Energy-aware code motion for GPU shader processors
-
Published:2013-12
Issue:3
Volume:13
Page:1-24
-
ISSN:1539-9087
-
Container-title:ACM Transactions on Embedded Computing Systems
-
language:en
-
Short-container-title:ACM Trans. Embed. Comput. Syst.
Author:
You Yi-Ping1,
Wang Shen-Hong1
Affiliation:
1. National Chiao Tung University, Hsinchu, Taiwan
Abstract
Graphics processing units (GPUs) are now being widely adopted in system-on-a-chip designs, and they are often used in embedded systems for manipulating computer graphics or even for general-purpose computation. Energy management is of concern to both hardware and software designers. In this article, we present an
energy-aware code-motion
framework for a compiler to generate concentrated accesses to input and output (I/O) buffers inside a GPU. Our solution attempts to gather the I/O buffer accesses into clusters, thereby extending the time period during which the I/O buffers are clock or power gated. We performed experiments in which the energy consumption was simulated by incorporating our compiler-analysis and code-motion framework into an in-house compiler tool. The experimental results demonstrated that our mechanisms were effective in reducing the energy consumption of the shader processor by an average of 13.1% and decreasing the energy-delay product by 2.2%.
Funder
National Science Council Taiwan
Institute for Information Industry
Publisher
Association for Computing Machinery (ACM)
Subject
Hardware and Architecture,Software
Reference28 articles.
1. Apple 2011. OpenGL ES on iOS. http://developer.apple.com/iphone/library/documentation/3DDrawing/Conceptual/OpenGLES_ProgrammingGuide/OpenGLESontheiPhone/OpenGLESontheiPhone.html#//apple_ref/doc/uid/TP40008793-CH101-SW1. Apple 2011. OpenGL ES on iOS. http://developer.apple.com/iphone/library/documentation/3DDrawing/Conceptual/OpenGLES_ProgrammingGuide/OpenGLESontheiPhone/OpenGLESontheiPhone.html#//apple_ref/doc/uid/TP40008793-CH101-SW1.
2. An 8.6 mW 25 Mvertices/s 400-MFLOPS 800-MOPS 8.91 mm$^{2}$ Multimedia Stream Processor Core for Mobile Applications
3. Operator strength reduction
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Learning based application driven energy aware compilation for GPU;Microprocessors and Microsystems;2022-10
2. Specialization Opportunities in Graphical Workloads;2019 28th International Conference on Parallel Architectures and Compilation Techniques (PACT);2019-09
3. VecRA;ACM Transactions on Embedded Computing Systems;2016-09