Energy-Aware Instruction-Set Customization for Real-Time Embedded Multiprocessor Systems
In this paper, the authors present a method to customize instruction-set for configurable multiprocessors under a given silicon area budget so that total dynamic energy consumption is minimized when Dynamic Voltage and Frequency Scaling (DVFS) is employed. The proposed method is based on Mixed-Integer Linear Programming (MILP) to select the optimal processor configurations for real-time tasks from custom instruction candidates. They have evaluated the proposed method using real-life applications and commercial configurable processors. The results show that the optimally configured multi-processors by their method have up to 23.2% reduction of dynamic energy consumption in comparison with the multi-processors configured by a conventional approach.