Accurate estimation of the tick length of a synchronous program is essential for efficient and predictable implementations that are devoid of timing faults. The techniques to determine the tick length statically are classified as worst case reaction time (WCRT) analysis. While a plethora of techniques exist for worst case execution time (WCET) analysis of procedural programs, there are only a handful of techniques for determining the WCRT value of synchronous programs. Most of these techniques produce overestimates and hence are unsuitable for the design of systems that are predictable while being also efficient. In this paper, we present an approach for the accurate estimation of the exact WCRT value of a synchronous program, called its tight WCRT value, using model checking. For our input specifications we have selected a synchronous C based language called PRET-C that is designed for programming Precision Timed (PRET) architectures. We then present an approach for static WCRT analysis of these programs via an intermediate format called TCCFG. This intermediate representation is then compiled to produce the input for the model checker. Experimental results that compare our approach to existing approaches demonstrate the benefits of the proposed approach. The proposed approach, while presented for PRET-C is also applicable for WCRT analysis of Esterel using simple adjustments to the generated model. The proposed approach thus paves the way for a generic approach for determining the tight WCRT value of synchronous programs at compile time. * Roop was supported by research and study leave from Auckland University and a research fellowship for experienced researchers from the Alexander von Humboldt foundation.

A large class of embedded systems is distinguished from general-purpose computing systems by the need to satisfy strict requirements on timing, often under constraints on available resources. Predictable system design is concerned with the challenge of building systems for which timing requirements can be guaranteed a priori. Perhaps paradoxically, this problem has become more difficult by the introduction of performanceenhancing architectural elements, such as caches, pipelines, and multithreading, which introduce a large degree of uncertainty and make guarantees harder to provide. The intention of this article is to summarize the current state of the art in research concerning how to build predictable yet performant systems. We suggest precise definitions for the concept of "predictability", and present predictability concerns at different abstraction levels in embedded system design. First, we consider timing predictability of processor instruction sets. Thereafter, we consider how programming languages can be equipped with predictable timing semantics, covering both a language-based approach using the synchronous programming paradigm, as well as an environment that provides timing semantics for a mainstream programming language (in this case C). We present techniques for achieving timing predictability on multicores. Finally, we discuss how to handle predictability at the level of networked embedded systems where randomly occurring errors must be considered.

No abstract

No abstract

No abstract