EPC: Extended Path Coverage for Measurement-Based Probabilistic Timing Analysis

Abstract

Abstract-Measurement-based probabilistic timing analysis (MBPTA) computes trustworthy upper bounds to the execution time of software programs. MBPTA has the connotation, typical of measurement-based techniques, that the bounds computed with it only relate to what is observed in actual program traversals, which may not include the effective worst-case phenomena. To overcome this limitation, we propose Extended Path Coverage (EPC), a novel technique that allows extending the representativeness of the bounds computed by MBPTA. We make the observation data probabilistically path-independent by modifying the probability distribution of the observed timing behaviour so as to negatively compensate for any benefits that a basic block may draw from a path leading to it. This enables the derivation of trustworthy upper bounds to the probabilistic execution time of all paths in the program, even when the user-provided input vectors do not exercise the worst-case path. Our results confirm that using MBPTA with EPC produces fully trustworthy upper bounds with competitively small overestimation in comparison to state-of-the-art MBPTA techniques.

Measurement-based cache representativeness on multipath programs

“…A more informed application of EVT to the so ware domain is advocated instead in [23], restricting EVT to using exponential tail distribution [2] on the account that it has been argued to be the most stable (and always overapproximating) distribution to model worst-case execution of real-time so ware [2,27]. A universally recognized issue in the application of EVT is related to identifying an exhaustively representative input sample [13,32,38]: our work directly responds to this challenge by synthetically deriving a path-upperbounding version of the target program and de ning the minimum number of observations to be collected on such version.…”

On uses of extreme value theory fit for industrial-quality WCET analysis

“…Representativeness of execution paths: Assuring sufficient path coverage is a widely acknowledged requirement of all timing analysis approaches based on measurements [26], [27]. In contrast with static timing analyses, the results computed by measurement-based methods hold only for the execution paths observed at analysis.…”

“…Path identification and generation of the respective input vectors remain a non-trivial problem for the end users. When PTC information is not available (or is considered unreliable), it is still possible to build a synthetic upper-bounding path [28] or use the measurements from several paths to artificially derive measurements for all unobserved paths [27].…”

“…We refer to this solution as multiplebucket application of EVT, as opposed to its single-bucket alternative. We do not consider how these paths have been selected, whether by the user or by other means [27], [28]. In this scenario, the whole MBPTA process is applied on a per-path basis to obtain individual CCDFs.…”

“…Finally, the application of EVT to model multiple paths, relating to path concerns in measurement-based analyses, has been studied in [27], [28] where methods have been proposed to increase the eventual path coverage.…”