Abstract
The problem of estimating a tight and safe Worst-Case Execution Time (WCET), needed for certification in safety-critical environment, is a challenging problem for modern embedded systems. A possible solution proposed in past years is to exploit statistical tools to obtain a probability distribution of the WCET. These probabilistic real-time analyses for WCET are, however, subject to errors, even when all the applicability hypotheses are satisfied and verified. This is caused by the uncertainties of the probabilistic-WCET distribution estimator. This article aims at improving the measurement-based probabilistic timing analysis approach providing some techniques to analyze and deal with such uncertainties. The so-called region of acceptance model based on state-of-the-art statistical test procedures is defined over the distribution space parameters. From this model, a set of strategies is derived and discussed to provide the methodology to deal with the trade-off safety/tightness of the WCET estimation. These techniques are then tested over real datasets, including industrial safety-critical applications, to show the increased value of using the proposed approach in probabilistic WCET analyses.
- J. Abella, C. Hernandez, E. Quiñones, F. J. Cazorla, P. R. Conmy, M. Azkarate-askasua, J. Perez, E. Mezzetti, and T. Vardanega. 2015. WCET analysis methods: Pitfalls and challenges on their trustworthiness. In Proceedings of the 10th IEEE International Symposium on Industrial Embedded Systems (SIES’15). IEEE, 1--10. DOI:https://doi.org/10.1109/SIES.2015.7185039Google Scholar
Cross Ref
- J. Abella, E. Quiñones, F. Wartel, T. Vardanega, and F. J. Cazorla. 2014. Heart of gold: Making the improbable happen to increase confidence in MBPTA. In Proceedings of the 26th Euromicro Conference on Real-time Systems. IEEE, 255--265. DOI:https://doi.org/10.1109/ECRTS.2014.33Google Scholar
- Kostiantyn Berezovskyi, Fabrice Guet, Luca Santinelli, Konstantinos Bletsas, and Eduardo Tovar. 2016. Measurement-based probabilistic timing analysis for graphics processor units. In Proceedings of the Architecture of Computing Systems (ARCS’16). Springer International Publishing, 223--236.Google Scholar
Digital Library
- G. Bernat, A. Colin, and S. M. Petters. 2002. WCET analysis of probabilistic hard real-time systems. In Proceedings of the 23rd IEEE Real-time Systems Symposium (RTSS’02). IEEE, 279--288. DOI:https://doi.org/10.1109/REAL.2002.1181582Google Scholar
- Francisco J. Cazorla, Leonidas Kosmidis, Enrico Mezzetti, Carles Hernandez, Jaume Abella, and Tullio Vardanega. 2019. Probabilistic worst-case timing analysis: Taxonomy and comprehensive survey. ACM Comput. Surv. 52, 1 (Feb. 2019). DOI:https://doi.org/10.1145/3301283Google Scholar
Digital Library
- Francisco J. Cazorla, Eduardo Quiñones, Tullio Vardanega, Liliana Cucu, Benoit Triquet, Guillem Bernat, Emery Berger, Jaume Abella, Franck Wartel, Michael Houston, Luca Santinelli, Leonidas Kosmidis, Code Lo, and Dorin Maxim. 2013. PROARTIS: Probabilistically analyzable real-time systems. ACM Trans. Embed. Comput. Syst. 12, 2s (May 2013). DOI:https://doi.org/10.1145/2465787.2465796Google Scholar
Digital Library
- Xavier Civit, Joan del Castillo, and Jaume Abella. 2018. A reliable statistical analysis of the best-fit distribution for high execution times. In Proceedings of the 21st Euromicro Conference on Digital System Design (DSD’18). IEEE, 727--734. DOI:https://doi.org/10.1109/DSD.2018.00012Google Scholar
Cross Ref
- Harald Cramér. 1928. On the composition of elementary errors. Scand. Actuar. J. 1928, 1 (1928), 13--74. DOI:https://doi.org/10.1080/03461238.1928.10416862Google Scholar
Cross Ref
- Sandor Csorgo and Julian J. Faraway. 1996. The exact and asymptotic distributions of Cramer-von Mises statistics. J. Roy. Stat. Soc. Series B (Methodol.) 58 (01 1996), 221--234. DOI:https://doi.org/10.2307/2346175Google Scholar
