Cost modeling and cycle-accurate co-simulation of heterogeneous multiprocessor systems

In this paper, we present a method to analyze different implementations of stream-based applications on heterogeneous multiprocessor systems. We take both resource usage and performance constraints into account. For the first aspect we use an empirical cost model. For the second aspect we build a network of cycle-accurate processor simulators. The simulation and resource cost estimation have been integrated in an existing framework, allowing one to generate fast exploration simulations, cycle-accurate simulations and FPGA implementations from a single system level specification. We show that with our methodology cycle-accurate performance numbers of candidate systems can be obtained. In our experiments with the QR and MJPEG applications, we found that the error of our resource cost model is below two percent.