{"id":"https://openalex.org/W4400681470","doi":"https://doi.org/10.1109/ispass61541.2024.00022","title":"On the Rise of AMD Matrix Cores: Performance, Power Efficiency, and Programmability","display_name":"On the Rise of AMD Matrix Cores: Performance, Power Efficiency, and Programmability","publication_year":2024,"publication_date":"2024-05-05","ids":{"openalex":"https://openalex.org/W4400681470","doi":"https://doi.org/10.1109/ispass61541.2024.00022"},"language":"en","primary_location":{"id":"doi:10.1109/ispass61541.2024.00022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass61541.2024.00022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","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/A5092658397","display_name":"Gabin Schieffer","orcid":"https://orcid.org/0009-0003-6504-7109"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Gabin Schieffer","raw_affiliation_strings":["KTH Royal Institute of Technology,Stockholm,Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078558764","display_name":"Daniel Ara\u00fajo De Medeiros","orcid":"https://orcid.org/0000-0002-1434-3042"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Daniel Ara\u00fajo De Medeiros","raw_affiliation_strings":["KTH Royal Institute of Technology,Stockholm,Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091933605","display_name":"Jennifer Faj","orcid":"https://orcid.org/0000-0002-7733-6229"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jennifer Faj","raw_affiliation_strings":["KTH Royal Institute of Technology,Stockholm,Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070686608","display_name":"Aniruddha Marathe","orcid":"https://orcid.org/0000-0003-0546-4472"},"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":"Aniruddha Marathe","raw_affiliation_strings":["Lawrence Livermore National Laboratory,Livermore,USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory,Livermore,USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037069204","display_name":"Ivy Peng","orcid":"https://orcid.org/0000-0003-4158-3583"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ivy Peng","raw_affiliation_strings":["KTH Royal Institute of Technology,Stockholm,Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5092658397"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":9.1028,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.98826906,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"132","last_page":"143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9607999920845032,"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":0.9607999920845032,"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":0.9380999803543091,"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/power","display_name":"Power (physics)","score":0.5588501691818237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45513996481895447},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.415131539106369},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.20997944474220276},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07777541875839233},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.06386780738830566}],"concepts":[{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.5588501691818237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45513996481895447},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.415131539106369},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.20997944474220276},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07777541875839233},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.06386780738830566},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispass61541.2024.00022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass61541.2024.00022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8700000047683716,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2066804546","https://openalex.org/W2791673912","https://openalex.org/W2895305554","https://openalex.org/W2901549770","https://openalex.org/W2912101967","https://openalex.org/W2999609284","https://openalex.org/W3009452684","https://openalex.org/W3035232708","https://openalex.org/W3043303806","https://openalex.org/W3044913359","https://openalex.org/W3104528661","https://openalex.org/W3205226039","https://openalex.org/W3205833606","https://openalex.org/W4230906109","https://openalex.org/W4282975155","https://openalex.org/W4309672181","https://openalex.org/W4318603355","https://openalex.org/W4378803429","https://openalex.org/W4385387602","https://openalex.org/W4385585370","https://openalex.org/W4386106927","https://openalex.org/W4388581101","https://openalex.org/W6745245109","https://openalex.org/W6855376183"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Matrix":[0,16,51,62,98,122,137,163],"multiplication":[1],"is":[2],"a":[3,22,44,94,144],"core":[4],"computational":[5],"part":[6],"of":[7,15,25,38,48,67,97,117,121,136,147],"deep":[8],"learning":[9],"and":[10,35,74,80,115,178],"scientific":[11],"workloads.":[12],"The":[13],"emergence":[14],"Cores":[17,52,63,99,123,138,164],"in":[18,53,105,143],"high-end":[19],"AMD":[20,54],"GPUs,":[21],"building":[23],"block":[24],"Exascale":[26],"computers,":[27],"opens":[28],"new":[29],"opportunities":[30],"for":[31,60,77],"optimizing":[32],"the":[33,49,90,111,118,132,140],"performance":[34,95,106],"power":[36,119],"efficiency":[37,120],"compute-intensive":[39],"applications.":[40],"This":[41],"work":[42],"provides":[43],"timely,":[45],"comprehensive":[46],"characterization":[47],"novel":[50],"GPUs.":[55],"We":[56,108],"develop":[57],"low-level":[58],"micro-benchmarks":[59],"leveraging":[61],"at":[64,124],"different":[65,125],"levels":[66],"parallelism,":[68],"achieving":[69],"up":[70],"to":[71,152,165],"350,":[72],"88,":[73],"69":[75],"TFLOPS":[76],"mixed,":[78],"float,":[79],"double":[81],"precision":[82],"on":[83],"one":[84],"GPU.":[85],"Using":[86],"results":[87,155],"obtained":[88],"from":[89,150],"micro-benchmarks,":[91],"we":[92,130],"provide":[93,110],"model":[96],"that":[100,157],"can":[101,160],"guide":[102],"application":[103,158],"developers":[104,159],"tuning.":[107],"also":[109],"first":[112],"quantitative":[113],"study":[114],"modeling":[116],"floating-point":[126],"data":[127,176],"types.":[128],"Finally,":[129],"evaluate":[131],"high-":[133],"level":[134],"programmability":[135],"through":[139],"rocBLAS":[141],"library":[142],"wide":[145],"range":[146],"matrix":[148],"sizes":[149],"16":[151],"64K.":[153],"Our":[154],"indicate":[156],"transparently":[161],"leverage":[162],"deliver":[166],"more":[167],"than":[168],"92%":[169],"peak":[170],"computing":[171],"throughput":[172],"by":[173],"properly":[174],"selecting":[175],"types":[177],"interfaces.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}