Fast Conjugate Gradients with Multiple GPUs

Ali Cevahir, Akira Nukada, Satoshi Matsuoka
Tokyo Institute of Technology
Computational Science – ICCS 2009 (2009), pp. 893-903


   title={Fast conjugate gradients with multiple GPUs},

   author={Cevahir, A. and Nukada, A. and Matsuoka, S.},

   journal={Computational Science–ICCS 2009},





Download Download (PDF)   View View   Source Source   



The limiting factor for efficiency of sparse linear solvers is the memory bandwidth. In this work, we describe a fast Conjugate Gradient solver for unstructured problems, which runs on multiple GPUs installed on a single mainboard. The solver achieves double precision accuracy with single precision GPUs, using a mixed precision iterative refinement algorithm. To achieve high computation speed, we propose a fast sparse matrix-vector multiplication algorithm, which is the core operation of iterative solvers. The proposed multiplication algorithm efficiently utilizes GPU resources via caching, coalesced memory accesses and load balance between running threads. Experiments on wide range of matrices show that our matrix-vector multiplication algorithm achieves up to 11.6 Gflops on single GeForce 8800 GTS card and CG implementation achieves up to 24.6 Gflops with four GPUs.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: