Evaluating performance and power of object-oriented vs. procedural programming in embedded processors

The development of high-performance and low power portable devices relies on both the underlying hardware architecture and technology as well as on the application software that executes on embedded processor cores. It has been extensively pointed out that the increasing complexity and decreasing time-to-market of embedded software can only be confronted by the use of modular and reusable code, which forces software designers to use objected oriented programming languages such as C++. However, the object-oriented approach is known to introduce a significant performance penalty compared to classical procedural programming. In this paper, the object oriented programming style is evaluated in terms of both performance and power for embedded applications. A set of benchmark kernels is compiled and executed on an embedded processor simulator, while the results are fed to instruction level and memory power models to estimate the power consumption of each system component for both programming styles.