Power Efficiency for Software Algorithms running on Graphics Processors

Björn Johnsson
Lund University

Per Ganestam
Lund University

Michael Doggett
Lund University

Tomas Akenine-Möller
Lund University

High Performance Graphics, 2012.

Abstract

Power efficiency has become the most important consideration for many modern computing devices. In this paper, we examine power efficiency of a range of graphics algorithms on different GPUs. To measure power consumption, we have built a power measuring device that samples currents at a high frequency. Comparing power efficiency of different graphics algorithms is done by measuring power and performance of three different primary rendering algorithms and three different shadow algorithms. We measure these algorithms’ power signatures on a mobile phone, on an integrated CPU and graphics processor, and on high-end discrete GPUs, and then compare power efficiency across both algorithms and GPUs. Our results show that power efficiency is not always proportional to rendering performance and that, for some algorithms, power efficiency varies across different platforms. We also show that for some algorithms, energy efficiency is similar on all platforms.

Downloads

An author generated version of the paper. [pdf 10 MB]

Video from one of the measured application, showing an animated camerapath in the Sponza Atrium. [mp4 16.1 MB]

Hindsight:
Since the publication of this paper, we have realized that we are pushing a lot of geometry through the iPhone and that it therefore does not operate at its best performance. The reason for using a lot of geometry was to get frame times higher than just a few milliseconds on the discrete cards, and we wanted to keep as much as possible the same when comparing energy efficiency.

Last update: Thursday, 10-Sep-2009 13:23:22 CEST
Page Manager: Jonas Wisbrant
Publisher: Department of Computer Science