Computer
Dynamic task binding for hardware/software reconfigurable networks
SBCCI '06 Proceedings of the 19th annual symposium on Integrated circuits and systems design
Classifier fitness based on accuracy
Evolutionary Computation
Mapping parallelism to multi-cores: a machine learning based approach
Proceedings of the 14th ACM SIGPLAN symposium on Principles and practice of parallel programming
A light-weight approach for online state classification of self-organizing parallel systems
ARCS'11 Proceedings of the 24th international conference on Architecture of computing systems
Hi-index | 0.00 |
This paper presents the use of decentralized self-organization concepts for the efficient dynamic parameterization of hardware components and the autonomic distribution of tasks in a symmetrical multi-core processor system. Using results obtained with an autonomic system on chip simulation model, we show that Learning Classifier Tables, a simplified XCS-based reinforcement learning technique optimized for a low-overhead hardware implementation and integration, achieves nearly optimal results for dynamic workload balancing during run time for a standard networking application at task level. Further investigations show the quantitative differences in optimization quality between scenarios when local and global system information is included in the classifier rules. Autonomic workload management or task repartitioning at run time relieves the software application developers from exploring this NP-hard problem during design time, and is able to react to dynamic changes in the MP-SoC operating environment.