Parallel Task Processing on a Multicore Platform in a PC-based Control System for Parallel Kinematics
Parallel Task Processing on a Multicore Platform in a PC-based Control System for Parallel Kinematics
复制标题
基于 PC 的并联运动控制系统中多核平台上的并行任务处理
DOI：
--
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
H. Michalik
中科院分区：
文献类型：
--
作者：
Yannick Dadji;J. Maass;H. Michalik
多核平台是具有一个物理处理器芯片的平台，该物理处理器芯片具有经由芯片级总线互连的多个核。由于它们通过并发提供更大的计算能力，提供更大的系统密度，多核平台提供了最佳的资格，以解决基于PC的控制系统中遇到的性能瓶颈，并行运动机器人与重CPU负载。重载控制任务由新的控制方法产生，包括奇异性预测，结构控制算法，视觉数据集成和类似任务等功能。在本文中，我们介绍了并行任务调度扩展的通信架构专门为开发基于PC的控制并联运动学。调度是专门为多核平台上的处理而设计的。它打破了机器人控制周期的串行任务处理，并扩展了并行任务处理路径，以提高整体控制性能。
Multicore platforms are such that have one physical processor chip with multiple cores interconnected via a chip level bus. Because they deliver a greater computing power through concurrency, offer greater system density multicore platforms provide best qualifications to address the performance bottleneck encountered in PC-based control systems for parallel kinematic robots with heavy CPU-load. Heavy load control tasks are generated by new control approaches that include features like singularity prediction, structure control algorithms, vision data integration and similar tasks. In this paper we introduce the parallel task scheduling extension of a communication architecture specially tailored for the development of PC-based control of parallel kinematics. The Scheduling is specially designed for the processing on a multicore platform. It breaks down the serial task processing of the robot control cycle and extends it with parallel task processing paths in order to enhance the overall control performance.