论文信息 - Finite-choice algorithm optimization in Conjugate Gradients∗

Finite-choice algorithm optimization in Conjugate Gradients∗

We present computational aspects of mathematically equivalent implementations of the Conjugate Gradient method. Since the implementations have different performance characteristics, but compute the same quantities, an adaptive implementation can at run time pick the optimal choice.

V. Eijkhout | J. Dongarra

[1] M. Hestenes,et al. Methods of conjugate gradients for solving linear systems , 1952 .

[2] John Van Rosendale. Minimizing Inner Product Data Dependencies in Conjugate Gradient Iteration , 1983, ICPP.

[3] Y. Saad,et al. Practical Use of Polynomial Preconditionings for the Conjugate Gradient Method , 1985 .

[4] Gérard Meurant. Multitasking the conjugate gradient method on the CRAY X-MP/48 , 1987, Parallel Comput..

[5] Anthony T. Chronopoulos,et al. s-step iterative methods for symmetric linear systems , 1989 .

[6] V. Eijkhout. Qualitative Properties of the Conjugate Gradient and Lanczos Methods in a Matrix Framework , 1992 .

[7] Victor Eijkhout,et al. LAPACK Working Note 56: Reducing Communication Costs in the Conjugate Gradient Algorithm on Distributed Memory Multiprocessors , 1993 .

[8] R. Pavani,et al. Parallel Numerical Linear Algebra , 1995, PDP.

[9] Yuefan Deng,et al. New trends in high performance computing , 2001, Parallel Computing.

[10] Jack J. Dongarra,et al. Automated empirical optimizations of software and the ATLAS project , 2001, Parallel Comput..