No abstract

Kahn Process Networks (KPNs) are a widely accepted programming model for MPSoCs. Existing KPN mapping techniques mainly focus on assigning processes to processors. However, with embedded interconnect becoming more complex, communication has started to play an equally important role to that of computation. This paper presents a new KPN mapping algorithm that addresses communication and computation jointly. The algorithm is tested on two platforms with real applications and with randomly generated KPNs. We show that the algorithm finds solutions in situations where bare process mapping fails. It also reduced the average application makespan considerably when compared to previous heuristics.

No abstract

Programming models which specify an application as a network of independent computational elements have emerged as a promising paradigm for programming streaming applications. The antagonism between expressivity and analysability has led to a number of different such programming models, which provide different degrees of freedom to the programmer. One example are Kahn process networks (KPNs), which, due to certain restrictions in communication, can guarantee determinacy (their results are independent of timing by construction). On the other hand, certain dataflow models, such as the CAL Actor Language, allow non-determinacy and thus higher expressivity, however at the price of static analysability and thus a potentially less efficient implementation. In many cases, however, non-determinacy is not required (or even not desired), and relying on KPN for the implementation seems advantageous.In this paper, we propose an algorithm for classifying dataflow actors (i.e. computational elements) as KPN compatible or potentially not. For KPN compatible dataflow actors, we propose an automatic KPN translation method based on this algorithm. In experiments, we show that more than 75% of all mature actors of a standard multimedia benchmark suite can be classified as KPN compatible and that their execution time can be reduced by up to 1.97x using our proposed translation technique. Finally, in a manual classification effort, we validate these results and list different classes of KPN incompatibility.

Kahn process networks are a popular programming model for programming multi-core systems. They ensure determinacy of applications by restricting processes to separate memory regions, only allowing communication over FIFO channels. However, many modern multi-core platforms concentrate on shared memory as a means of communication and data exchange. In this work, we present a concept for deterministic memory sharing in Kahn process networks. It allows to take advantage of shared memory data exchange mechanisms on such platforms while still preserving determinacy. We show how any Kahn process network can be transformed to use deterministic memory sharing by giving a set of transformations that can be applied selectively, only looking at one process at a time. We demonstrate how these techniques can be applied to an ultrasound image reconstruction algorithm. For an implementation on a test system, our technique yields significantly better performance combined with a drastically smaller memory footprint.