Energy-Aware DNN Graph Optimization

05/12/2020
by   Yu Wang, et al.
3

Unlike existing work in deep neural network (DNN) graphs optimization for inference performance, we explore DNN graph optimization for energy awareness and savings for power- and resource-constrained machine learning devices. We present a method that allows users to optimize energy consumption or balance between energy and inference performance for DNN graphs. This method efficiently searches through the space of equivalent graphs, and identifies a graph and the corresponding algorithms that incur the least cost in execution. We implement the method and evaluate it with multiple DNN models on a GPU-based machine. Results show that our method achieves significant energy savings, i.e., 24

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/12/2018

End-to-End Learning of Energy-Constrained Deep Neural Networks

Deep Neural Networks (DNN) are increasingly deployed in highly energy-co...
research
09/14/2020

NextDoor: GPU-Based Graph Sampling for Graph Machine Learning

Representation learning is a fundamental task in machine learning. It co...
research
10/25/2020

LazyBatching: An SLA-aware Batching System for Cloud Machine Learning Inference

In cloud ML inference systems, batching is an essential technique to inc...
research
12/05/2018

ECC: Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model

Many DNN-enabled vision applications constantly operate under severe ene...
research
09/28/2018

Intelligence Beyond the Edge: Inference on Intermittent Embedded Systems

Energy-harvesting technology provides a promising platform for future Io...
research
10/31/2019

ALERT: Accurate Anytime Learning for Energy and Timeliness

An increasing number of software applications incorporate runtime Deep N...
research
05/24/2022

Multi-Agent Collaborative Inference via DNN Decoupling: Intermediate Feature Compression and Edge Learning

Recently, deploying deep neural network (DNN) models via collaborative i...

Please sign up or login with your details

Forgot password? Click here to reset