Exploiting Computation Reuse in Cloud-Based Deep Learning via Input Reordering

Enting Guo, Peng Li, Kun Wang, Huibin Feng, Jingyuan Lu, Song Guo

Research output: Unpublished conference presentation (presented paper, abstract, poster)Conference presentation (not published in journal/proceeding/book)Academic researchpeer-review

Abstract

Recently, deep learning (DL) becomes increasingly important since its transformative effect on a wide range of applications. During inference process, the DL model is deployed on the cloud to answer online queries. One crucial issue in the progress of DL inference is energy consumption, which significantly retards computation performance. Therefore, many previous investigations decrease the energy consumption via computation reuse technique based on similarity. However, if input data consists individually from mobile devices, applying these schemes will significantly decline computation performance. Because in disordered individual inputs, similarity for reuse is difficult to exploit directly. Results of initial experimental observations show that (1) individual input data also has high similarity for reuse, and (2) the total similarity during computation process has a relation with the characteristics of input data. This motivates us to design a reordering scheme to enhance similarity for computation reuse. Our main approaches are using statistical theory to predict the similarities among input data, and determining the execution sequence. Based on these approaches, we propose an effective input reordering scheme for computation reuse to save energy consumption. The evaluation under various benchmarks demonstrates that the reordering scheme significantly outperforms the previous schemes, for instance, the computation reuse is enhanced to
1.1×
and the energy consumption is minimized to 40% according to the configuration of traditional computation reuse technique.
Original languageEnglish
Pages1-6
Number of pages6
Publication statusPublished - Jun 2020
Event2020 IEEE International Conference on Communications (ICC 2020) - Dublin, Ireland
Duration: 7 Jun 202011 Jun 2020

Conference

Conference2020 IEEE International Conference on Communications (ICC 2020)
Country/TerritoryIreland
CityDublin
Period7/06/2011/06/20

Keywords

  • Deep Learning
  • Computation Reuse
  • Cloud Computing

Cite this