Worst-Case-Execution-Time (WCET) analysis computes upper bounds on the execution time of a program on a given hardware platform. Abstractions employed for static timing analysis can lead to non-determinism that may require the analyzer to evaluate an exponential number of choices even for straight-line code. Pruning the search space is potentially unsafe because of "timing anomalies" where local worst-case choices may not lead to the global worst-case scenario. In this paper we present an approach towards more efficient WCET analysis that uses precomputed information to safely discard analysis states.
@InProceedings{reineke_et_al:OASIcs.WCET.2009.2289, author = {Reineke, Jan and Sen, Rathijit}, title = {{Sound and Efficient WCET Analysis in the Presence of Timing Anomalies}}, booktitle = {9th International Workshop on Worst-Case Execution Time Analysis (WCET'09)}, pages = {1--11}, series = {Open Access Series in Informatics (OASIcs)}, ISBN = {978-3-939897-14-9}, ISSN = {2190-6807}, year = {2009}, volume = {10}, editor = {Holsti, Niklas}, publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik}, address = {Dagstuhl, Germany}, URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.WCET.2009.2289}, URN = {urn:nbn:de:0030-drops-22894}, doi = {10.4230/OASIcs.WCET.2009.2289}, annote = {Keywords: WCET analysis, timing anomalies, domino effect} }
Feedback for Dagstuhl Publishing