A novel GPU power model for accurate smartphone power breakdown

Young Geun Kim, Minyong Kim, Jae Min Kim, Minyoung Sung, Sung Woo Jung

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

As GPU power consumption in smartphones increases with more advanced graphic performance, it becomes essential to estimate GPU power consumption accurately. The conventional GPU power model assumes, simply, that a GPU consumes constant power when turned on; however, this is no longer true for recent smartphone GPUs. In this paper, we propose an accurate GPU power model for smartphones, considering newly adopted dynamic voltage and frequency scaling. For the proposed GPU power model, our evaluation results show that the error rate for system power estimation is as low as 2.9%, on average, and 4.6% in the worst case.

Original languageEnglish
Pages (from-to)157-164
Number of pages8
JournalETRI Journal
Volume37
Issue number1
DOIs
Publication statusPublished - 2015 Jan 1

Fingerprint

Smartphones
Electric power utilization
Graphics processing unit

Keywords

  • GPU
  • Power breakdown
  • Power consumption
  • Power model
  • Smartphone

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science(all)
  • Electronic, Optical and Magnetic Materials

Cite this

A novel GPU power model for accurate smartphone power breakdown. / Kim, Young Geun; Kim, Minyong; Kim, Jae Min; Sung, Minyoung; Jung, Sung Woo.

In: ETRI Journal, Vol. 37, No. 1, 01.01.2015, p. 157-164.

Research output: Contribution to journalArticle

Kim, Young Geun ; Kim, Minyong ; Kim, Jae Min ; Sung, Minyoung ; Jung, Sung Woo. / A novel GPU power model for accurate smartphone power breakdown. In: ETRI Journal. 2015 ; Vol. 37, No. 1. pp. 157-164.
@article{69ff4858448b40429807760345a13e19,
title = "A novel GPU power model for accurate smartphone power breakdown",
abstract = "As GPU power consumption in smartphones increases with more advanced graphic performance, it becomes essential to estimate GPU power consumption accurately. The conventional GPU power model assumes, simply, that a GPU consumes constant power when turned on; however, this is no longer true for recent smartphone GPUs. In this paper, we propose an accurate GPU power model for smartphones, considering newly adopted dynamic voltage and frequency scaling. For the proposed GPU power model, our evaluation results show that the error rate for system power estimation is as low as 2.9{\%}, on average, and 4.6{\%} in the worst case.",
keywords = "GPU, Power breakdown, Power consumption, Power model, Smartphone",
author = "Kim, {Young Geun} and Minyong Kim and Kim, {Jae Min} and Minyoung Sung and Jung, {Sung Woo}",
year = "2015",
month = "1",
day = "1",
doi = "10.4218/etrij.15.0113.1411",
language = "English",
volume = "37",
pages = "157--164",
journal = "ETRI Journal",
issn = "1225-6463",
publisher = "ETRI",
number = "1",

}

TY - JOUR

T1 - A novel GPU power model for accurate smartphone power breakdown

AU - Kim, Young Geun

AU - Kim, Minyong

AU - Kim, Jae Min

AU - Sung, Minyoung

AU - Jung, Sung Woo

PY - 2015/1/1

Y1 - 2015/1/1

N2 - As GPU power consumption in smartphones increases with more advanced graphic performance, it becomes essential to estimate GPU power consumption accurately. The conventional GPU power model assumes, simply, that a GPU consumes constant power when turned on; however, this is no longer true for recent smartphone GPUs. In this paper, we propose an accurate GPU power model for smartphones, considering newly adopted dynamic voltage and frequency scaling. For the proposed GPU power model, our evaluation results show that the error rate for system power estimation is as low as 2.9%, on average, and 4.6% in the worst case.

AB - As GPU power consumption in smartphones increases with more advanced graphic performance, it becomes essential to estimate GPU power consumption accurately. The conventional GPU power model assumes, simply, that a GPU consumes constant power when turned on; however, this is no longer true for recent smartphone GPUs. In this paper, we propose an accurate GPU power model for smartphones, considering newly adopted dynamic voltage and frequency scaling. For the proposed GPU power model, our evaluation results show that the error rate for system power estimation is as low as 2.9%, on average, and 4.6% in the worst case.

KW - GPU

KW - Power breakdown

KW - Power consumption

KW - Power model

KW - Smartphone

UR - http://www.scopus.com/inward/record.url?scp=84921914872&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84921914872&partnerID=8YFLogxK

U2 - 10.4218/etrij.15.0113.1411

DO - 10.4218/etrij.15.0113.1411

M3 - Article

AN - SCOPUS:84921914872

VL - 37

SP - 157

EP - 164

JO - ETRI Journal

JF - ETRI Journal

SN - 1225-6463

IS - 1

ER -