- L. Cucu-Grosjean, L. Santinelli, M. Houston, C. Lo, T. Vardanega, L. Kosmidis, J. Abella, E. Mezzetti, E. Quiñones, and F. J. Cazorla. 2012. Measurement-based probabilistic timing analysis for multi-path programs. In Proceedings of the 24th Euromicro Conference on Real-time Systems. IEEE, 91--101. DOI:https://doi.org/10.1109/ECRTS.2012.31Google Scholar
- Corentin Damman, Gregory Edison, Fabrice Guet, Eric Noulard, Luca Santinelli, and Jerome Hugues. 2016. Architectural performance analysis of FPGA synthesized LEON processors. In Proceedings of the 27th International Symposium on Rapid System Prototyping: Shortening the Path from Specification to Prototype. ACM, New York, NY, 33--40. DOI:https://doi.org/10.1145/2990299.2990306Google Scholar
Digital Library
- D. Dasari, B. Akesson, V. Nélis, M. A. Awan, and S. M. Petters. 2013. Identifying the sources of unpredictability in COTS-based multicore. In Proceedings of the International Symposium on Industrial Embedded Systems. IEEE, 39--48. DOI:https://doi.org/10.1109/SIES.2013.6601469Google Scholar
- Robert Davis and Liliana Cucu-Grosjean. 2019. A survey of probabilistic schedulability analysis techniques for real-time systems. Leibniz Trans. Embed. Syst. 6, 1 (2019), 04–1–04:53. DOI:https://doi.org/10.4230/LITES-v006-i001-a004Google Scholar
- Robert I. Davis, Alan Burns, and David Griffin. 2017. On the Meaning of pWCET Distributions and Their Use in Schedulability Analysis. Retrieved from https://www-users.cs.york.ac.uk/ robdavis/papers/RTSOPS2017pWCET.pdf.Google Scholar
- Robert I. Davis, Luca Santinelli, Sebastian Altmeyer, Claire Maiza, and Liliana Cucu-Grosjean. 2013. Analysis of probabilistic cache related pre-emption delays. In Proceedings of the 25th Euromicro Conference on Real-time Systems (ECRTS’13). IEEE, 168--179. DOI:https://doi.org/10.1109/ECRTS.2013.27Google Scholar
Digital Library
- Darinka Dentcheva and Andrzej Ruszczyński. 2003. Portfolio Optimization with Stochastic Dominance Constraints. Elsevier. DOI:https://doi.org/10.18452/8306Google Scholar
- Julien Durand, Youcef Bouchebaba, and Luca Santinelli. 2019. Statistical analysis for shared resources effects with multi-core real-time systems. In Proceedings of the 13th IEEE International Symposium on Embedded Multicore/Many-core Systems-on-chip (MCSoC’19). IEEE, 362--371. DOI:https://doi.org/10.1109/MCSoC.2019.00058Google Scholar
Cross Ref
- S. Edgar and A. Burns. 2001. Statistical analysis of WCET for scheduling. In Proceedings of the 22nd IEEE Real-time Systems Symposium (RTSS’01). IEEE, 215--224. DOI:https://doi.org/10.1109/REAL.2001.990614Google Scholar
- M. Fernandez, D. Morales, L. Kosmidis, A. Bardizbanyan, I. Broster, C. Hernandez, E. Quinones, J. Abella, F. Cazorla, P. Machado, and L. Fossati. 2017. Probabilistic timing analysis on time-randomized platforms for the space domain. In Proceedings of the Conference on Design, Automation 8 Test in Europe. ACM and IEEE, 738--739.Google Scholar
- R. A. Fisher and L. H. C. Tippett. 1928. Limiting forms of the frequency distribution of the largest or smallest member of a sample. Math. Proc. Cambr. Philos. Soc. 24, 2 (1928), 180--190. DOI:https://doi.org/10.1017/S0305004100015681Google Scholar
Cross Ref
- William Fornaciari, Giovanni Agosta, David Atienza, Carlo Brandolese, Leila Cammoun, Luca Cremona, Alessandro Cilardo, Albert Farres, José Flich, Carles Hernandez, Michal Kulchewski, Simone Libutti, José Maria Martínez, Giuseppe Massari, Ariel Oleksiak, Anna Pupykina, Federico Reghenzani, Rafael Tornero, Michele Zanella, Marina Zapater, and Davide Zoni. 2018. Reliable power and time-constraints-aware predictive management of heterogeneous exascale systems. In Proceedings of the 18th International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS’18). Association for Computing Machinery, New York, NY, 187--194. DOI:https://doi.org/10.1145/3229631.3239368Google Scholar
Digital Library
- S. Jiménez Gil, I. Bate, G. Lima, L. Santinelli, A. Gogonel, and L. Cucu-Grosjean. 2017. Open challenges for probabilistic measurement-based worst-case execution time. IEEE Embed. Syst. Lett. 9, 3 (Sept. 2017), 69--72. DOI:https://doi.org/10.1109/LES.2017.2712858Google Scholar
