1130

Studying Thermal Management for Graphics-Processor Architectures

J. W. Sheaffer, K. Skadron, D. P. Luebke
Department of Computer Science, The University of Virginia
Performance Analysis of Systems and Software, 2005. ISPASS 2005. IEEE International Symposium on In Performance Analysis of Systems and Software, 2005. ISPASS 2005. IEEE International Symposium on (22 March 2005), pp. 54-65.

@conference{sheaffer2005studying,

   title={Studying thermal management for graphics-processor architectures},

   author={Sheaffer, J.W. and Skadron, K. and Luebke, D.P.},

   booktitle={Performance Analysis of Systems and Software, 2005. ISPASS 2005. IEEE International Symposium on},

   pages={54–65},

   isbn={0780389654},

   year={2005},

   organization={IEEE}

}

We have previously presented Qsilver, a flexible simulation system for graphics architectures. In this paper we describe our extensions to this system, which we use – instrumented with a power model and HotSpot – to analyze the application of standard CPU static and runtime thermal management techniques on the GPU. We describe experiments implementing clock gating, fetch gating, dynamic voltage scaling, multiple clock domains and permuted floor-planning on the GPU using our simulation environment, and demonstrate that these techniques are beneficial in the GPU domain. Further, we show that the inherent parallelism of GPU workloads enables significant thermal gains on chips designed employing static floorplan repartitioning
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: