Spendthrift: Machine learning based resource and frequency scaling for ambient energy harvesting nonvolatile processors
Spendthrift: Machine learning based resource and frequency scaling for ambient energy harvesting nonvolatile processors
复制标题
DOI：
10.1109/aspdac.2017.7858402
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Kaisheng Ma;Xueqing Li;S. Srinivasa;Yongpan Liu;Jack Sampson;Yuan Xie;N. Vijaykrishnan
中科院分区：
文献类型：
--
作者：
Kaisheng Ma;Xueqing Li;S. Srinivasa;Yongpan Liu;Jack Sampson;Yuan Xie;N. Vijaykrishnan
无电池能量收集系统在将输入的能量转化为前进的过程中面临着双重挑战。此类系统不仅必须应对本质上较弱且波动的电源，而且它们利用高于平均功率的短暂时期的时间窗口非常有限。为了最大限度地提高前进速度，此类系统应在可用时积极消耗能源，而不是针对峰值平均情况效率进行优化。然而，处理器可以通过多种方式在功耗和性能之间进行权衡。在本文中，我们研究了两种方法：频率缩放和资源缩放，并开发了一种预测器驱动的方案，用于在两种技术之间动态分配未来的功率预算。我们表明，我们的解决方案可以在频率和资源的最佳静态配置下实现相当于基线无序 (OoO) 处理器 2.08 倍的前进速度。组合技术的性能优于任何一种单独技术，仅频率方法和仅资源方法分别实现了 1.43 倍和 1.61 倍的前向进度改进。
Batteryless energy harvesting systems face a twofold challenge in converting incoming energy into forward progress. Not only must such systems contend with inherently weak and fluctuating power sources, but they have very limited temporal windows for capitalizing on transitory periods of above-average power. To maximize forward progress, such systems should aggressively consume energy when it is available, rather than optimizing for peak averagecase efficiency. However, there are multiple ways that a processor can trade between consumption and performance. In this paper, we examine two approaches, frequency scaling and resource scaling, and develop a predictor-driven scheme for dynamically allocating future power budgets between the two techniques. We show that our solution can achieve forward progress equal to 2.08X of the baseline Out-of-Order (OoO) processor with the best static configuration of frequency and resources. The combined technique outperforms either technique in isolation, with frequency-only and resource-only approaches achieving 1.43X and 1.61X forward progress improvements, respectively.