Job Parallelism using Graphical Processing Unit individual Multi-Processors and Highly Localised Memory

D. P. Playne, K. A. Hawick
Computer Science, Massey University, North Shore 102-904, Auckland, New Zealand
CSTN Computational Science Technical Note Series, Technical Report CSTN-159, 2012


   title={Job parallelism using graphical processing unit individual multiprocessors and highly localised memory},

   author={Playne, D and Hawick, K},


   institution={Tech. Rep. CSTN-159, Computer Science, Massey University}


Download Download (PDF)   View View   Source Source   



Graphical Processing Units(GPUs) are usually programmed to provide data-parallel acceleration to a host processor. Modern GPUs typically have an internal multi-processor (MP) structure that can be exploited in an unusual way to offer semi-independent task parallelism providing the MPs can operate within their own localised memory and apply data-parallelism to their own problem subset. We describe a combined simulation and statistical analysis application using component labelling and benchmark it on a range of modern GPU and CPU devices with various numbers of cores. As well as demonstrating a high degree of job parallelism and throughput we find a typical GPU MP outperforms a conventional CPU core.
No votes yet.
Please wait...

You must be logged in to post a comment.

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: