6902

Analysis and optimization of power consumption in the iterative solution of sparse linear systems on multi-core and many-core platforms

Hartwig Anzt, Vincent Heuveline, Jose I. Aliaga, Maribel Castillo, Juan C. Fernandez, Rafael Mayo, Enrique S. Quintana-Orti
Institute for Applied and Numerical Mathematics 4, Karlsruhe Institute of Technology, Fritz-Erler-Str. 23, 76133 Karlsruhe, Germany
International Green Computing Conference and Workshops (IGCC), 2011

@inproceedings{anzt2011analysis,

   title={Analysis and optimization of power consumption in the iterative solution of sparse linear systems on multi-core and many-core platforms},

   author={Anzt, H. and Heuveline, V. and Aliaga, J.I. and Castillo, M. and Fernandez, J.C. and Mayo, R. and Quintana-Orti, E.S.},

   booktitle={Green Computing Conference and Workshops (IGCC), 2011 International},

   pages={1–6},

   year={2011},

   organization={IEEE}

}

Download Download (PDF)   View View   Source Source   

2065

views

Energy efficiency is a major concern in modern high-performance-computing. Still, few studies provide a deep insight into the power consumption of scientific applications. Especially for algorithms running on hybrid platforms equipped with hardware accelerators, like graphics processors, a detailed energy analysis is essential to identify the most costly parts, and to evaluate possible improvement strategies. In this paper we analyze the computational and power performance of iterative linear solvers applied to sparse systems arising in several scientific applications. We also study the gains yield by dynamic voltage/frequency scaling (DVFS), and illustrate that this technique alone cannot to reduce the energy cost to a considerable amount for iterative linear solvers. We then apply techniques that set the (multi-core processor in the) host system to a low-consuming state for the time that the GPU is executing. Our experiments conclusively reveal how the combination of these two techniques deliver a notable reduction of energy consumption without a noticeable impact on computational performance.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: