Word-Length Oriented Multiobjective Optimization of Area and Power Consumption in DSP Algorithm Implementation

摘要

The word-length of Functional Units (FU) has a great impact on design costs. This paper addresses the problem of choosing different word-lengths for each FU while considering circuit area and power consumption. A high-level synthesis tool is used to minimize the circuit area and power consumption by selecting an optimal word-length for each FU in the system. Our results demonstrate that by customizing word lengths to nonstandard sizes, savings can be made in the overall area and power without losing accuracy.