Transformation-Based Exploration of Data Parallel Architecture for Customizable Hardware: A JPEG Encoder Case Study

In this paper, we present a method for the design of MPSoCs for complex data-intensive applications. This method aims at a blend exploration of the communication, the memory system architecture and the computation resource parallelism. The proposed method is exemplified on a JPEG Encoder case study by describing all the design steps. Our method allows for a JPEG encoder implementation having a throughput increase of 84% and an increase of the achievable FPGA maximum frequency f_max of 64% with an area overhead of 6 with respect to a reference solution. Our method is also assessed with additional explorations of applications from different domains.