Simulation is an important technique for integrating interacting models for predicting results of hypothetical scenarios. A typical application area for simulators is virtual prototyping (VP). In VP, simulators replace the real-world prototype. Hence, the quality of the virtual prototype depends on the quality of its simulations, which in turn are highly dependent on the quality of the models and the computational power, especially if visualization and/or real-time constraints are required. Unfortunately defining models is an error-prone activity which requires domain-experts to have knowledge about the implementation details and/or IT-technical concerns. In addition, the bigger the dataset, the more computational power is needed, which affects the cost, and in turn, the usability of today’s simulators. To address both of these aspects, we propose a user-friendly, adaptive and scalable agentbased modelling and simulation framework with a hybrid CPU/GPU/FPGA high performance computing platform. The solution we describe provides domain-experts with a a scalable, adaptive, and efficient simulator and enables domain-experts to define high quality models without indepth IT-knowledge. We use a running example from the particle transmission domain to illustrate our approach.