Generative and Multi-phase Learning for Computer Systems Optimization
Generative and Multi-phase Learning for Computer Systems Optimization
复制标题
DOI：
10.1145/3307650.3326633
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Yi Ding;Nikita Mishra;H. Hoffmann
中科院分区：
文献类型：
--
作者：
Yi Ding;Nikita Mishra;H. Hoffmann
机器学习和人工智能对于计算机系统优化是非常宝贵的：随着计算机系统暴露出更多的管理资源，ML/AI对于建模这些资源的复杂交互是必要的。将ML/AI纳入计算机系统的标准方法是首先训练学习者准确预测系统的行为作为资源使用的函数-例如，以预测作为核心使用的函数的能量效率-然后将所学习的模型部署为系统的一部分-例如，调度员在本文中，我们表明：（1）学习精度的持续提高可能不会改善系统的结果，但（2）将系统问题的知识纳入学习过程中，改善了系统的结果，即使它可能不会提高整体精度。具体来说，我们了解应用程序的性能和功率作为资源使用的函数，系统的目标是以最小的能量满足延迟约束。我们提出了一种新的生成模型，提高了学习精度的稀缺数据，我们提出了一个多相采样技术，它结合了系统问题的知识。我们的结果既有积极的，也有消极的。生成模型提高了准确性，即使对于最先进的学习系统也是如此，但对能源产生了负面影响。与现有技术相比，多相采样降低了能耗，但没有提高精度。这些结果意味着，系统优化的学习可能已经达到了收益递减的点，精度的提高对系统的结果几乎没有影响。因此，我们主张，未来的系统学习工作应该不再强调准确性，而是将系统问题的结构纳入学习者。
Machine learning and artificial intelligence are invaluable for computer systems optimization: as computer systems expose more resources for management, ML/AI is necessary for modeling these resources' complex interactions. The standard way to incorporate ML/AI into a computer system is to first train a learner to accurately predict the system's behavior as a function of resource usage- e.g., to predict energy efficiency as a function of core usage-and then deploy the learned model as part of a system-e.g., a scheduler. In this paper, we show that (1) continued improvement of learning accuracy may not improve the systems result, but (2) incorporating knowledge of the systems problem into the learning process improves the systems results even though it may not improve overall accuracy. Specifically, we learn application performance and power as a function of resource usage with the systems goal of meeting latency constraints with minimal energy. We propose a novel generative model which improves learning accuracy given scarce data, and we propose a multi-phase sampling technique, which incorporates knowledge of the systems problem. Our results are both positive and negative. The generative model improves accuracy, even for state-of-the-art learning systems, but negatively impacts energy. Multi-phase sampling reduces energy consumption compared to the state-of-the-art, but does not improve accuracy. These results imply that learning for systems optimization may have reached a point of diminishing returns where accuracy improvements have little effect on the systems outcome. Thus we advocate that future work on learning for systems should de-emphasize accuracy and instead incorporate the system problem's structure into the learner.