Organisation: |
Inria Grenoble Rhône-Alpes and LIG, Grenoble (FRANCE)
|
---|---|
Functionality: |
Support for Interactive Probabilistic Chains
|
Tools used: |
CADP (Construction and Analysis of Distributed Processes)
|
Period: |
2009
|
Description: |
Interactive Probabilistic Chains (IPCs) are an approach to performance
evaluation inspired by Interactive Markov Chains, but using
probabilities instead of stochastic distributions and a central clock
governing all delays. This has the advantage of enabling to combine
probabilistic/stochastic information (e.g., the rates at which
applications produce and consume messages) with precise timing
information (e.g., memory access time). The semantics of IPCs is
defined by a structured operational semantics for standard process
algebra operators (sequential and parallel composition,
nondeterministic choice, etc.), and probabilistic branching
bisimulation has been proven to be a congruence for the parallel
composition of IPCs.
|
Conclusions: |
Taking advantage of the open architecture of CADP, a tool chain
(11,600 lines of C code) has been developed and experimented on
several examples of a streaming system-on-chip architecture.
|
Publications: |
[Coste-Hermanns-Lantreibecq-Serwe-09]
Nicolas Coste, Holger Hermanns, Etienne Lantreibecq, and Wendelin Serwe
Available on-line at: http://cadp.inria.fr/publications/Coste-Hermanns-Lantreibecq-Serwe-09.html [Coste-10] Nicolas Coste. "Towards Performance Prediction of Compositional Models in GALS Designs". Thèse de doctorat en informatique de l'Université de Grenoble, June 2010. Available on-line at: http://cadp.inria.fr/publications/Coste-10.html |
Contact: | Inria Grenoble Rhône Alpes / VASY project-team 655, avenue de l'Europe 38330 Montbonnot FRANCE E-mail: Wendelin.Serwe@inria.fr |
Further remarks: | This tool, amongst others, is described on the CADP Web site: http://cadp.inria.fr/software |