Corresponding publication at IMPACT'16 (http://impact.gforge.inria.fr/impact2016)This paper studies the applicability of polyhedral techniques to the parallel language Open-Stream [25]. When applicable, polyhedral techniques are invaluable for compile-time debugging andfor generating efficient code well suited to a target architecture. OpenStream is a two-level languagein which a control program directs the initialization of parallel task instances that communicatethrough streams, with possibly multiple writers and readers. It has a fairly complex semantics in itsmost general setting, but we restrict ourselves to the case where the control program is sequential,which is representative of the majority of the OpenStream applications. This res...
We revisit the problem of computing liveness sets, i.e., the set of variables live-in and live-out o...
With the advent of complex modern architectures, the low-levelparadigms long considered sufficient t...
Shared-memory concurrency is a classic concurrency model which, among other things, makes it possibl...
Corresponding publication at IMPACT'16 (http://impact.gforge.inria.fr/impact2016)In this report, we ...
Scientific applications have an increasing need of resources and many grand scientific challenges re...
As single processing unit performance has reached a technological limit, the power wall, the past de...
Motivated by modern day physics which in addition to experiments also tries to verify and deduce law...
This thesis intends to show how to efficiently exploit the parallelism present in applications in or...
Parallel programs need to manage the time trade-off between synchronization and computation. A high ...
We present two contributions to the field of parallel programming.The first contribution is theoreti...
In distributed graph computation, graph partitioning is an important preliminary step because the co...
Nowadays, applications from dissimilar domains, such as high-performance computing and high-integrit...
Dataflow Models of Computation (MoCs) are widely used in embedded systems, including multimedia proc...
Jury de soutenance : DR, DHOME Michel, President PR, MIGUET Serge, Rapporteur MCF-HDR, HOUZET Domini...
Clusters of multicore/GPU nodes connected with a fast network offer very high therotical peak perfor...
We revisit the problem of computing liveness sets, i.e., the set of variables live-in and live-out o...
With the advent of complex modern architectures, the low-levelparadigms long considered sufficient t...
Shared-memory concurrency is a classic concurrency model which, among other things, makes it possibl...
Corresponding publication at IMPACT'16 (http://impact.gforge.inria.fr/impact2016)In this report, we ...
Scientific applications have an increasing need of resources and many grand scientific challenges re...
As single processing unit performance has reached a technological limit, the power wall, the past de...
Motivated by modern day physics which in addition to experiments also tries to verify and deduce law...
This thesis intends to show how to efficiently exploit the parallelism present in applications in or...
Parallel programs need to manage the time trade-off between synchronization and computation. A high ...
We present two contributions to the field of parallel programming.The first contribution is theoreti...
In distributed graph computation, graph partitioning is an important preliminary step because the co...
Nowadays, applications from dissimilar domains, such as high-performance computing and high-integrit...
Dataflow Models of Computation (MoCs) are widely used in embedded systems, including multimedia proc...
Jury de soutenance : DR, DHOME Michel, President PR, MIGUET Serge, Rapporteur MCF-HDR, HOUZET Domini...
Clusters of multicore/GPU nodes connected with a fast network offer very high therotical peak perfor...
We revisit the problem of computing liveness sets, i.e., the set of variables live-in and live-out o...
With the advent of complex modern architectures, the low-levelparadigms long considered sufficient t...
Shared-memory concurrency is a classic concurrency model which, among other things, makes it possibl...