{"id":"https://openalex.org/W4396814805","doi":"https://doi.org/10.23919/isc.2024.10528925","title":"Porting HPC Applications to AMD Instinct\u2122 MI300A using Unified Memory and OpenMP\u00ae","display_name":"Porting HPC Applications to AMD Instinct\u2122 MI300A using Unified Memory and OpenMP\u00ae","publication_year":2024,"publication_date":"2024-05-01","ids":{"openalex":"https://openalex.org/W4396814805","doi":"https://doi.org/10.23919/isc.2024.10528925"},"language":"en","primary_location":{"id":"doi:10.23919/isc.2024.10528925","is_oa":true,"landing_page_url":"https://doi.org/10.23919/isc.2024.10528925","pdf_url":"https://ieeexplore.ieee.org/ielx7/10528919/10528920/10528925.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ISC High Performance 2024 Research Paper Proceedings (39th International Conference)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/10528919/10528920/10528925.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060832946","display_name":"Suyash Tandon","orcid":"https://orcid.org/0000-0001-5025-0284"},"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":"Suyash Tandon","raw_affiliation_strings":["Advanced Micro Devices, Inc.,Austin,U.S.A","Advanced Micro Devices, Inc., Austin, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc.,Austin,U.S.A","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"Advanced Micro Devices, Inc., Austin, U.S.A","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Leopold Grinberg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096066","display_name":"Open Knowledge (United Kingdom)","ror":"https://ror.org/00thqng93","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210096066"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Leopold Grinberg","raw_affiliation_strings":["OpenCFD Ltd.,Berkshire,U.K","OpenCFD Ltd., Berkshire, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OpenCFD Ltd.,Berkshire,U.K","institution_ids":["https://openalex.org/I4210096066"]},{"raw_affiliation_string":"OpenCFD Ltd., Berkshire, U.K","institution_ids":["https://openalex.org/I4210096066"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028956723","display_name":"Gheorghe-Teodor Bercea","orcid":"https://orcid.org/0000-0003-4331-4360"},"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":"Gheorghe-Teodor Bercea","raw_affiliation_strings":["Advanced Micro Devices, Inc.,Austin,U.S.A","Advanced Micro Devices, Inc., Austin, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc.,Austin,U.S.A","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"Advanced Micro Devices, Inc., Austin, U.S.A","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053563062","display_name":"Carlo Bertolli","orcid":"https://orcid.org/0009-0006-6852-1445"},"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":"Carlo Bertolli","raw_affiliation_strings":["Advanced Micro Devices, Inc.,Austin,U.S.A","Advanced Micro Devices, Inc., Austin, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc.,Austin,U.S.A","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"Advanced Micro Devices, Inc., Austin, U.S.A","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096170861","display_name":"Mark Olesen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096066","display_name":"Open Knowledge (United Kingdom)","ror":"https://ror.org/00thqng93","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210096066"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Olesen","raw_affiliation_strings":["OpenCFD Ltd.,Berkshire,U.K","OpenCFD Ltd., Berkshire, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OpenCFD Ltd.,Berkshire,U.K","institution_ids":["https://openalex.org/I4210096066"]},{"raw_affiliation_string":"OpenCFD Ltd., Berkshire, U.K","institution_ids":["https://openalex.org/I4210096066"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038525037","display_name":"S. Bn\u00e0","orcid":"https://orcid.org/0000-0001-5817-2073"},"institutions":[{"id":"https://openalex.org/I19908199","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03g9ch715","country_code":"BG","type":"facility","lineage":["https://openalex.org/I19908199"]},{"id":"https://openalex.org/I4210119786","display_name":"Cineca","ror":"https://ror.org/02f013h18","country_code":"IT","type":"other","lineage":["https://openalex.org/I4210119786"]}],"countries":["BG","IT"],"is_corresponding":false,"raw_author_name":"Simone Bna","raw_affiliation_strings":["CINECA,SuperComputing Applications and Innovations Department,Bologna,Italy","SuperComputing Applications and Innovations Department, CINECA, Bologna, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CINECA,SuperComputing Applications and Innovations Department,Bologna,Italy","institution_ids":["https://openalex.org/I19908199"]},{"raw_affiliation_string":"SuperComputing Applications and Innovations Department, CINECA, Bologna, Italy","institution_ids":["https://openalex.org/I4210119786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038263077","display_name":"Nicholas Malaya","orcid":"https://orcid.org/0000-0001-6259-7453"},"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":"Nicholas Malaya","raw_affiliation_strings":["Advanced Micro Devices, Inc.,Austin,U.S.A","Advanced Micro Devices, Inc., Austin, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc.,Austin,U.S.A","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"Advanced Micro Devices, Inc., Austin, U.S.A","institution_ids":["https://openalex.org/I4210137977"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9987999796867371,"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/porting","display_name":"Porting","score":0.8822827339172363},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8266503214836121},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5393379330635071},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5046910047531128},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.5026164054870605},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.44191455841064453},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.40971797704696655},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4042325019836426},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3585245609283447},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3297891616821289},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.30881035327911377}],"concepts":[{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.8822827339172363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8266503214836121},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5393379330635071},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5046910047531128},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.5026164054870605},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.44191455841064453},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.40971797704696655},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4042325019836426},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3585245609283447},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3297891616821289},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.30881035327911377},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/isc.2024.10528925","is_oa":true,"landing_page_url":"https://doi.org/10.23919/isc.2024.10528925","pdf_url":"https://ieeexplore.ieee.org/ielx7/10528919/10528920/10528925.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ISC High Performance 2024 Research Paper Proceedings (39th International Conference)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.23919/isc.2024.10528925","is_oa":true,"landing_page_url":"https://doi.org/10.23919/isc.2024.10528925","pdf_url":"https://ieeexplore.ieee.org/ielx7/10528919/10528920/10528925.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ISC High Performance 2024 Research Paper Proceedings (39th International Conference)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396814805.pdf"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1633459444","https://openalex.org/W2078794610","https://openalex.org/W2107868646","https://openalex.org/W2110187357","https://openalex.org/W2224081020","https://openalex.org/W2289627868","https://openalex.org/W2521614036","https://openalex.org/W2522451327","https://openalex.org/W2561081978","https://openalex.org/W2739789142","https://openalex.org/W2745325018","https://openalex.org/W2750212803","https://openalex.org/W2767028519","https://openalex.org/W2788316508","https://openalex.org/W2888279336","https://openalex.org/W2969535219","https://openalex.org/W2969798978","https://openalex.org/W2970909703","https://openalex.org/W2991211299","https://openalex.org/W3035561133","https://openalex.org/W3037205796","https://openalex.org/W3081656884","https://openalex.org/W3098288584","https://openalex.org/W3102927675","https://openalex.org/W3116661430","https://openalex.org/W3199181189","https://openalex.org/W3208752547","https://openalex.org/W4214700238","https://openalex.org/W4231880402","https://openalex.org/W6785878876"],"related_works":["https://openalex.org/W1994175142","https://openalex.org/W2192640005","https://openalex.org/W4396623380","https://openalex.org/W4317827391","https://openalex.org/W40577698","https://openalex.org/W1839004754","https://openalex.org/W1597188213","https://openalex.org/W2497938157","https://openalex.org/W4233212676","https://openalex.org/W184932080"],"abstract_inverted_index":{"AMD":[0,18],"Instinct\u2122":[1],"MI300A":[2],"is":[3,63,135],"the":[4,17,40,76,79,84,87,107,120,143],"world's":[5],"first":[6],"data":[7,43,47,89],"center":[8],"accelerated":[9],"processing":[10],"unit":[11],"(APU)":[12],"with":[13,123],"memory":[14,32,113],"shared":[15],"between":[16],"\u201cZen":[19],"4\u201d":[20],"EPYC\u2122":[21],"cores":[22],"and":[23,45,55,67,86,114,145],"third":[24],"generation":[25],"CDNA":[26],"\u2122":[27],"compute":[28],"units.":[29],"A":[30],"single":[31],"space":[33],"offers":[34],"several":[35],"advantages:":[36],"i)":[37],"it":[38,50],"eliminates":[39],"need":[41],"for":[42,131],"replication":[44],"costly":[46],"transfers,":[48],"ii)":[49],"substantially":[51],"simplifies":[52],"application":[53,152],"development":[54],"allows":[56],"an":[57,127],"incremental":[58],"acceleration":[59],"of":[60,106,147],"applications,":[61],"iii)":[62],"easy":[64],"to":[65,119,141],"maintain,":[66],"iv)":[68],"its":[69],"potential":[70],"can":[71,91],"be":[72,92],"well":[73],"realized":[74],"via":[75],"abstractions":[77],"in":[78,94],"OpenMP\u00ae":[80],"5.2":[81],"standard,":[82],"where":[83],"host":[85],"device":[88],"environments":[90],"unified":[93,112],"a":[95,104,138,149],"more":[96],"performant":[97],"way.":[98],"In":[99],"this":[100],"article,":[101],"we":[102],"provide":[103],"blueprint":[105],"APU":[108],"programming":[109],"model":[110],"leveraging":[111],"highlight":[115],"key":[116],"distinctions":[117],"compared":[118],"conventional":[121],"approach":[122],"discrete":[124],"GPUs.":[125],"OpenFOAM\u00ae,":[126],"open-source":[128],"C++":[129],"library":[130],"computational":[132],"fluid":[133],"dynamics,":[134],"presented":[136],"as":[137],"case":[139],"study":[140],"emphasize":[142],"flexibility":[144],"ease":[146],"offloading":[148],"full-scale":[150],"production-ready":[151],"on":[153],"MI300":[154],"APUs":[155],"using":[156],"directive-based":[157],"OpenMP":[158],"programming.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
