A Parallel Algebraic Multigrid Solver on Graphics Processing Units

摘要：

The paper presents a multi-GPU implementation of the preconditioned conjugate gradient algorithm with an algebraic multigrid preconditioner (PCG-AMG) for an elliptic model problem on a 3D unstructured grid. An efficient parallel sparse matrix-vector multiplication scheme underlying the PCG-AMg algorithm is presented for the many-core GPU architecture. A performance comparison of the parallel solver shows that a singe Nvidia Tesla C1060 GPU board delivers the performance of a sixteen node Infiniband cluster and a multi-GPU configuration with eight GPUs is about 100 times faster than a typical server CPU core.

作者: Gundolf Haase Manfred Liebmann Craig C. Douglas Gernot Plank

作者单位: Institute for Mathematics and Scientific Computing, University of Graz Institute for Mathematics and Scientific Computing,University of Graz Department of Mathematics, Uni Department of Mathematics, University of Wyoming Computing Laboratory, Oxford University

会议类型: 国际会议

会议名称: The Second International Conference on High Performance Computing and Applications(第二届高性能计算及应用国际会议)

会议地点: 上海

会议语种:英文

页码: 38-47

在线出版日期: 2009-08-10（万方平台首次上网日期，不代表论文的发表时间）