Architecting graphics processors for non-graphics compute acceleration

Tor M. Aamodt
Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, Canada
IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, 2009. PacRim 2009, p.963-968


   title={Architecting graphics processors for non-graphics compute acceleration},

   author={Aamodt, T.M.},

   booktitle={Communications, Computers and Signal Processing, 2009. PacRim 2009. IEEE Pacific Rim Conference on},





Download Download (PDF)   View View   Source Source   



This paper discusses the emergence of graphics processing units (GPUs) that contain architecture features for accelerating non-graphics (or GPGPU) applications. It provides 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 architectures and related programming models for non-graphics computing on GPUs are briefly described. Finally, some recent research and architecture challenges related to accelerating non-graphics workloads on GPUs are summarized.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: