Frames will provide support for the programming of distributed-memory machines via a library of basic algorithms, data structures and so-called programming frames (or frameworks). The latter are skeletons with problem dependent parameters to be provided by the users. Frames focuses on re-usability and portability as well as on small and easy-to-learn interfaces. Thus, non-expert users will be provided with tools to program and exploit parallel machines efficiently.
We shall develop basic frames (which can be used to build more sophisticated ones) as well as complex frames for, e.g., Branch-and-Cut, finite element methods, tree-structured combinatorial optimisation algorithms, finite difference methods, sorting and searching algorithms. All these frames will be especially valuable and relevant to industrial cooperators.
Frames will be constructed for different target machines and common programming environments (like PVM or MPI). The focus, however, is on distributed-memory machines. Frames will be adapted optimally to the target systems, contain efficient state-of-the-art programming techniques, and therefore increase the acceptance of parallel computing.
More information:
The
Shared Memory Simulation Frame (SMS-Frame)
People involved in the Frames:
Participating Sites in the Frames WorkPackage:
Also have a look at the ALCOM-IT project Home Page