DCAILGJul 20, 2022

AutoDiCE: Fully Automated Distributed CNN Inference at the Edge

arXiv:2207.12113v13 citationsh-index: 27
Originality Incremental advance
AI Analysis

This addresses the problem of efficient deep learning inference at the edge for applications like image classification and speech recognition, offering an incremental improvement by automating existing distribution approaches.

The paper tackles the challenge of deploying large CNNs on resource-constrained edge devices by proposing AutoDiCE, a framework that automates CNN splitting and deployment across multiple edge devices for distributed inference, resulting in reduced energy consumption, lower memory usage per device, and improved system throughput.

Deep Learning approaches based on Convolutional Neural Networks (CNNs) are extensively utilized and very successful in a wide range of application areas, including image classification and speech recognition. For the execution of trained CNNs, i.e. model inference, we nowadays witness a shift from the Cloud to the Edge. Unfortunately, deploying and inferring large, compute and memory intensive CNNs on edge devices is challenging because these devices typically have limited power budgets and compute/memory resources. One approach to address this challenge is to leverage all available resources across multiple edge devices to deploy and execute a large CNN by properly partitioning the CNN and running each CNN partition on a separate edge device. Although such distribution, deployment, and execution of large CNNs on multiple edge devices is a desirable and beneficial approach, there currently does not exist a design and programming framework that takes a trained CNN model, together with a CNN partitioning specification, and fully automates the CNN model splitting and deployment on multiple edge devices to facilitate distributed CNN inference at the Edge. Therefore, in this paper, we propose a novel framework, called AutoDiCE, for automated splitting of a CNN model into a set of sub-models and automated code generation for distributed and collaborative execution of these sub-models on multiple, possibly heterogeneous, edge devices, while supporting the exploitation of parallelism among and within the edge devices. Our experimental results show that AutoDiCE can deliver distributed CNN inference with reduced energy consumption and memory usage per edge device, and improved overall system throughput at the same time.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes