In a wait-free model any number of processes may crash. A process runs solo when it computes its local output without receiving any communication from other processes, either because they crashed or they are too slow. While in wait-free shared-memorymodels at most one process may run solo in an execution, any number of processes may have to run solo in an asynchronous wait-free message-passing ...

(Latency-Insensitive Design) theory was invented to deal with SoC timing closure issues, by allowing arbitrary fixed integer latencies on long global wires. Latencies are coped with using a resynchronization protocol that performs dynamic scheduling of data transportation. Functional behaviour is preserved. This dynamic scheduling is implemented using specific synchronous hardware elements: Rel...

ion : Réutilisation : Légende : SI1 SI2 SIn te l-0 04 30 49 7, v er si on 2 4 Ja n 20 10 Chapitre 3 : Concepts de base et vue métier d’un composant métier processus 82 c) Origines de la variabilité Nous distinguons deux aspects qui peuvent être à l’origine de la variabilité représentée dans des CMP. 1. Variabilité des PM : un CMP modélise des PM similaires qui peuvent être déclinés de plusieurs...

The paper presents a programming language called DSystemJ, for dynamic distributed Globally Asynchronous Locally Synchronous systems (GALS), its formal model, formal syntax and semantics, its compilation and implementation. The language is aimed at dynamic distributed systems, which use socket based communication protocols for communicating between components. DSystemJ allows the creation and c...

The processing of queries expressed as trees of boolean operators applied to predi-cates on sensor data streams has several applications in mobile computing. Sensor data must beretrieved from the sensors to a query processing device, such as a smartphone, over one or morenetwork interfaces. Retrieving a data item incurs a cost, e.g., an energy expense that depletes thesmartphone...

Processor failures in post-petascale parallel computing platforms are common occurrences. The traditional fault-tolerance solution, checkpoint-rollback, severely limits parallel efficiency. One solution is to replicate application processes so that a processor failure does not necessarily imply an application failure. Process replication, combined with checkpoint-rollback, has been recently adv...

Embedded systems have to be more and more adaptive: they must perform reconfigurations in reaction to changes in their environment, related to resources or dependability. The management of this dynamical adaptivity, as in autonomic systems, can be considered as a control loop, on continuous or discrete criteria. Embedded systems are also by nature safety-critical, and must be statically checkab...

ion des prédicats Le model checking symbolique utilise une représenta-tion efficace des formules booléennes. Une façon orthogonale pour accrôıtre l’effi-cacité est de simplifier le modèle en cours de vérification en prenant une abstraction.Ce principe a été utilisé en vérification de matériel (propriétés en logique temporellede programmes assembleur) [16] puis de logiciel [14]. ...

The Linux kernel does not export a stable, well-de ned kernel interface, complicating the development of kernel-level services, such as device drivers and le systems. While there does exist a set of functions that are exported to external modules, these are continually changing, and have implicit, ill-documented preconditions, which, if not satis ed, can cause the entire system to crash or hang...