Block Red-Black Ordering Method for Parallel Processing of ICCG Solver

Authors:
Takeshi Iwashita;Masaaki Shimasaki
Affiliations:
-;-
Venue:
ISHPC '02 Proceedings of the 4th International Symposium on High Performance Computing
Year:
2002

Citing 4
Cited 1

The effect of ordering on preconditioned conjugate gradients

BIT
Overlapped multicolor MILU preconditioning

SIAM Journal on Scientific Computing
Developments and trends in the parallel solution of linear systems

Parallel Computing - Special Anniversary issue
Ordering strategies and related techniques to overcome the trade-off between parallelism and convergence in incomplete factorizations

Parallel Computing - Special Anniversary issue

Physical simulation for animation and visual effects: parallelization and characterization for chip multiprocessors

Proceedings of the 34th annual international symposium on Computer architecture

Quantified Score

Hi-index	0.00

Visualization

Abstract

The present paper proposes a new parallel ordering, "block red-black ordering," for a parallelized ICCG solver with fewer synchronization points and a high convergence rate. In the new method, nodes in an analyzed grid are divided into several or many blocks, and red-black ordering is applied to the blocks. Several blocks are assigned to each processor and the substitution is carried out in parallel. Only one synchronization point exists in each parallelized substitution. We performed an analytical investigation using the ordering graph theory and computational tests on a scalar parallel computer. These results show that a convergence rate is improved by an increase in the number of nodes of one block and that a high parallel performance is attained by using an appropriate block size.