001028952 001__ 1028952
001028952 005__ 20240722202104.0
001028952 0247_ $$2datacite_doi$$a10.34734/FZJ-2024-04892
001028952 037__ $$aFZJ-2024-04892
001028952 041__ $$aEnglish
001028952 1001_ $$0P:(DE-Juel1)200201$$aSaglam, Berk$$b0$$eCorresponding author$$ufzj
001028952 245__ $$aHeterogeneous Memory Aware Prefetching on High Performance Arm Processors$$f - 2024-04-18
001028952 260__ $$c2024
001028952 300__ $$a142
001028952 3367_ $$2DataCite$$aOutput Types/Supervised Student Publication
001028952 3367_ $$02$$2EndNote$$aThesis
001028952 3367_ $$2BibTeX$$aMASTERSTHESIS
001028952 3367_ $$2DRIVER$$amasterThesis
001028952 3367_ $$0PUB:(DE-HGF)19$$2PUB:(DE-HGF)$$aMaster Thesis$$bmaster$$mmaster$$s1721622217_29528
001028952 3367_ $$2ORCID$$aSUPERVISED_STUDENT_PUBLICATION
001028952 502__ $$aMasterarbeit, Rheinische Friedrich-Wilhelms-Universität Bonn, 2024$$bMasterarbeit$$cRheinische Friedrich-Wilhelms-Universität Bonn$$d2024$$o2024-04-18
001028952 520__ $$aModern computing often sees up to 80% of computation time spent on data retrieval,emphasizing the importance of prefetching for enhancing CPU data delivery speeds bymoving data from slower storage to faster caches. Balancing timeliness and aggressivenessis crucial for reducing access times. Utilizing heterogeneous memory, in this contextHBM2 and DDR5, serve different roles due to their bandwidth and capacity trade-offs, underscoring the need for balanced memory management and awareness whileprefetching.This work focuses on developing prefetching strategies for heterogeneous memoryconfigurations in high-performance Arm processors, targeting a system architecturecomprising 20 cores, with 16 cores dedicated to HBM2 and 4 cores dedicated to DDR5memory. The primary objective is to reduce latency and improve system performanceby introducing two innovative optimization strategies for prefetching. These strategiesmeticulously balance timeliness and aggressiveness by adaptively tuning the prefetchdegree and distance. These strategies adapt dynamically to the specific memory type andavailable bandwidth with consideration of the prefetch accuracy, optimizing prefetchingoperations for enhanced performance and efficiency. The Prefetcher are integrated withthe L2 cache and its performance is rigorously assessed through Gem5 simulations. Theseevaluations compare the effectiveness of adaptive optimization strategies for both Streamand PC-based Stride Prefetchers, utilizing the Arm Neoverse V1 as the computationalmodel.Findings reveal adaptive prefetching is boosting system performance, notably with HBM2and DDR5 Memory, while facing memory contention on DDR5. This research advancesprefetching strategies with the understanding of heterogeneous memory, advocatingfurther exploration to enhance high-performance computing efficiency and performance.
001028952 536__ $$0G:(DE-HGF)POF4-5122$$a5122 - Future Computing & Big Data Systems (POF4-512)$$cPOF4-512$$fPOF IV$$x0
001028952 8564_ $$uhttps://juser.fz-juelich.de/record/1028952/files/Saglam_MasterThesis_Bonn_2024.pdf$$yOpenAccess
001028952 8564_ $$uhttps://juser.fz-juelich.de/record/1028952/files/Saglam_MasterThesis_Bonn_2024.gif?subformat=icon$$xicon$$yOpenAccess
001028952 8564_ $$uhttps://juser.fz-juelich.de/record/1028952/files/Saglam_MasterThesis_Bonn_2024.jpg?subformat=icon-1440$$xicon-1440$$yOpenAccess
001028952 8564_ $$uhttps://juser.fz-juelich.de/record/1028952/files/Saglam_MasterThesis_Bonn_2024.jpg?subformat=icon-180$$xicon-180$$yOpenAccess
001028952 8564_ $$uhttps://juser.fz-juelich.de/record/1028952/files/Saglam_MasterThesis_Bonn_2024.jpg?subformat=icon-640$$xicon-640$$yOpenAccess
001028952 909CO $$ooai:juser.fz-juelich.de:1028952$$popenaire$$popen_access$$pVDB$$pdriver$$pdnbdelivery
001028952 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)200201$$aForschungszentrum Jülich$$b0$$kFZJ
001028952 9131_ $$0G:(DE-HGF)POF4-512$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5122$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vSupercomputing & Big Data Infrastructures$$x0
001028952 9141_ $$y2024
001028952 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001028952 920__ $$lyes
001028952 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001028952 980__ $$amaster
001028952 980__ $$aVDB
001028952 980__ $$aUNRESTRICTED
001028952 980__ $$aI:(DE-Juel1)JSC-20090406
001028952 9801_ $$aFullTexts