Optimization Methods of Multi-Core Embedded System

Abstract

With the development of the Internet of everything technology, embedded system has become one of the most common computing systems. Embedded system has high portability, but there are often stronger limitations in energy consumption, real-time and so on. In this work, have improved some traditional optimization algorithms, and finally get a task scheduling sequence, which can reduce the total execution time and cost of the task. Firstly, the multi-module division is used to divide multiple tasks into different modules, improve the classical Kernighan-Lin (KL) algorithm and clustering algorithm implement this process. Second, this paper invokes a series of algorithms to calculate the priority value of the task. Finally, this paper call two multi-core scheduling algorithms to schedule the tasks within each module to the Central Processing Unit (CPU) in the module. The proposed algorithm is implemented in this paper. With directed acyclic graph as input, the improvement effect of the algorithm and the direct advantages and disadvantages of different algorithms are evaluated with different task quantity.