Compiler support for software-based cache partitioning
LCTES '95 Proceedings of the ACM SIGPLAN 1995 workshop on Languages, compilers, & tools for real-time systems
Application-specific memory management for embedded systems using software-controlled caches
Proceedings of the 37th Annual Design Automation Conference
A Dynamic Programming Algorithm for Cache Memory Partitioning for Real-Time Systems
IEEE Transactions on Computers
Data cache locking for higher program predictability
SIGMETRICS '03 Proceedings of the 2003 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
OS-Controlled Cache Predictability for Real-Time Systems
RTAS '97 Proceedings of the 3rd IEEE Real-Time Technology and Applications Symposium (RTAS '97)
Low-Complexity Algorithms for Static Cache Locking in Multitasking Hard Real-Time Systems
RTSS '02 Proceedings of the 23rd IEEE Real-Time Systems Symposium
Cache Optimization for Memory-Resident Decision Support Commercial Workloads
ICCD '99 Proceedings of the 1999 IEEE International Conference on Computer Design
A New Memory Monitoring Scheme for Memory-Aware Scheduling and Partitioning
HPCA '02 Proceedings of the 8th International Symposium on High-Performance Computer Architecture
Data Caches in Multitasking Hard Real-Time Systems
RTSS '03 Proceedings of the 24th IEEE International Real-Time Systems Symposium
Dynamic Partitioning of Shared Cache Memory
The Journal of Supercomputing
Data Windows: A Data-Centric Approach for Query Execution in Memory-Resident Databases
Proceedings of the conference on Design, automation and test in Europe - Volume 2
Industrial machinery optimization and maintenance system via world wide web
WSEAS Transactions on Computers
| Hi-index | 0.00 |
Embedded real-time databases become a basic part of the embedded systems in many using environments. Caches are used for reducing the gap between processor and off-chip memory. But caches introduce unpredictability in general real-time systems. Although several cache partitioning approaches have been purposed to tackle this problem, there is no scheme designed for real-time database system up to now. In this paper, we present a data centered cache partitioning approach that allows different tasks to have a shared locking partition in cache. The hard real-time tasks will have their own partitions and thus they can perform high predictability. At the same time, a shared non-locking partition is reserved for the soft real-time tasks. In this way we can target performance improvements based on the data that are frequently used by many tasks in the system. Our experiment results show that the miss rate can be reduced by about 10%∼18% compared with that of a statically partitioned cache and by about 24%∼40% compared with a dynamic cache using LRU replacement policy.