Algebraic block red-black ordering method for parallelized ICCG solver with fast convergence and low communication costs

Proposes a new parallelized incomplete Cholesky conjugate gradient (ICCG) solver effective on a small-scale multiprocessor system. The new method is based on a new reordering technique, namely the block red-black ordering method. Its parallel performance is evaluated in a finite edge-element eddy-cu...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on magnetics 2003-05, Vol.39 (3), p.1713-1716
Main Authors: Iwashita, T., Shimasaki, M.
Format: Article
Language:English
Subjects:
Applied classical electromagnetism
Blocking
Concurrent computing
Convergence
Costs
Electromagnetism
electron and ion optics
Exact sciences and technology
Finite difference methods
Fundamental areas of phenomenology (including applications)
Kernel
Linear systems
Magnetism
Mathematical analysis
Mathematical methods in physics
Mathematical models
Multiprocessing systems
Numerical approximation and analysis
Numerical optimization
Order disorder
Parallel processing
Performance analysis
Physics
Processors
Solvers
Testing
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Proposes a new parallelized incomplete Cholesky conjugate gradient (ICCG) solver effective on a small-scale multiprocessor system. The new method is based on a new reordering technique, namely the block red-black ordering method. Its parallel performance is evaluated in a finite edge-element eddy-current analysis. A numerical test shows that the proposed method is effective on a small number of processors due to fast convergence and low communication costs.
ISSN:0018-9464
1941-0069
DOI:10.1109/TMAG.2003.810531