An Energy-aware Online Learning Framework for Resource Management in Heterogeneous Platforms
An Energy-aware Online Learning Framework for Resource Management in Heterogeneous Platforms
复制标题
DOI：
10.1145/3386359
复制
发表时间：
2020-05-01
影响因子：
1.4
通讯作者：
Ogras, Umit Y.
中科院分区：
文献类型：
--
作者：
Mandal, Sumit K.;Bhat, Ganapati;Ogras, Umit Y.
移动的平台必须满足快速响应时间和最小能耗的矛盾要求，这是动态变化应用的函数。为了满足这一需求，作为这些器件核心的片上系统（SoC）提供了各种控制旋钮，例如活动内核的数量及其电压/频率电平。出于两个原因，在运行时最佳地控制这些旋钮具有挑战性。首先，大的配置空间禁止穷举解决方案。其次，离线设计的控制策略充其量是次优的，因为许多潜在的新应用在设计时是未知的。我们通过提出一种在线模仿学习方法来解决这些挑战。我们的关键思想是构建一个离线策略，并使其在线适应新的应用程序，以优化给定的指标（例如，能源）。所提出的方法利用了在运行时学习的功率性能模型所启用的监督。我们证明了其有效性的商业移动的平台与16个不同的基准。我们的方法成功地适应控制策略，以未知的应用程序后，执行不到25%的指令。
Mobile platforms must satisfy the contradictory requirements of fast response time and minimum energy consumption as a function of dynamically changing applications. To address this need, systems-on-chip (SoC) that are at the heart of these devices provide a variety of control knobs, such as the number of active cores and their voltage/frequency levels. Controlling these knobs optimally at runtime is challenging for two reasons. First, the large configuration space prohibits exhaustive solutions. Second, control policies designed offline are at best sub-optimal, since many potential new applications are unknown at design-time. We address these challenges by proposing an online imitation learning approach. Our key idea is to construct an offline policy and adapt it online to new applications to optimize a given metric (e.g., energy). The proposed methodology leverages the supervision enabled by power-performance models learned at runtime. We demonstrate its effectiveness on a commercial mobile platform with 16 diverse benchmarks. Our approach successfully adapts the control policy to an unknown application after executing less than 25% of its instructions.