Data processing on convolutional neural networks (CNNs) places a heavy burden on energy-constrained mobile platforms. This article optimizes energy on a mobile client by partitioning CNN computations between in situ processing on the client and offloaded computations in the cloud. A new analytical CNN energy model is formulated, capturing all major components of the in situ computation, for ASIC-based deep learning accelerators. The model is benchmarked against measured silicon data. The analytical framework is used to determine the optimal energy partition point between the client and the cloud at runtime. On standard CNN topologies, partitioned computation is demonstrated to provide significant energy savings on the client over a fully cloud-based computation or fully in situ computation. For example, at 80 Mbps effective bit rate and 0.78 W transmission power, the optimal partition for AlexNet [SqueezeNet] saves up to 52.4% [73.4%] energy over a fully cloud-based computation and 27.3% [28.8%] energy over a fully in situ computation.

中文翻译：

---

NeuPart：使用分析模型在连接云的移动客户端上推动 CNN 计算的节能分区

卷积神经网络 (CNN) 上的数据处理给能量受限的移动平台带来了沉重的负担。本文通过在客户端的原位处理和云中的卸载计算之间划分 CNN 计算来优化移动客户端上的能量。为基于 ASIC 的深度学习加速器制定了一个新的分析 CNN 能量模型，捕获原位计算的所有主要组件。该模型以测得的硅数据为基准。分析框架用于在运行时确定客户端和云之间的最佳能量分割点。在标准的 CNN 拓扑上，分区计算被证明可以通过完全基于云的计算或完全原位计算为客户端提供显着的能源节省。例如，在 80 Mbps 有效比特率和 0.