Energy optimization by exploiting execution slacks in streaming applications on Multiprocessor Systems
Energy optimization by exploiting execution slacks in streaming applications on Multiprocessor Systems
复制标题
DOI：
10.1145/2463209.2488875
复制
发表时间：
2013-05
期刊：
影响因子：
--
通讯作者：
Ashutosh Kumar Singh;Anup Das;Akash Kumar
中科院分区：
文献类型：
--
作者：
Ashutosh Kumar Singh;Anup Das;Akash Kumar
动态电压和频率调整（DVFS）为优化多处理器片上系统（MPSoC）的能效提供了巨大的潜力。用于处理器电压和频率调整的常规方法不适合于流媒体应用，这是由于执行任务中的依赖性的循环性质，这可能潜在地违反吞吐量约束。在本文中，我们提出了一种方法，适用于DVFS这样的循环相关的任务。该方法涉及离线分析，假设最坏情况下的执行时间的任务，以确定执行，可以放慢和在线分析，利用松弛所产生的任务，完成其执行之前的最坏情况下的执行时间。因此，该方法在离线和在线分析期间最小化能量消耗，同时满足吞吐量约束。基于现实生活中的流媒体应用模型的实验表明，所提出的方法降低了43%的整体能耗相比，现有的方法。
Dynamic voltage and frequency scaling (DVFS) offers great potential for optimizing the energy efficiency of Multiprocessor Systems-on-Chip (MPSoCs). The conventional approaches for processor voltage and frequency adjustment are not suitable for streaming multimedia applications due to the cyclic nature of dependencies in the executing tasks which can potentially violate the throughput constraints. In this paper, we propose a methodology that applies DVFS for such cyclic dependent tasks. The methodology involves an off-line analysis that assumes worst-case execution times of tasks to identify the executions that can be slowed down and an on-line analysis to utilize the slacks arising from tasks that finish their execution before the worst-case execution times. Thus, the methodology minimizes energy consumption during both off-line and on-line analysis while satisfying the throughput constraints. Experiments based on models of real-life streaming multimedia applications show that the proposed methodology reduces the overall energy consumption by 43% when compared to existing approaches.