Obstacles in worst-case execution time analysis

Abstract

The analysis of the worst-case execution time (WCET) requires detailed knowledge of the program behavior. In practice it is still not possible to obtain all needed information automatically. In this paper we present the current state of the art of WCET analysis and point to the main problems to be solved. The most eminent problem is the state problem, i.e., the precise determination of possible processor states at different program locations. The path problem refers to the fact that current tools are not able to calculate all (in)feasible paths automatically. We discuss how the main open problems manifest themselves in static and in measurement-based WCET analysis methods.