18156

Towards a Unified CPU-GPU code hybridization: A GPU Based Optimization Strategy Efficient on Other Modern Architectures

Ludomir Oteski, Guillaume De Verdiere, Sylvain Contassot-Vivier, Stephane Vialle, Juliet Ryan
ONERA, 91123 Palaiseau, France
hal-01742774, (5 April 2018)

@misc{oteski2018towards,

   title={Towards a Unified CPU–GPU code hybridization: A GPU Based Optimization Strategy Efficient on Other Modern Architectures},

   author={Oteski, Ludomir and De Verdi{`e}re, Guillaume and Contassot-Vivier, Sylvain and Vialle, Stephane and Ryan, Juliet},

   year={2018}

}

Download Download (PDF)   View View   Source Source   

465

views

In this paper, we suggest a different methodology to shorten the code optimization development time while getting a unified code with good performance on different targeted devices. In the scope of this study, experiments are illustrated on a Discontinuous Galerkin code applied to Computational Fluid Dynamics. Tests are performed on CPUs, KNL Xeon-Phi and GPUs where performance comparison confirms that the GPU optimization guideline leads to efficient versions on CPU and Xeon-Phi for this kind of scientific applications. Based on these results, we finally suggest a methodology to end-up with an efficient hybridized CPU-GPU implementation.
Rating: 2.0/5. From 1 vote.
Please wait...

* * *

* * *

HGPU group © 2010-2018 hgpu.org

All rights belong to the respective authors

Contact us: