Learn More
The move towards Service Grids, where services are composed to meet the requirements of a user community within constraints specified by the resource provider, present many challenges to service provision and description. To support our research activities in the autonomous composition of services to form a Semantic Service Grid we describe the adoption(More)
—The increasing numbers of cores, shared caches and memory nodes within machines introduces a complex hardware topology. High-performance computing applications now have to carefully adapt their placement and behavior according to the underlying hierarchy of hardware resources and their software affinities. We introduce the Hardware Locality (hwloc)(More)
We identify two forms of workflow expression, temporal, in which relations may imply temporal dependencies, and spatial, in which they do not. Spatial expressions enable the dynamic modification of the workflow; by raising the level of abstraction they provide flexibility. This flexibility is at the cost of information; temporal expressions can guide(More)
Communication libraries have dramatically made progress over the fifteen years, pushed by the success of cluster architectures as the preferred platform for high performance distributed computing. However, many potential optimizations are left unexplored in the process of mapping application communication requests onto low level network commands. The(More)
Exploiting the full computational power of current hierarchical multiprocessor machines requires a very careful distribution of threads and data among the underlying non-uniform architecture so as to avoid remote memory access penalties. Directive-based programming languages such as OpenMP, can greatly help to perform such a distribution by providing(More)
In this paper, we present two new methods to simulate Petri Nets: a data parallel simulation and a distributed simulation. Both simulations use an equational representation of the net in the so called (min, +) algebra. The data parallel simulation is based on the use of matrix representation of these equations, and the distributed simulation on the(More)
Communication libraries have dramatically made progress over the fifteen years, pushed by the success of cluster architectures as the preferred platform for high performance distributed computing. However, many potential optimizations are left unexplored in the process of mapping application communication requests onto low level network commands. The(More)