Fresh from the NVIDIA Numeric Libraries Team, a white paper illustrating the use of the CUSPARSE and CUBLAS libraries to achieve a 2x speedup of incomplete-LU- and Cholesky-preconditioned iterative methods. The paper focuses on the Bi-Conjugate Gradient and stabilized Conjugate Gradient iterative methods that can be used to solve large sparse non-symmetric and symmetric positive definite linear systems, respectively. The paper also comments on the parallel sparse triangular solver, which is an essential building block in these algorithms.
Read the technical review on our NVIDIA Research Site
Download the white paper or the webinar recording discussing this white paper: www.nvidia.com/webinars.