论文标题
能源感知的DNN图优化
Energy-Aware DNN Graph Optimization
论文作者
论文摘要
与深度神经网络（DNN）中的现有工作不同，我们为推理性能优化了，我们探索了DNN图表优化，以实现能源意识和为电力和资源受限的机器学习设备节省。我们提出了一种方法，该方法允许用户优化DNN图的能耗和推理性能之间的平衡。此方法有效地搜索了等效图的空间，并标识了一个图形和相应的算法，这些算法会产生最低的执行成本。我们在基于GPU的计算机上使用多个DNN模型来对其进行评估。结果表明，我们的方法可实现明显的能源节省，即24％具有可忽略的性能影响。
Unlike existing work in deep neural network (DNN) graphs optimization for inference performance, we explore DNN graph optimization for energy awareness and savings for power- and resource-constrained machine learning devices. We present a method that allows users to optimize energy consumption or balance between energy and inference performance for DNN graphs. This method efficiently searches through the space of equivalent graphs, and identifies a graph and the corresponding algorithms that incur the least cost in execution. We implement the method and evaluate it with multiple DNN models on a GPU-based machine. Results show that our method achieves significant energy savings, i.e., 24% with negligible performance impact.
