Cache Leakage Management for Multi-programming Workloads

摘要

Power consumption is becoming a critical design issue of embedded systems due to the popularity of portable device such as cellular phones and personal digital assistants. Leakage is projected to most amount of cache power budget in 70nm technology. In this paper, we utilize the task-level information to manage cache leakage power. We partition the caches among tasks according to their working set size. We then apply different leakage management policies to the cache regions allocated to active and suspended tasks, respectively. Our proposed policies effectively reduce L1 cache leakage energy by 84% on the average for the multi-programming workloads with only negligible degradations in performances.