Iterative Methods for Sparse Linear Systems on Graphics Processing Unit

被引:15
作者
Ahamed, Abal-Kassim Cheik [1 ]
Magoules, Frederic [1 ]
机构
[1] Ecole Cent Paris, Appl Math & Syst Lab, Chatenay Malabry, France
来源
2012 IEEE 14TH INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING AND COMMUNICATIONS & 2012 IEEE 9TH INTERNATIONAL CONFERENCE ON EMBEDDED SOFTWARE AND SYSTEMS (HPCC-ICESS) | 2012年
关键词
Krylov methods; linear algebra; sparse matrix-vector multiplication; graphics processing unit; CUDA; CUBLAS; CUSPARSE; Cusp; DOMAIN DECOMPOSITION METHODS;
D O I
10.1109/HPCC.2012.118
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Many engineering and science problems require a computational effort to solve large sparse linear systems. Krylov subspace based iterative solvers have been widely used in that direction. Iterative Krylov methods involve linear algebra operations such as summation of vectors, dot product, norm, and matrix-vector multiplication. Since these operations could be very costly in computation time on Central Processing Unit (CPU), we propose in this paper to focus on the design of iterative solvers to take advantage of massive parallelism of Graphics Processing Unit (GPU). We consider Stabilized BiConjugate Gradient (BiCGStab), Stabilized BiConjugate Gradient (L) (BiCGStabl), Generalized Conjugate Residual (P-GCR), Bi-Conjugate Gradient Conjugate Residual (P-BiCGCR), transpose-free Quasi Minimal Residual (P-tfQMR) for the solution of sparse linear systems with non symmetric matrices and Conjugate Gradient (CG) for symmetric positive definite matrices. We discuss data format and data structure for sparse matrices, and how to efficiently implement these solvers on the Nvidia's CUDA platform. The scalability and performance of the methods are tested on several engineering problems, together with numerous numerical experiments which clearly illustrate the robustness, competitiveness and efficiency of our own proper implementation compared to the existing libraries.
引用
收藏
页码:836 / 842
页数:7
相关论文
共 50 条
  • [41] Accelerating adaptive inverse distance weighting interpolation algorithm on a graphics processing unit
    Mei, Gang
    Xu, Liangliang
    Xu, Nengxiong
    [J]. ROYAL SOCIETY OPEN SCIENCE, 2017, 4 (09):
  • [42] Implementation of the Sampling Importance Resampling Particle Filter Algorithm in Graphics Processing Unit
    Dulger, Ozcan
    Oguztuzun, Halit
    Demirekler, Mubeccel
    [J]. 2015 23RD SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2015, : 2195 - 2198
  • [43] COMPRESSED MULTIROW STORAGE FORMAT FOR SPARSE MATRICES ON GRAPHICS PROCESSING UNITS
    Koza, Zbigniew
    Matyka, Maciej
    Szkoda, Sebastian
    Miroslaw, Lukasz
    [J]. SIAM JOURNAL ON SCIENTIFIC COMPUTING, 2014, 36 (02) : C219 - C239
  • [44] Graphics processing unit acceleration of the red/black SOR method
    Konstantinidis, Elias
    Cotronis, Yiannis
    [J]. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2013, 25 (08) : 1107 - 1120
  • [45] Efficient Nonbonded Interactions for Molecular Dynamics on a Graphics Processing Unit
    Eastman, Peter
    Pande, Vijay S.
    [J]. JOURNAL OF COMPUTATIONAL CHEMISTRY, 2010, 31 (06) : 1268 - 1272
  • [46] Fast motion estimation for HEVC on graphics processing unit (GPU)
    Dongkyu Lee
    Donggyu Sim
    Keeseong Cho
    Seoung-Jun Oh
    [J]. Journal of Real-Time Image Processing, 2016, 12 : 549 - 562
  • [48] Air pollution modelling using a Graphics Processing Unit with CUDA
    Molnar, F., Jr.
    Szakaly, T.
    Meszaros, R.
    Lagzi, I.
    [J]. COMPUTER PHYSICS COMMUNICATIONS, 2010, 181 (01) : 105 - 112
  • [49] Memory Coalescing Implementation of Metropolis Resampling on Graphics Processing Unit
    Dulger, Ozcan
    Oguztuzun, Halit
    Demirekler, Mubeccel
    [J]. JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2018, 90 (03): : 433 - 447
  • [50] Adaptation of fluid model EULAG to graphics processing unit architecture
    Rojek, Krzysztof Andrzej
    Ciznicki, Milosz
    Rosa, Bogdan
    Kopta, Piotr
    Kulczewski, Michal
    Kurowski, Krzysztof
    Piotrowski, Zbigniew Pawel
    Szustak, Lukasz
    Wojcik, Damian Karol
    Wyrzykowski, Roman
    [J]. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2015, 27 (04) : 937 - 957