System-wide energy minimization for real-time tasks: lower bound and approximation

We present a dynamic voltage scaling (DVS) technique that minimizes system-wide energy consumption for both periodic and sporadic tasks. It is known that a system consists of processors and a number of other components. Energy-aware processors can be run in different speed levels; components like memory and I/O subsystems and network interface cards can be in a standby state when they are active but idle. Processor energy optimization solutions are not necessarily efficient from the perspective of systems. Current system-wide energy optimization studies are often limited to periodic tasks with heuristics in getting approximated solutions. In this paper, we develop an exact dynamic programming algorithm for periodic tasks on processors with practical discrete speed levels. The algorithm determines the lower bound of energy expenditure in pseudo-polynomial time. An approximation algorithm is proposed to provide performance guarantee with a given bound in polynomial running time. Becaus...

• Type: Conference
• Year: 2006
• Where: ICCAD
• Authors: Xiliang Zhong, Cheng-Zhong Xu
• Keywords: Hardware, ICCAD 2006, Sporadic Tasks, System-wide Energy Consumption, System-wide Energy Optimization