Design space minimization with timing and code size optimization for embedded DSP

Abstract

One of the most challenging problems in high-level synthesis is how to quickly explore a wide range of design options to achieve high-quality designs. This paper presents an Integrated Framework for Design Optimization and Space Minimization (IDOM) towards finding the minimum configuration satisfying timing and code size constraints. We show an effective way to reduce the design space to be explored through the study of the fundamental properties and relations among multiple design parameters, such as retiming value, unfolding factor, timing, and code size. Theories are presented to produce a small set of feasible design choices with provable quality. IDOM algorithm is proposed to generate high-quality design by integrating performance and code size optimization techniques. The experimental results on a set of DSP benchmarks show the efficiency and effectiveness of the IDOM algorithm. It constantly generates the minimal configuration for all the benchmarks. The cost of design space exploration using IDOM is only 3% of that using the standard method.