Automatical exploration of low power architecture in co-design tool

Abstract

Energy consumption is a hot topic in the design of embedded systems. As mobile computing system (video camera, cellular phone, etc.) becomes more popular, how to lengthen the battery life of these systems becomes a critical issue. Also embedded system design is one of the most challenging tasks because the increasing complexity of new and various applications and the great variety of constraints to meet (lower cost, higher performance, lower energy). In this paper, we focus on the constraint of low energy consumption in hardware/software codesign tool. Our goal is to reach the best trade-off between system performance and energy consumption. For hardware and software units (DSP, RISC processors), we have developed a model of energy consumption and the methodology to evaluate the energy consumption of the designed systems. Then to reduce this energy, we introduce optimizations in allocation and scheduling steps. Experimental results show that this approach is promising and that it provides architectures with an energy saving of 50%.