Pipeline schedule synthesis for real-time streaming tasks with inter/intra-instance precedence constraints

Abstract

Heterogeneous multi-core platforms are widely accepted for high performance multimedia embedded systems. Although pipeline techniques can enhance performance for the multi-core platforms, data dependencies for processing compressed multimedia data makes it difficult, if not impossible, to automate pipelined design. In this paper, we target on multimedia streaming applications on heterogeneous multi-core platforms and develop the Tile Piecing Algorithm for pipelined schedule synthesis within the targeted applications and platforms. The algorithm gives an efficient way to construct a pipelined schedule. The performance evaluation result shows that the algorithm performs as well as the optimal algorithm to utilize the computation resource. On the other hand, the algorithm only takes hundreds of milliseconds to complete, which is less than one tenth of the running time for optimal algorithm. Last, the synthesized schedule is well packed. The short execution time and schedule make-span makes the algorithm more practical to be used during the run-time.