Modern heterogeneous multi-processor embedded systems very often expose to the designer a large number of degrees of freedom, related to the application partitioning/mapping and to the component- and system-level architecture composition. The number is even larger when the designer targets systems based on configurable Application Specific Instruction-set Processors, due to the fine customizability of their internal architecture. This poses the need for effective and user-friendly design tools, capable to deal with the extremely wide system-level design space exposed by multi-processor architecture and, at the same time, with an extended variety of processing element architectural configurations, to be evaluated in detail and in reasonable times. As a possible solution, within the MADNESS project [1], an integrated toolset has been proposed, combining the benefits of novel fast FPGA-based prototyping techniques with those provided by high-level simulation. In the toolset, the resulting evaluation platform serves as an underlying layer for a Design Space search algorithm. The paper presents the individual tools included in the toolset and their interaction strategy. The approach is then evaluated with a design space exploration case study, taking as a target application a video compression kernel. The integrated toolset has been used to produce a Pareto front of evaluated system-level configurations.