"(APUs).":[53],"APU":[56,155],"supports":[57],"three":[58],"logical":[59],"partitioning":[60,95],"modes\u2014SPX,":[61],"TPX,":[62],"and":[63,68,97,164],"CPX,":[64],"for":[65,78,133,185],"single,":[66],"triple,":[67],"core-partitioned,":[69],"respectively\u2014to":[70],"compute":[72,146],"resource":[73],"allocation,":[74],"offering":[75],"new":[76],"opportunities":[77],"tuning.":[80],"In":[81],"this":[82],"work,":[83],"we":[84],"evaluate":[85],"APUs":[91],"different":[93,131],"GPU":[94,165],"modes":[96,132],"demonstrate":[98],"impact":[101],"across":[102],"kernels":[108],"represented":[109],"RAJA":[112],"Performance":[113],"Suite.":[114],"We":[115,136,172],"use":[116],"counter":[118],"analysis":[119],"explain":[121],"up":[123,180],"30%":[125],"difference":[126],"execution":[128,170],"time":[129],"stencil":[134],"kernels.":[135,187],"also":[137],"explore":[138],"dynamic":[140],"power":[141,159,177],"sharing":[142,152],"among":[143],"accelerator":[145],"units":[147],"APU.":[150],"Power":[151],"enables":[153],"dynamically":[157],"allocate":[158],"resources":[160],"between":[161],"CPU":[163],"based":[166],"workload":[169],"behaviors.":[171],"observed":[173],"throttling":[174],"resulted":[178],"20%":[182],"slowdown":[183],"particularly":[184],"FLOP-bound":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-09T00:00:00"}