Autonomic Workload Management for Multi-core Processor Systems
Autonomic Workload Management for Multi-core Processor Systems
复制标题
多核处理器系统的自主工作负载管理
DOI：
--
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
A. Herkersdorf
中科院分区：
文献类型：
--
作者：
J. Zeppenfeld;A. Herkersdorf
本文提出了使用分散的自组织概念的高效动态参数化的硬件组件和自主分配的任务在一个对称的多核处理器系统。使用自主系统芯片仿真模型获得的结果，我们表明，学习分类表，一个简化的XCS为基础的强化学习技术优化的低开销硬件实现和集成，实现了接近最佳的结果，在运行时的动态工作负载平衡的标准网络应用程序在任务级。进一步的调查表明，当局部和全局系统信息包括在分类器规则的情况下，优化质量的定量差异。在运行时的自主工作负载管理或任务重新分区减轻了软件应用程序开发人员在设计时探索这个NP难问题，并且能够对MP-SoC操作环境中的动态变化做出反应。
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.