Neurosurgeon: Collaborative intelligence between the cloud and mobile edge

#graph_partitioning #cloud-edge_collaboration #prediction_model #computation_offloading

Meta Info

Presented in ASPLOS 2017.

Authors: Yiping Kang, Johann Hauswald, Cao Gao, Austin Rovinski, Trevor Mudge, Jason Mars, Lingjia Tang (UMich).

Understanding the paper

TL;DRs

This paper presents Neurosurgeon, a lightweight scheduler to automatically partition DNN computation between mobile devices and data centers at the granularity of neural network layers.

It doesn't require per-application profiling.

Overview

Dynamic DNN Partitioning

  1. Analysis of the target DNN (use the prediction models to estimate)

  2. Partition point selection (for best end-to-end latency or best mobile energy consumption)

Related Work

Previous research efforts focus on offloading computation from the mobile to the cloud.

Last updated