As single-processor systems are ceasing to scale effectively, multi-processor systems are becoming more and more popular. While there are many challenges of designing multi-processor systems in hardware, writing efficient parallel applications that utilize the computing capability of multiple processors may reveal to be even more challenging. In this paper, we introduce a framework that allows to efficiently execute applications expressed as Kahn process networks on multiprocessor systems using protothreads and windowed FIFOs. We show that application developers can use this framework to achieve considerable speed-ups on the Cell Broadband Engine without needing to write architecture-specific code.