A Unified Framework for Throughput Analysis of Streaming Applications under Memory Constraints

Abstract

Streaming applications are an important class of applications in real-time embedded systems, which usually run under restricted resource constraints and with real-time requirement. They are often modeled with Synchronous data flow graphs (SDFGs) or Cyclo-Static data flow graphs (CSDFGs) at the design stage. A proper analysis of the models gives a predictable design for a system. In this paper, we focus on the throughput analysis of (C)SDFGs, taking into account memory constraints. Memory related analysis needs to choose a memory abstraction that decides when the space of consumed data is released and when the required space is claimed. Different memory abstractions may lead to different achievable throughputs. The existing techniques, however, consider only a certain abstraction. If a model is implemented according to other abstractions, the analysis result may not truly evaluate the performance of the system. In this paper, we present a novel unified framework for throughput analysis of memory constrained (C)SDFGs for different abstractions, aiming to provide evaluations matching up to the corresponding implementations. Our methods are exact. Experiments are carried out on several models of real streaming applications and hundreds of synthetic graphs to evaluate the effects and performance of our methods.