DynO: Dynamic Onloading of Deep Neural Networks from Cloud to Device

Abstract

Recently, there has been an explosive growth of mobile and embedded applications using convolutional neural networks(CNNs). To alleviate their excessive computational demands, developers have traditionally resorted to cloud offloading, inducing high infrastructure costs and a strong dependence on networking conditions. On the other end, the emergence of powerful SoCs is gradually enabling on-device execution. Nonetheless, low- and mid-tier platforms still struggle to run state-of-the-art CNNs sufficiently. In this paper, we present DynO, a distributed inference framework that combines the best of both worlds to address several challenges, such as device heterogeneity, varying bandwidth and multi-objective requirements. Key components that enable this are its novel CNN-specific data packing method, which exploits the variability of precision needs in different parts of the CNN when onloading computation, and its novel scheduler that jointly tunes the partition point and transferred data precision at run time to adapt inference to its execution environment. Quantitative evaluation shows that DynO outperforms the current state-of-the-art, improving throughput by over an order of magnitude over device-only execution and up to 7.9x over competing CNN offloading systems, with up to 60x less data transferred.

Accepted for publication at the ACM Transactions on Embedded Computing Systems (TECS) in the special issue on Accelerating AI on the Edge

References in corpus (7)

• SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud
• DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments
• JALAD: Joint Accuracy- and Latency-Aware Deep Structure Decoupling for Edge-Cloud Execution
• Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions
• EmBench: Quantifying Performance Variations of Deep Neural Networks across Modern Commodity Devices
• Trading-off Accuracy and Energy of Deep Inference on Embedded Systems: A Co-Design Approach
• HAPI: Hardware-Aware Progressive Inference

Cited by in corpus (4)

• FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing
• LimitNet: Progressive, Content-Aware Image Offloading for Extremely Weak Devices & Networks
• Smart at what cost? Characterising Mobile Deep Neural Networks in the wild
• MultiTASC++: A Continuously Adaptive Scheduler for Edge-Based Multi-Device Cascade Inference