- B. Gnedenko. 1943. Sur La Distribution Limite Du Terme Maximum D’Une Serie Aleatoire. Ann. Math. 44, 3 (1943), 423--453. Retrieved from http://www.jstor.org/stable/1968974.Google Scholar
Cross Ref
- Fabrice Guet, Luca Santinelli, and Jerome Morio. 2017. On the representativity of execution time measurements: Studying dependence and multi-mode tasks. In Proceedings of the 17th International Workshop on Worst-case Execution Time Analysis (WCET’17). (OpenAccess Series in Informatics (OASIcs)), Jan Reineke (Ed.), Vol. 57. Schloss Dagstuhl–Leibniz-Zentrum fuer Informatik, 3:1–3:13. DOI:https://doi.org/10.4230/OASIcs.WCET.2017.3Google Scholar
- Jeffery Hansen, Scott Hissam, and Gabriel A. Moreno. 2009. Statistical-based WCET estimation and validation. In Proceedings of the 9th International Workshop on Worst-case Execution Time Analysis (WCET’09). (OpenAccess Series in Informatics (OASIcs)), Niklas Holsti (Ed.), Vol. 10. Schloss Dagstuhl–Leibniz-Zentrum fuer Informatik, 1--11. DOI:https://doi.org/10.4230/OASIcs.WCET.2009.2291Google Scholar
- Jun-Haeng Heo, Hongjoon Shin, Woosung Nam, Juseong Om, and Changsam Jeong. 2013. Approximation of modified Anderson–Darling test statistics for extreme value distributions with unknown shape parameter. J. Hydrol. 499 (2013), 41--49.Google Scholar
Cross Ref
- R. Kirner and P. Puschner. 2008. Obstacles in worst-case execution time analysis. In Proceedings of the 11th IEEE International Symposium on Object and Component-oriented Real-time Distributed Computing (ISORC’08). IEEE, 333--339. DOI:https://doi.org/10.1109/ISORC.2008.65Google Scholar
- A. Kolmogorov. 1933. Sulla determinazione empírica di uma legge di distribuzione. Inst. Ital. Attuari, Giorn.4 (1933), 83--91.Google Scholar
- L. Kosmidis, E. Quińones, J. Abella, T. Vardanega, I. Broster, and F. J. Cazorla. 2014. Measurement-based probabilistic timing analysis and its impact on processor architecture. In Proceedings of the 17th Euromicro Conference on Digital System Design. IEEE, 401--410. DOI:https://doi.org/10.1109/DSD.2014.50Google Scholar
- G. Lima, D. Dias, and E. Barros. 2016. Extreme value theory for estimating task execution time bounds: A careful look. In Proceedings of the Euromicro Conference on Real-time Systems (ECRTS’16). IEEE, 200--211. DOI:https://doi.org/10.1109/ECRTS.2016.20Google Scholar
- Frank J. Massey Jr. 1951. The Kolmogorov-Smirnov test for goodness of fit. J. Amer. Stat. Assoc. 46, 253 (1951), 68--78.Google Scholar
Cross Ref
- Daniel McFadden. 1978. Modeling the choice of residential location. Transport. Res. Rec. 1, 673 (1978), 72--77.Google Scholar
- Thomas Nolte, Meng Liu, and Bjorn Lisper. 2014. Challenges with probabilities in response-time analysis of real-time systems. In Proceedings of the 5th Real-time Scheduling Open Problems Seminar (RTSOPS’14). 3--4.Google Scholar
- Edgar Elias Osuna. 2013. Tail-restricted stochastic dominance. IMA J. Manag. Math. 24, 1 (2013), 21--44. DOI:https://doi.org/10.1093/imaman/dpr023Google Scholar
Cross Ref
- Stefan M. Petters. 2003. Comparison of trace generation methods for measurement based WCET analysis. In Proceedings of the 3rd International Workshop on Worst-case Execution Time Analysis.Google Scholar
- James P. Quirk and Rubin Saposnik. 1962. Admissibility and measurable utility functions. Rev. Econ. Studies 29, 2 (1962), 140--146. DOI:https://doi.org/10.2307/2295819Google Scholar
Cross Ref
- F. Reghenzani, G. Massari, and W. Fornaciari. 2018. chronovise: Measurement-based probabilistic timing analysis framework. J. Open Source Softw. 3, 28 (2018), 711. DOI:https://doi.org/10.21105/joss.00711Google Scholar
Cross Ref
- F. Reghenzani, G. Massari, and W. Fornaciari. 2018. The misconception of exponential tail upper-bounding in probabilistic real-time. IEEE Embed. Syst. Lett. 11, 3 (2018), 77--80. DOI:https://doi.org/10.1109/LES.2018.2889114Google Scholar
Digital Library
- F. Reghenzani, G. Massari, and W. Fornaciari. 2019. A probabilistic approach to energy-constrained mixed-criticality systems. In Proceedings of the IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED’19). IEEE/ACM, 1--6. DOI:https://doi.org/10.1109/ISLPED.2019.8824991Google Scholar
- F. Reghenzani, G. Massari, W. Fornaciari, and A. Galimberti. 2019. Probabilistic-WCET reliability: On the experimental validation of EVT hypotheses. In Proceedings of the International Conference on Omni-layer Intelligent Systems (COINS’19). ACM, New York, NY, 229--234. DOI:https://doi.org/10.1145/3312614.3312660Google Scholar
- F. Reghenzani, G. Massari, L. Santinelli, and W. Fornaciari. 2019. Statistical power estimation dataset for external validation GoF tests on EVT distribution. Data in Brief 25 (June 2019), 104071. DOI:https://doi.org/10.1016/j.dib.2019.104071Google Scholar
- Federico Reghenzani, Luca Santinelli, and William Fornaciari. 2019. Why statistical power matters for probabilistic real-time: Work-in-progress. In Proceedings of the International Conference on Embedded Software Companion (EMSOFT’19). Association for Computing Machinery, New York, NY. DOI:https://doi.org/10.1145/3349568.3351555Google Scholar
Digital Library
- Michael Thomas Rolf-Dieter Reiss. 2007. Statistical Analysis of Extreme Values with Applications to Insurance, Finance, Hydrology and Other Fields. Birkhäuser Basel. DOI:https://doi.org/10.1007/978-3-7643-7399-3Google Scholar
- L. Santinelli, F. Guet, and J. Morio. 2017. Revising measurement-based probabilistic timing analysis. In Proceedings of the IEEE Real-time and Embedded Technology and Applications Symposium (RTAS’17). IEEE, 199--208. DOI:https://doi.org/10.1109/RTAS.2017.16Google Scholar
- Luca Santinelli and Zhishan Guo. 2017. On the criticality of probabilistic worst-case execution time models. In Dependable Software Engineering. Theories, Tools, and Applications, Kim Guldstrand Larsen, Oleg Sokolsky, and Ji Wang (Eds.). Springer, 59--74.Google Scholar
- K. P. Silva, L. F. Arcaro, and R. S. d. Oliveira. 2017. On using GEV or Gumbel models when applying EVT for probabilistic WCET estimation. In Proceedings of the IEEE Real-time Systems Symposium (RTSS’17). IEEE, 220--230. DOI:https://doi.org/10.1109/RTSS.2017.00028Google Scholar
Cross Ref
- Ganghuai Wang, J. H. Lambert, and Y. Y. Haimes. 1999. Stochastic ordering of extreme value distributions. IEEE Trans. Syst. Man Cyber. Part A: Syst. Hum. 29, 6 (Nov. 1999), 696--701. DOI:https://doi.org/10.1109/3468.798077Google Scholar
- F. Wartel, L. Kosmidis, C. Lo, B. Triquet, E. Quiñones, J. Abella, A. Gogonel, A. Baldovin, E. Mezzetti, L. Cucu, T. Vardanega, and F. J. Cazorla. 2013. Measurement-based probabilistic timing analysis: Lessons from an integrated-modular avionics case study. In Proceedings of the 8th IEEE International Symposium on Industrial Embedded Systems. IEEE, 241--248. DOI:https://doi.org/10.1109/SIES.2013.6601497Google Scholar
Index Terms
Dealing with Uncertainty in pWCET Estimations
Recommendations
Probabilistic-WCET Reliability: On the experimental validation of EVT hypotheses
COINS '19: Proceedings of the International Conference on Omni-Layer Intelligent SystemsThe interest in probabilistic real-time is increasing, in response to the lack of traditional static WCET analysis methods for applications running on complex systems, like multi/many-cores and COTS platforms. However, the probabilistic theory is still ...
PWCET: Power-Aware Worst Case Execution Time Analysis
ICPPW '14: Proceedings of the 2014 43rd International Conference on Parallel Processing WorkshopsWorst case execution time (WCET) analysis is used to verify that real-time tasks on systems can be executed without violating any timing constraints. Power consumption is not considered in most of the WCET research work. However, real-time embedded ...
Response Time Analysis for Fixed-Priority Tasks with Multiple Probabilistic Parameters
RTSS '13: Proceedings of the 2013 IEEE 34th Real-Time Systems SymposiumIn this paper, we consider a probabilistic model for real-time task systems with probabilistic worst-case execution times, probabilistic minimum inter-arrival times and probabilistic deadlines. We propose an analysis computing response time ...






Comments