Supporting industrial use of probabilistic timing analysis with explicit argumentation

Abstract

Probabilistic Timing Analysis (PTA) in general and its measurement-based variant called MBPTA in particular have potential for mitigating the problems that impair current worstcase execution time (WCET) analysis techniques whether as in industrial practice or in state-of-the-art research. MBPTA can compute tight upper bounds on the execution time of software programs, which it expresses as probabilistic exceedance functions, without needing much information on the hardware and software internals of the system. To exploit this capability in practice, some reasoned argument must be constructed to explain why the method is suitable. This paper details our experience with the construction of such an argument, and in particular shows how the structure of the argument allows it to be easily configured for the needs of different industries.