Energy-aware code motion for GPU shader processors

Yi-Ping You*, Shen Hong Wang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Scopus citations

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%.

Original languageEnglish
Article number49
JournalTransactions on Embedded Computing Systems
Volume13
Issue number3
DOIs
StatePublished - 1 Dec 2013

Keywords

  • Compilers for low power
  • Energy management
  • Shader processors

Fingerprint Dive into the research topics of 'Energy-aware code motion for GPU shader processors'. Together they form a unique fingerprint.

Cite this