{"id":"https://openalex.org/W4410342870","doi":"https://doi.org/10.1109/access.2025.3569533","title":"Memory Prefetching Evaluation of Scientific Applications on a Modern HPC Arm-Based Processor","display_name":"Memory Prefetching Evaluation of Scientific Applications on a Modern HPC Arm-Based Processor","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4410342870","doi":"https://doi.org/10.1109/access.2025.3569533"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3569533","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3569533","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3569533","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005324895","display_name":"Nam Ho","orcid":"https://orcid.org/0000-0002-6973-4120"},"institutions":[{"id":"https://openalex.org/I2799978770","display_name":"X-Fab (Germany)","ror":"https://ror.org/030bh9196","country_code":"DE","type":"company","lineage":["https://openalex.org/I2799978770"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Nam Ho","raw_affiliation_strings":["Jülich Supercomputing Centre, Institute for Advanced Simulation, Forschungszentrum Jülich GmbH, Jülich, Germany","Institute for Advanced Simulation, Jülich Supercomputing Centre, Forschungszentrum Jülich GmbH, Jülich, Germany"],"affiliations":[{"raw_affiliation_string":"Jülich Supercomputing Centre, Institute for Advanced Simulation, Forschungszentrum Jülich GmbH, Jülich, Germany","institution_ids":["https://openalex.org/I2799978770"]},{"raw_affiliation_string":"Institute for Advanced Simulation, Jülich Supercomputing Centre, Forschungszentrum Jülich GmbH, Jülich, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042151208","display_name":"Carlos Falquez","orcid":"https://orcid.org/0000-0003-0382-7743"},"institutions":[{"id":"https://openalex.org/I2799978770","display_name":"X-Fab (Germany)","ror":"https://ror.org/030bh9196","country_code":"DE","type":"company","lineage":["https://openalex.org/I2799978770"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Carlos Falquez","raw_affiliation_strings":["Jülich Supercomputing Centre, Institute for Advanced Simulation, Forschungszentrum Jülich GmbH, Jülich, Germany","Institute for Advanced Simulation, Jülich Supercomputing Centre, Forschungszentrum Jülich GmbH, Jülich, Germany"],"affiliations":[{"raw_affiliation_string":"Jülich Supercomputing Centre, Institute for Advanced Simulation, Forschungszentrum Jülich GmbH, Jülich, Germany","institution_ids":["https://openalex.org/I2799978770"]},{"raw_affiliation_string":"Institute for Advanced Simulation, Jülich Supercomputing Centre, Forschungszentrum Jülich GmbH, Jülich, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018708711","display_name":"Antoni Portero","orcid":"https://orcid.org/0000-0003-1319-6404"},"institutions":[{"id":"https://openalex.org/I2799978770","display_name":"X-Fab (Germany)","ror":"https://ror.org/030bh9196","country_code":"DE","type":"company","lineage":["https://openalex.org/I2799978770"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Antoni Portero","raw_affiliation_strings":["Jülich Supercomputing Centre, Institute for Advanced Simulation, Forschungszentrum Jülich GmbH, Jülich, Germany","Institute for Advanced Simulation, Jülich Supercomputing Centre, Forschungszentrum Jülich GmbH, Jülich, Germany"],"affiliations":[{"raw_affiliation_string":"Jülich Supercomputing Centre, Institute for Advanced Simulation, Forschungszentrum Jülich GmbH, Jülich, Germany","institution_ids":["https://openalex.org/I2799978770"]},{"raw_affiliation_string":"Institute for Advanced Simulation, Jülich Supercomputing Centre, Forschungszentrum Jülich GmbH, Jülich, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069177753","display_name":"Estela Suarez","orcid":"https://orcid.org/0000-0003-0748-7264"},"institutions":[{"id":"https://openalex.org/I2799978770","display_name":"X-Fab (Germany)","ror":"https://ror.org/030bh9196","country_code":"DE","type":"company","lineage":["https://openalex.org/I2799978770"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Estela Suarez","raw_affiliation_strings":["Jülich Supercomputing Centre, Institute for Advanced Simulation, Forschungszentrum Jülich GmbH, Jülich, Germany","Institute for Advanced Simulation, Jülich Supercomputing Centre, Forschungszentrum Jülich GmbH, Jülich, Germany"],"affiliations":[{"raw_affiliation_string":"Jülich Supercomputing Centre, Institute for Advanced Simulation, Forschungszentrum Jülich GmbH, Jülich, Germany","institution_ids":["https://openalex.org/I2799978770"]},{"raw_affiliation_string":"Institute for Advanced Simulation, Jülich Supercomputing Centre, Forschungszentrum Jülich GmbH, Jülich, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076651122","display_name":"D. Pleiter","orcid":"https://orcid.org/0000-0001-7296-7817"},"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":"Dirk Pleiter","raw_affiliation_strings":["Division of Computational Science and Technology, EECS, KTH Royal Institute of Technology, Stockholm, Sweden","PDC Center for High Performance Computing, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Division of Computational Science and Technology, EECS, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"PDC Center for High Performance Computing, 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/A5005324895"],"corresponding_institution_ids":["https://openalex.org/I2799978770"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10769472,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"85898","last_page":"85926"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9617000222206116,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9617000222206116,"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":0.9584000110626221,"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":0.9477999806404114,"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":0.8275492191314697},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5677950382232666},{"id":"https://openalex.org/keywords/random-access-memory","display_name":"Random access memory","score":0.46224215626716614},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4584377408027649},{"id":"https://openalex.org/keywords/arm-architecture","display_name":"ARM architecture","score":0.4309096038341522},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.42921769618988037},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3830224871635437},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2465038001537323}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8275492191314697},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5677950382232666},{"id":"https://openalex.org/C2994168587","wikidata":"https://www.wikidata.org/wiki/Q5295","display_name":"Random access memory","level":2,"score":0.46224215626716614},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4584377408027649},{"id":"https://openalex.org/C26771161","wikidata":"https://www.wikidata.org/wiki/Q16980","display_name":"ARM architecture","level":2,"score":0.4309096038341522},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.42921769618988037},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3830224871635437},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2465038001537323}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/access.2025.3569533","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3569533","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/e4ac9bd9-97e2-4c07-976c-c58a8ef68f0b","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/e4ac9bd9-97e2-4c07-976c-c58a8ef68f0b","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ho, N, Falquez, C, Portero, A, Suarez, E & Pleiter, D 2025, 'Memory Prefetching Evaluation of Scientific Applications on a Modern HPC Arm-Based Processor', IEEE Access, vol. 13, pp. 85898-85926. https://doi.org/10.1109/ACCESS.2025.3569533","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:doaj.org/article:2defa946a8ac4e198d07381cb1730379","is_oa":true,"landing_page_url":"https://doaj.org/article/2defa946a8ac4e198d07381cb1730379","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 85898-85926 (2025)","raw_type":"article"},{"id":"pmh:oai:pure.rug.nl:openaire/e4ac9bd9-97e2-4c07-976c-c58a8ef68f0b","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/e4ac9bd9-97e2-4c07-976c-c58a8ef68f0b","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ho, N, Falquez, C, Portero, A, Suarez, E & Pleiter, D 2025, 'Memory Prefetching Evaluation of Scientific Applications on a Modern HPC Arm-Based Processor', IEEE Access, vol. 13, pp. 85898-85926. https://doi.org/10.1109/ACCESS.2025.3569533","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3569533","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3569533","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W196759981","https://openalex.org/W1588915715","https://openalex.org/W1985210871","https://openalex.org/W1987873989","https://openalex.org/W2000041758","https://openalex.org/W2001420671","https://openalex.org/W2010128395","https://openalex.org/W2018689653","https://openalex.org/W2030812654","https://openalex.org/W2036162037","https://openalex.org/W2036514477","https://openalex.org/W2041517833","https://openalex.org/W2071249960","https://openalex.org/W2076211048","https://openalex.org/W2097385643","https://openalex.org/W2101511474","https://openalex.org/W2105686649","https://openalex.org/W2109341366","https://openalex.org/W2121288477","https://openalex.org/W2125305952","https://openalex.org/W2147657366","https://openalex.org/W2156803948","https://openalex.org/W2165113127","https://openalex.org/W2166620913","https://openalex.org/W2234355962","https://openalex.org/W2234679013","https://openalex.org/W2281928997","https://openalex.org/W2302754089","https://openalex.org/W2310426546","https://openalex.org/W2329976284","https://openalex.org/W2416944327","https://openalex.org/W2537450429","https://openalex.org/W2613264175","https://openalex.org/W2735601364","https://openalex.org/W2790721814","https://openalex.org/W2795232275","https://openalex.org/W2898679695","https://openalex.org/W2899156542","https://openalex.org/W2951689436","https://openalex.org/W3012303953","https://openalex.org/W3095952171","https://openalex.org/W3124943311","https://openalex.org/W3126960560","https://openalex.org/W3147011727","https://openalex.org/W3153963463","https://openalex.org/W3196818429","https://openalex.org/W4205662846","https://openalex.org/W4241590855","https://openalex.org/W4247249462","https://openalex.org/W4255807648","https://openalex.org/W4292169167","https://openalex.org/W4387064022","https://openalex.org/W4405348520","https://openalex.org/W6663494537","https://openalex.org/W6749259350","https://openalex.org/W6779824479"],"related_works":["https://openalex.org/W2418291489","https://openalex.org/W2937608115","https://openalex.org/W3096519538","https://openalex.org/W2744747300","https://openalex.org/W4241166160","https://openalex.org/W2068121105","https://openalex.org/W1700025863","https://openalex.org/W4251287623","https://openalex.org/W2055184282","https://openalex.org/W4254641500"],"abstract_inverted_index":{"Memory":[0],"prefetching":[1,48,177],"is":[2],"a":[3,119,142,153,162,175,192],"well-known":[4],"technique":[5],"for":[6,50],"mitigating":[7],"the":[8,57,65,72,78,111,114,196],"negative":[9],"impact":[10,66,73],"of":[11,59,67,74,106,113,145,195],"memory":[12,16,27,89,107,171,209],"access":[13,90,108,123],"latencies":[14],"on":[15,77,180,199],"bandwidth.":[17],"This":[18,69,129],"problem":[19],"has":[20,42],"become":[21],"more":[22],"pressing":[23],"as":[24,161],"improvements":[25],"in":[26,35],"bandwidth":[28,170],"have":[29],"not":[30],"kept":[31],"pace":[32],"with":[33],"increases":[34],"computational":[36],"power.":[37],"While":[38],"much":[39],"existing":[40],"work":[41],"been":[43],"devoted":[44],"to":[45,62,208],"finding":[46],"appropriate":[47,115],"techniques":[49],"specific":[51],"workloads,":[52],"few":[53],"provide":[54],"insight":[55],"into":[56],"behavior":[58],"scientific":[60],"applications":[61,197],"better":[63,120],"understand":[64],"prefetchers.":[68],"paper":[70],"investigates":[71],"hardware":[75,163],"prefetchers":[76,140],"latest":[79],"Arm-based":[80],"high-end":[81],"processor":[82,160],"architectures.":[83],"In":[84],"this":[85],"work,":[86],"we":[87],"investigate":[88],"patterns":[91,109],"by":[92,168],"analyzing":[93],"locality":[94],"properties":[95,125],"and":[96,99,117,126,138,185],"visualizing":[97],"delta":[98],"repetitive":[100],"address":[101],"patterns.":[102],"A":[103],"deeper":[104],"understanding":[105],"allows":[110],"use":[112],"prefetcher":[116,127],"reaching":[118],"correlation":[121],"between":[122],"pattern":[124],"performance.":[128,210],"can":[130],"guide":[131],"future":[132],"co-design":[133],"efforts.":[134],"We":[135,173],"evaluated":[136],"traditional":[137],"innovative":[139],"using":[141,156],"gem5-based":[143],"model":[144,151],"Arm":[146],"Neoverse":[147],"V1":[148],"cores.":[149],"The":[150],"features":[152],"16-core":[154],"architecture,":[155],"Amazon\u2019s":[157],"Graviton":[158],"3":[159],"reference,":[164],"but":[165],"substituting":[166],"DDR5":[167],"high":[169],"(HBM2).":[172],"performed":[174],"detailed":[176],"evaluation":[178],"focusing":[179],"stencil,":[181],"sparse":[182],"matrix-vector":[183],"multiplication,":[184],"Breadth-First":[186],"Search":[187],"kernels.":[188],"These":[189],"kernels":[190],"represent":[191],"broad":[193],"range":[194],"running":[198],"today\u2019s":[200],"High-Performance":[201],"Computing":[202],"(HPC)":[203],"systems,":[204],"which":[205],"are":[206],"sensitive":[207]},"counts_by_year":[],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}