DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices
DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices
复制标题
DOI：
10.1109/ipsn.2016.7460664
复制
发表时间：
2016-04
期刊：
影响因子：
--
通讯作者：
N. Lane;S. Bhattacharya;Petko Georgiev;Claudio Forlivesi;Lei Jiao;Lorena Qendro;F. Kawsar
中科院分区：
文献类型：
--
作者：
N. Lane;S. Bhattacharya;Petko Georgiev;Claudio Forlivesi;Lei Jiao;Lorena Qendro;F. Kawsar
深度学习领域的突破正在从根本上改变传感器数据的解释方式，以提取移动应用程序所需的高级信息。至关重要的是，深度模型在推理准确性方面的收益将嵌入到未来几代移动应用程序中。在这项工作中，我们介绍了DeepX的设计和实现，这是一个用于深度学习执行的软件加速器。DeepX显著降低了深度学习所需的设备资源（即内存、计算、能量），这些资源目前是移动应用的严重瓶颈。DeepX的基础是一对为深度学习推理阶段设计的资源控制算法，它们：(1)将单片深度模型网络架构分解为各种类型的单元块，然后由异构本地设备处理器（例如gpu， cpu）更有效地执行；(2)执行有原则的资源缩放，调整深度模型的体系结构，以形成每个单元块引入的开销。实验表明，DeepX甚至可以让大规模深度学习模型在现代移动处理器上高效执行，并且显著优于现有的解决方案，例如基于云的卸载。
Breakthroughs from the field of deep learning are radically changing how sensor data are interpreted to extract the high-level information needed by mobile apps. It is critical that the gains in inference accuracy that deep models afford become embedded in future generations of mobile apps. In this work, we present the design and implementation of DeepX, a software accelerator for deep learning execution. DeepX signif- icantly lowers the device resources (viz. memory, computation, energy) required by deep learning that currently act as a severe bottleneck to mobile adoption. The foundation of DeepX is a pair of resource control algorithms, designed for the inference stage of deep learning, that: (1) decompose monolithic deep model network architectures into unit- blocks of various types, that are then more efficiently executed by heterogeneous local device processors (e.g., GPUs, CPUs); and (2), perform principled resource scaling that adjusts the architecture of deep models to shape the overhead each unit-blocks introduces. Experiments show, DeepX can allow even large-scale deep learning models to execute efficently on modern mobile processors and significantly outperform existing solutions, such as cloud-based offloading.