Scenario-Aware Program Specialization for Timing Predictability

The successful application of static program analysis strongly depends on flow facts a such as loop bounds, control-flow constraints, and operating modes. This problem heavily affects the design real-time systems, since analyses are prerequisite to determine timing behavior program. For example, this becomes obvious in worst-case execution time (WCET) analysis, which is often infeasible without user-annotated facts. Moreover, many simulation approaches use statically derived timings partial paths reduce overhead. Annotating binary or source level either error-prone tedious, requires specialized compilers that can transform source-level annotations along with during optimization. To overcome these obstacles, so-called scenarios be used. Scenarios design-time methodology describe set possible system parameters, image resolutions, modes, application-dependent information described by scenario unknown general but known constant for specific system. In article, 1 we present scenario-aware specialization improve predictability. provide an implementation embedded software written C/C++. We show effectiveness our approach evaluating its impact WCET using almost all TACLeBench–achieving average reduction 31%. addition, thorough qualitative evaluation-based comparison closely related work, well two case studies.