Improving the configuration of the predictable ACDC data cache for real-time systems

Segarra, J. (Universidad de Zaragoza) ; Marti-Campoy, A.

Resumen: In real-time systems, analyzing the worst-case execution time (WCET) of a task in the presence of data caches is hard. The ACDC is a data cache that provides predictability, facilitating WCET analysis. It works by granting data cache replacement permission to specific load/store instructions. Nonetheless, knowing how to select these instructions to minimize the WCET, i.e., configuring the ACDC, is not trivial. In this paper, we propose four new methods to configure the ACDC, and compare them with existing methods. Unlike those in previous studies, our proposed methods provide specific ACDC configurations for the different phases of a given task, instead of a single ACDC configuration per task. We evaluate the WCET bounds obtained when using different ACDC configuration methods on the TACLeBench benchmark suite. Our results show that the most complex benchmarks work better with multiple-content configurations, which indicates that realistic tasks may also benefit from this kind of configuration. The methods proposed in this study improve the WCET in more than 60% of cases, with an average WCET improvement of nearly 5% and up to 50% in some cases.

Idioma: Inglés

DOI: 10.1109/ACCESS.2022.3230068

Año: 2022

Publicado en: IEEE Access 10 (2022), 132708-132724
ISSN: 2169-3536

Factor impacto JCR: 3.9 (2022)

Categ. JCR: COMPUTER SCIENCE, INFORMATION SYSTEMS rank: 73 / 158 = 0.462 (2022) - Q2 - T2
Categ. JCR: TELECOMMUNICATIONS rank: 41 / 88 = 0.466 (2022) - Q2 - T2
Categ. JCR: ENGINEERING, ELECTRICAL & ELECTRONIC rank: 100 / 274 = 0.365 (2022) - Q2 - T2

Factor impacto CITESCORE: 9.0 - Engineering (Q1) - Computer Science (Q1) - Materials Science (Q1)

Factor impacto SCIMAGO: 0.926 - Computer Science (miscellaneous) (Q1) - Materials Science (miscellaneous) (Q1) - Engineering (miscellaneous) (Q1)

Financiación: info:eu-repo/grantAgreement/ES/AEI/PID2019-105660RB-C21-AEI-10.13039-501100011033
Financiación: info:eu-repo/grantAgreement/ES/AEI/PID2020-117713RB-I00
Financiación: info:eu-repo/grantAgreement/ES/DGA-ESF/T58-20R

Tipo y forma: Artículo (Versión definitiva)

Área (Departamento): Área Arquit.Tecnología Comput. (Dpto. Informát.Ingenie.Sistms.)