Model-based precision analysis and optimization for digital signal processors

Embedded signal processing has witnessed explosive growth in recent years in both scientific and consumer applications, driving the need for complex, high-performance signal processing systems that are largely application driven. In order to efficiently implement these systems on programmable platforms such as digital signal processors (DSPs), it is important to analyze and optimize the application design from early stages of the design process. A key performance concern for designers is choosing the data format. In this work, we propose a systematic and efficient design flow involving model-based design to analyze application data sets and precision requirements. We demonstrate this design flow with an exploration study into the required precision for eigenvalue decomposition (EVD) using the Jacobi algorithm. We demonstrate that with a high degree of structured analysis and automation, we are able to analyze the data set to derive an efficient data format, and optimize important parts of the algorithm with respect to precision.