Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Architecting Graphics Processors for Non-Graphics Compute Acceleration Tor M. Aamodt

Summary: Architecting Graphics Processors for Non-Graphics Compute Acceleration
Tor M. Aamodt
Dept. of Electrical and Computer Engineering
University of British Columbia, Vancouver, Canada
This paper discusses the emergence of graphics process-
ing units (GPUs) that contain architecture features for ac-
celerating non-graphics (or GPGPU) applications. It pro-
vides an introduction for those interested in undertaking
research at the intersection of manycore computing and
GPU architecture. First, the motivation for using GPUs for
non-graphics processing rather than developing specialized
hardware is outlined. Then, the features of GPU archi-
tectures and related programming models for non-graphics
computing on GPUs are briefly described. Finally, some re-
cent research and architecture challenges related to accel-
erating non-graphics workloads on GPUs are summarized.
1 Introduction
Trends in semiconductor scaling [5, 8] coupled with


Source: Aamodt, Tor - Department of Electrical and Computer Engineering, University of British Columbia


Collections: Engineering; Computer Technologies and Information Sciences