A Fast Yet Accurate Message-level Communication Bus Model for Timing Prediction of SDFGs on MPSoC

International audienceFast yet accurate performance and timing prediction of complexparallel data flow applications on multi-processor systems remainsa difficult discipline. The reason for it comes from the complexity ofthe data flow applications and the hardware platform with sharedresources, like buses and memories. This combination may lead tocomplex timing interferences that are difficult to express in pure analyticalor classical simulation-based approaches. In this work, wepropose a message-level communication model for timing and performanceprediction of Synchronous Data Flow (SDF) applicationson MPSoCs with shared memories. We compare our work againstmeasurement and TLM simulation-based performance predictionmodels on two case-studies from the computer vision domain. Weshow that the accuracy and execution time of our simulation outperformsexisting approaches and is suitable for a fast yet accuratedesign space exploration