Leakage Aware Dynamic Slack Reclamation in Real-Time Embedded Systems

Leakage energy consumption is an increasing concern in current and future CMOS technology generations. Procrastination scheduling, where task execution can be delayed to maximize the duration of idle intervals, has been proposed to minimize leakage energy drain. We address dynamic slack reclamation techniques under procrastination scheduling to minimize the static and dynamic energy consumption. In addition to dynamic task slowdown, we propose dynamic procrastination which seeks to extend idle intervals through slack reclamation. While using the entire slack for either slowdown or procrastination need not be the most efficient approach, we distribute the slack between slowdown and procrastination to exploit maximum energy savings. Our simulation experiments show that dynamic slowdown results on an average 10% energy gains over static slowdown. Dynamic procrastination can extend the average sleep intervals by up to 70%, while meeting all timing requirements.