8468

Efficient implementation of data flow graphs on multi-gpu clusters

Vincent Boulos, Sylvain Huet, Vincent Fristot, Luc Salvo, Dominique Houzet
GIPSA-lab, Image-Signal Department, CNRS UMR 5216, University of Grenoble
Journal of Real-Time Image Processing, 2012
@article{boulos2012efficient,

   title={Efficient implementation of data flow graphs on multi-gpu clusters},

   author={Boulos, V. and Huet, S. and Fristot, V. and Salvo, L. and Houzet, D.},

   journal={Journal of Real-Time Image Processing},

   pages={1–16},

   year={2012},

   publisher={Springer}

}

Download Download (PDF)   View View   Source Source   

1035

views

Nowadays, it is possible to build a multi-GPU supercomputer, well suited for implementation of digital signal processing algorithms, for a few thousand dollars. However, to achieve the highest performance with this kind of architecture, the programmer has to focus on inter-processor communications, tasks synchronization. In this paper, we propose a high level programming model based on a data flow graph (DFG) allowing an efficient implementation of digital signal processing applications on a multi-GPU computer cluster. This DFG-based design flow abstracts the underlying architecture. We focus particularly on the efficient implementation of communications by automating computation-communication overlap, which can lead to significant speedups as shown in the presented benchmark. The approach is validated on three experiments: a multi-host multi-gpu benchmark, a 3D granulometry application developed for research on materials and an application for computing visual saliency maps.
VN:F [1.9.22_1171]
Rating: 0.0/5 (0 votes cast)

* * *

* * *

Follow us on Twitter

HGPU group

1924 peoples are following HGPU @twitter

Like us on Facebook

HGPU group

432 people like HGPU on Facebook

HGPU group © 2010-2016 hgpu.org

All rights belong to the respective authors

Contact us: