Abstract
Dynamic cache reconfiguration has been widely explored for energy optimization and performance improvement for single-core systems. Cache partitioning techniques are introduced for the shared cache in multicore systems to alleviate inter-core interference. While these techniques focus only on performance and energy, they ignore vulnerability due to soft errors. In this article, we present a static profiling based algorithm to enable vulnerability-aware energy-optimization for real-time multicore systems. Our approach can efficiently search the space of cache configurations and partitioning schemes for energy optimization while task deadlines and vulnerability constraints are satisfied. A machine learning technique has been employed to minimize the static profiling time without sacrificing the accuracy of results. Our experimental results demonstrate that our approach can achieve 19.2% average energy savings compared with the base configuration, while drastically reducing the vulnerability (49.3% on average) compared to state-of-the-art techniques. Furthermore, the machine learning technique enabled more than 10x speedup in static profiling time with a negligible prediction error of 3%.
Funder
National Science Foundation
Publisher
Association for Computing Machinery (ACM)
Subject
Hardware and Architecture,Software
Reference51 articles.
1. Statistics and Machine Learning Toolbox Matlab. 2017b. MathWorks Retrieved from https://www.mathworks.com/products/statistics.html. Statistics and Machine Learning Toolbox Matlab. 2017b. MathWorks Retrieved from https://www.mathworks.com/products/statistics.html.
2. Dynamic phase-based tuning for embedded systems using phase distance mapping
3. Balancing Performance and Reliability in the Memory Hierarchy
4. The gem5 simulator
5. Computing Architectural Vulnerability Factors for Address-Based Structures
Cited by
15 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献