Optimization of power consumption in the iterative solution of sparse linear systems on graphics processors

Authors:
Hartwig Anzt;Maribel Castillo;Juan C. Fernández;Vincent Heuveline;Francisco D. Igual;Rafael Mayo;Enrique S. Quintana-Ortí
Affiliations:
Institute for Applied and Numerical Mathematics 4, Karlsruhe Institute of Technology, Karlsruhe, Germany 76133;Depto. de Ingeniería y Ciencia de Computadores, Universidad Jaume I, Castellón, Spain 12.071;Depto. de Ingeniería y Ciencia de Computadores, Universidad Jaume I, Castellón, Spain 12.071;Institute for Applied and Numerical Mathematics 4, Karlsruhe Institute of Technology, Karlsruhe, Germany 76133;Depto. de Ingeniería y Ciencia de Computadores, Universidad Jaume I, Castellón, Spain 12.071;Depto. de Ingeniería y Ciencia de Computadores, Universidad Jaume I, Castellón, Spain 12.071;Depto. de Ingeniería y Ciencia de Computadores, Universidad Jaume I, Castellón, Spain 12.071
Venue:
Computer Science - Research and Development
Year:
2012

Citing 8
Cited 2

GMRES: a generalized minimal residual algorithm for solving nonsymmetric linear systems

SIAM Journal on Scientific and Statistical Computing
Numerical Linear Algebra for High Performance Computers

Numerical Linear Algebra for High Performance Computers
Iterative Methods for Sparse Linear Systems

Iterative Methods for Sparse Linear Systems
Performance and accuracy of hardware-oriented native-, emulated-and mixed-precision solvers in FEM simulations

International Journal of Parallel, Emergent and Distributed Systems
Implementing sparse matrix-vector multiplication on throughput-oriented processors

Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis
The International Exascale Software Project roadmap

International Journal of High Performance Computing Applications
An error correction solver for linear systems: evaluation of mixed precision implementations

VECPAR'10 Proceedings of the 9th international conference on High performance computing for computational science
Power Consumption of Mixed Precision in the Iterative Solution of Sparse Linear Systems

IPDPSW '11 Proceedings of the 2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and PhD Forum

Case studies of multi-core energy efficiency in task based programs

ICT-GLOW'12 Proceedings of the Second international conference on ICT as Key Technology against Global Warming
Energy efficiency vs. performance of the numerical solution of PDEs: An application study on a low-power ARM-based cluster

Journal of Computational Physics

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we analyze the power consumption of different GPU-accelerated iterative solver implementations enhanced with energy-saving techniques. Specifically, while conducting kernel calls on the graphics accelerator, we manually set the host system to a power-efficient idle-wait status so as to leverage dynamic voltage and frequency control. While the usage of iterative refinement combined with mixed precision arithmetic often improves the execution time of an iterative solver on a graphics processor, this may not necessarily be true for the power consumption as well. To analyze the trade-off between computation time and power consumption we compare a plain GMRES solver and its preconditioned variant to the mixed-precision iterative refinement implementations based on the respective solvers. Benchmark experiments conclusively reveal how the usage of idle-wait during GPU-kernel calls effectively leverages the power-tools provided by hardware, and improves the energy performance of the algorithm.