Performance Estimation for Many-core Processor in Model-Based Development

Recently, embedded systems such as automotive applications, have become large and more complicated. In addition, the use of Model-Based Development (MBD) such as MATLAB/Simulink for embedded systems becomes increasingly common. Various processors used in embedded systems have evolved, and many-core processors have appeared. Many-core processors are high performance and low consumption, and is beginning to be introduced in embedded systems that require sufficient computational resources such as self-driving systems. Nowadays, software developers should select actual optimum processors that meet the target performance. However, examining and considering a large number of actual processors are not efficient. Relative to these trends, a tool that can easily convey hardware information to the software is now available and is expected to be used in parallelizing compilers, parallelizing tools, and others. In this paper, we utilized such tools, and estimated the software performance at the instruction level. We also evaluated the performance result, such as the instruction set of the many-core processors and influence of contention.