Accelerating Large Scale Image Analyses on Parallel CPU-GPU Equipped Systems

George Teodoro, Tahsin M. Kurc, Tony Pan, Lee Cooper, Jun Kong, Patrick Widener, Joel H. Saltz
Center for Comprehensive Informatics, Emory University, Atlanta, GA 30322
Center for Comprehensive Informatics, Emory University, Technical report CCI-TR-2011-4, 2011


   title={Accelerating Large Scale Image Analyses on Parallel CPU-GPU Equipped Systems},

   author={Teodoro, G. and Kurc, T.M. and Pan, T. and Cooper, L. and Kong, J. and Widener, P. and Saltz, J.H.},



Download Download (PDF)   View View   Source Source   



General-purpose graphical processing units (GPGPUs) have transformed high-performance computing over the past decade. Making great computational power available with reduced cost and power consumption overheads, heterogeneous CPU-GPU-equipped systems have helped to make possible the emerging class of exascale data-intensive applications. Although the theoretical performance achieved by these hybrid systems is impressive, taking practical advantage of this computing power remains a very challenging problem. Most applications are still being deployed to either GPU or CPU, leaving the other resource under or un-utilized. In this paper, we describe techniques for dynamic smart work partitioning, load balancing, and performance-aware task grouping in order to make efficient collaborative use of available CPUs and GPUs. In the context of a largescale image analysis application, our evaluations show that intelligently co-scheduling CPUs and GPUs can significantly improve performance over GPU-only or multi-core CPU-only approaches.
Rating: 2.5/5. From 3 votes.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: