{"id":"https://openalex.org/W7148604364","doi":"https://doi.org/10.1109/hipcw66559.2025.00110","title":"Performance Characterization of Data Transfer and Allocation Strategies on AMD MI300A APUs: Early Experiences","display_name":"Performance Characterization of Data Transfer and Allocation Strategies on AMD MI300A APUs: Early Experiences","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7148604364","doi":"https://doi.org/10.1109/hipcw66559.2025.00110"},"language":null,"primary_location":{"id":"doi:10.1109/hipcw66559.2025.00110","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipcw66559.2025.00110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 32nd International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW)","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/A5071358621","display_name":"Goutham Kalikrishna Reddy Kuncham","orcid":"https://orcid.org/0000-0003-2112-4769"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Goutham Kalikrishna Reddy Kuncham","raw_affiliation_strings":["The Ohio State University,Department of Computer Science and Engineering,Columbus,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,Columbus,USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029253472","display_name":"Siyuan Zhang","orcid":"https://orcid.org/0000-0001-6888-7793"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siyuan Zhang","raw_affiliation_strings":["The Ohio State University,Department of Computer Science and Engineering,Columbus,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,Columbus,USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103171233","display_name":"Bharath Ramesh","orcid":"https://orcid.org/0000-0002-6430-8587"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bharath Ramesh","raw_affiliation_strings":["The Ohio State University,Department of Computer Science and Engineering,Columbus,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,Columbus,USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055205226","display_name":"Kaushik Kandadi Suresh","orcid":"https://orcid.org/0000-0002-3705-2387"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaushik Kandadi Suresh","raw_affiliation_strings":["The Ohio State University,Department of Computer Science and Engineering,Columbus,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,Columbus,USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132795274","display_name":"Dhabaleswar K. Panda","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhabaleswar K. Panda","raw_affiliation_strings":["The Ohio State University,Department of Computer Science and Engineering,Columbus,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,Columbus,USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69336248,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"311","last_page":"312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.2215999960899353,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.2215999960899353,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.20669999718666077,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.11969999969005585,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-transmission","display_name":"Data transmission","score":0.38280001282691956},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.36230000853538513},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.3165000081062317},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.28870001435279846},{"id":"https://openalex.org/keywords/characterization","display_name":"Characterization (materials science)","score":0.2793999910354614},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2766999900341034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.550000011920929},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3172000050544739},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3061999976634979},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C2780841128","wikidata":"https://www.wikidata.org/wiki/Q5073781","display_name":"Characterization (materials science)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hipcw66559.2025.00110","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipcw66559.2025.00110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 32nd International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W3015594417","https://openalex.org/W4289656775","https://openalex.org/W4289827853","https://openalex.org/W4396814805","https://openalex.org/W4401211711","https://openalex.org/W4406157579","https://openalex.org/W4410510709"],"related_works":[],"abstract_inverted_index":{"AMD":[0],"MI300A":[1],"APU,":[2],"the":[3,20,73],"first":[4],"data":[5,25,43,62],"center-class":[6],"APU":[7],"with":[8],"a":[9,51],"unified":[10],"HBM3":[11],"memory":[12,32,40,56],"pool":[13],"for":[14,81,96],"both":[15],"CPU":[16],"and":[17,42,61,69,79,84,98],"GPU,":[18],"offers":[19],"potential":[21],"to":[22,90],"bypass":[23],"traditional":[24],"copy":[26],"bottlenecks.":[27],"While":[28],"this":[29,47],"design":[30],"simplifies":[31],"sharing,":[33],"it":[34],"introduces":[35],"challenges":[36],"in":[37],"determining":[38],"optimal":[39],"allocation":[41,57],"transfer":[44,63],"strategies.":[45],"In":[46],"paper,":[48],"we":[49],"present":[50],"comprehensive":[52],"performance":[53],"characterization":[54],"of":[55],"(Malloc":[58],"vs.":[59],"hipMalloc)":[60],"methods":[64],"(CPU-based":[65],"memcpy,":[66],"GPU-driven":[67],"hipMemcpy,":[68],"kernel-based":[70],"copies)":[71],"on":[72],"MI300A.":[74],"We":[75],"systematically":[76],"report":[77],"bandwidth":[78],"latency":[80],"intra-APU,":[82],"inter-APU,":[83],"inter-node":[85],"scenarios,":[86],"offering":[87],"actionable":[88],"insights":[89],"help":[91],"developers":[92],"fully":[93],"leverage":[94],"APUs":[95],"HPC":[97],"AI":[99],"workloads.":[100]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-04-03T00:00:00"}