Publication: TCOR: A Tile Cache with Optimal Replacement
| dc.contributor.author | Joseph, D. | |
| dc.contributor.author | Aragón, J.L. | |
| dc.contributor.author | Parcerisa, J.M. | |
| dc.contributor.author | González, A, | |
| dc.contributor.department | Ingeniería y Tecnología de Computadores | |
| dc.date.accessioned | 2024-01-31T17:13:39Z | |
| dc.date.available | 2024-01-31T17:13:39Z | |
| dc.date.issued | 2022-04-06 | |
| dc.description.abstract | Cache Replacement Policies are known to have an important impact on hit rates. The OPT replacement policy [27] has been formally proven as optimal for minimizing misses. Due to its need to look far ahead for future memory accesses, it is often reduced to a yardstick for measuring the efficacy of other practical caches. In this paper, we bring the OPT to life, in architectures for mobile GPUs, for which energy efficiency is of great consequence. We also mold other factors in the memory hierarchy to enhance its impact. The end results are a 13.8% decrease in the memory hierarchy energy consumption and an increased throughput in the Tiling Engine. We also observe a 5.5% decrease in the total GPU energy and a 3.7% increase in frames per second (FPS). | es |
| dc.format | application/pdf | es |
| dc.format.extent | 14 | es |
| dc.identifier.citation | Proc. of the 28th IEEE Int. Symposium on High-Performance Computer Architecture (HPCA), Seoul, South Korea, pp. 662-675, ISBN: 978-1-6654-2027-3, Abril 2022 | |
| dc.identifier.doi | https://doi.org/10.1109/HPCA53966.2022.00055 | |
| dc.identifier.eissn | 978-1-6654-2027-3 | |
| dc.identifier.uri | http://hdl.handle.net/10201/138323 | |
| dc.language | eng | es |
| dc.publisher | IEEE | es |
| dc.relation | TÍTULO PROYECTO: "CoCoUnit: An Energy-Efficient Processing Unit for Cognitive Computing" Código: Grant agreement ID 833057 Organismo financiador: European Union, Program EXCELLENT SCIENCE - European Research Council (ERC) Advanced Grant TÍTULO PROYECTO: "Arquitecturas de Dominio Específico para Sistemas de Computación Energéticamente Eficientes" Código: PID2020-113172RB-I00 Organismo financiador: Agencia Estatal de Investigación, Ministerio de Ciencia e Innovación | es |
| dc.relation.ispartof | 28th IEEE Int. Symposium on High-Performance Computer Architecture (HPCA), Seoul, South Korea, Abril 2022 | es |
| dc.relation.requires | https://doi.org/10.1109/HPCA53966.2022.00055 | es |
| dc.rights | info:eu-repo/semantics/openAccess | es |
| dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 Internacional | * |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
| dc.subject | GPU | es |
| dc.subject | Caches | es |
| dc.subject | Cache Replacement | es |
| dc.subject | OPT | es |
| dc.subject | Belady | es |
| dc.subject | Energy-efficient | es |
| dc.subject | Pipelines | es |
| dc.subject | Memory management | es |
| dc.subject | Memory architecture | es |
| dc.title | TCOR: A Tile Cache with Optimal Replacement | es |
| dc.type | info:eu-repo/semantics/lecture | es |
| dc.type | info:eu-repo/semantics/lecture | es |
| dspace.entity.type | Publication | es |
Collections
Este ítem está sujeto a una licencia Creative Commons. http://creativecommons.org/licenses/by-nc-nd/4.0/