Energy efficient real-time task scheduling for embedded systems with hybrid main memory

Available energy is the most critical limitation on the performance of embedded systems along with the increasing sophistication. Phase Change Memory (PCM), with high density and low idle power has recently been extensively studied as a promising alternative main memory of DRAM. In this paper, a hybrid PCM/DRAM main memory is utilized to leverage the low power of PCM and high performance of DRAM. We reconsider the real-time task scheduling problem of hybrid PCM/DRAM-based embedded systems. To maximize energy saving, two static scheduling algorithms under Rate-Monotonic(RM) and Earliest Deadline First (EDF) are proposed while guaranteeing the real-time constraints of all tasks. Since the actual execution time is much shorter than the worst-case execution time in real environment, we propose two dynamic mechanisms to optimize the energy consumption of our static solutions, so as to fully use the slack time produced by completed tasks. All the proposed algorithms minimize the number of task migrations from PCM to DRAM and ensure each task instance can be migrated at most once. Experimental results show our real-time scheduling algorithms reduce 25.7% to 47.2% of energy consumption on average.