JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services

TL;DR

JointDNN is a novel adaptive engine that efficiently partitions DNN computations between mobile devices and the cloud, significantly reducing latency and energy consumption for mobile AI applications.

Contribution

It introduces an optimization framework for collaborative DNN processing that adapts to device and cloud constraints, improving efficiency over existing methods.

Findings

Up to 18x reduction in latency.

Up to 32x reduction in mobile energy consumption.

Effective partitioning of DNN layers between mobile and cloud.

Abstract

Deep learning models are being deployed in many mobile intelligent applications. End-side services, such as intelligent personal assistants, autonomous cars, and smart home services often employ either simple local models on the mobile or complex remote models on the cloud. However, recent studies have shown that partitioning the DNN computations between the mobile and cloud can increase the latency and energy efficiencies. In this paper, we propose an efficient, adaptive, and practical engine, JointDNN, for collaborative computation between a mobile device and cloud for DNNs in both inference and training phase. JointDNN not only provides an energy and performance efficient method of querying DNNs for the mobile side but also benefits the cloud server by reducing the amount of its workload and communications compared to the cloud-only approach. Given the DNN architecture, we investigate the efficiency of processing some layers on the mobile device and some layers on the cloud server. We provide optimization formulations at layer granularity for forward- and backward-propagations in DNNs, which can adapt to mobile battery limitations and cloud server load constraints and quality of service. JointDNN achieves up to 18 and 32 times reductions on the latency and mobile energy consumption of querying DNNs compared to the status-quo approaches, respectively.