A Code Policy Guaranteeing Fully Automated Path Analysis

Abstract

Calculating the worst-case execution time (WCET) of real-time tasks is still a tedious job. Programmers are required to provide additional information on the program flow, analyzing subtle, context dependent loop bounds manually. In this paper, we propose to restrict written and generated code to the class of programs with input-data independent loop counters. The proposed policy builds on the ideas of single-path code, but only requires partial input-data independence. It is always possible to find precise loop bounds for these programs, using an efficient variant of abstract execution. The systematic construction of tasks following the policy is facilitated by embedding knowledge on input-data dependence in function interfaces and types. Several algorithms and benchmarks are analyzed to show that this restriction is indeed a good candidate for removing the need for manual annotations.