Abstract
Graphical Processing Units (GPUs) have become more accessible peripheral devices with great computing capacity. Moreover, GPUs can be used not only to accelerate the graphics produced by a computer but also for general purpose computing. Many researchers use this technique on their personal workstations to accelerate the execution of their programs and have often encountered that the amount of memory available on GPU cards is typically smaller than the amount of memory available on the host computer. We are interested in exploring approaches to solve problems with this restriction.
Our main contribution is to devise ways in which portions of the problem can be moved to the memory of the GPU to be solved using its multiprocessing capabilities. We implemented on a GPU the Jacobi iterative method to solve systems of linear equations and report the details from the results obtained, analyzing its performance and accuracy. Our code solves a system of linear equations large enough to exceed the card’s memory, but not the host memory. Significant speedups were observed, as the execution time taken to solve each system is faster than those obtained with Intel\(^{\tiny \textregistered }\) MKL and Eigen, libraries designed to work on CPUs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We use initial_row to point the diagonal element. This variable is calculated with respect to the general matrix.
References
Papakonstantinou, A., Gururaj, K., Stratton, J.A., Chen, D., Cong, J., Hwu, W.-M.W.: FCUDA: enabling efficient compilation of CUDA kernels onto FPGAS. In: 2009 IEEE 7th Symposium on Application Specific Processors (2009)
Donno, D.D., Esposito, A., Tarricone, L., Catarinucci, L.: Introduction to GPU computing and CUDA programming: a case study on FDTD [em programmers notebook]. IEEE Antennas Propag. Mag. 52(3), 116–122 (2010)
Tomov, S., Nath, R., Ltaief, H., Dongarra, J.: Dense linear algebra solvers for multicore with GPU accelerators. In: Proceedings of the IEEE IPDPS 2010, 19–23 April 2010, Atlanta, GA, pp. 1–8. IEEE Computer Society (2010). https://doi.org/10.1109/IPDPSW.2010.5470941
Dongarra, J., et al.: Accelerating numerical dense linear algebra calculations with GPUs. In: Kindratenko, V. (ed.) Numerical Computations with GPUs, pp. 3–28. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-06548-9_1
Guennebaud, G., Jacob, B., et al.: Eigen v3 (2010). http://eigen.tuxfamily.org
Intel: Developer reference for intel\(\textregistered \) math kernel library 2018 - c (2017). https://software.intel.com/en-us/mkl-developer-reference-c
NVIDIA: CUDA CUBLAS Library, January 2010
Tomov, S., Dongarra, J., Baboulin, M.: Towards dense linear algebra for hybrid GPU accelerated manycore systems. Parallel Comput. 36, 232–240 (2010)
Jaramillo, J.D., Vidal Maciá, A.M., Correa Zabala, F.J.: Métodos directos para la solución de sistemas de ecuaciones lineales simétricos, indefinidos, dispersos y de gran dimensión. Universidad Eafit (2006)
NVIDIA: CUDA programming guide, January 2010
Correa Zabala, F.J.: Métodos Numéricos, 1st edn. Universidad EAFIT, November 2010
NVIDIA: What is GPU-accelerated computing? http://www.nvidia.com/object/what-is-gpu-computing.html
Flynn, M.: Very high-speed computing systems. Proc. IEEE 54, 1901–1909 (1967)
Almasi, G.S., Gottlieb, A.: Highly Parallel Computing. Benjamin-Cummings Publishing Co., Inc., Redwood City (1989)
Eves, H.: Elementary Matrix Theory, Reprinted edn. Dover Publications Inc., Mineola (1980)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Llano-Ríos, T.F., Ocampo-García, J.D., Yepes-Ríos, J.S., Correa-Zabala, F.J., Trefftz, C. (2018). Solving Large Systems of Linear Equations on GPUs. In: Serrano C., J., Martínez-Santos, J. (eds) Advances in Computing. CCC 2018. Communications in Computer and Information Science, vol 885. Springer, Cham. https://doi.org/10.1007/978-3-319-98998-3_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-98998-3_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-98997-6
Online ISBN: 978-3-319-98998-3
eBook Packages: Computer ScienceComputer Science (R0)