3559

CULA: hybrid GPU accelerated linear algebra routines

John R. Humphrey, Daniel K. Price, Kyle E. Spagnoli, Aaron L. Paolini, Eric J. Kelmelis
EM Photonics, Inc, 51 E Main St, Suite 203, Newark, DE, 19711, ETATS-UNIS
Modeling and Simulation for Defense Systems and Applications V. Edited by Kelmelis, Eric J. Proceedings of the SPIE, Volume 7705, pp. 770502-770502-7 (2010).

@conference{humphrey2010cula,

   title={CULA: hybrid GPU accelerated linear algebra routines},

   author={Humphrey, J.R. and Price, D.K. and Spagnoli, K.E. and Paolini, A.L. and Kelmelis, E.J.},

   booktitle={Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series},

   volume={7705},

   pages={1},

   issn={0277-786X},

   year={2010}

}

Download Download (PDF)   View View   Source Source   Source codes Source codes

Package:

894

views

The modern graphics processing unit (GPU) found in many standard personal computers is a highly parallel math processor capable of nearly 1 TFLOPS peak throughput at a cost similar to a high-end CPU and an excellent FLOPS/watt ratio. High-level linear algebra operations are computationally intense, often requiring O(N3) operations and would seem a natural fit for the processing power of the GPU. Our work is on CULA, a GPU accelerated implementation of linear algebra routines. We present results from factorizations such as LU decomposition, singular value decomposition and QR decomposition along with applications like system solution and least squares. The GPU execution model featured by NVIDIA GPUs based on CUDA demands very strong parallelism, requiring between hundreds and thousands of simultaneous operations to achieve high performance. Some constructs from linear algebra map extremely well to the GPU and others map poorly. CPUs, on the other hand, do well at smaller order parallelism and perform acceptably during low-parallelism code segments. Our work addresses this via hybrid a processing model, in which the CPU and GPU work simultaneously to produce results. In many cases, this is accomplished by allowing each platform to do the work it performs most naturally.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: