Two-level dynamic scheduling in PARDISO: improved scalability on shared memory multiprocessing systems

Authors:
Olaf Schenk;Klaus Gärtner
Affiliations:
Department of Computer Science, University of Basel, Klingelbergstrasse 50, CH-4056 Basel, Switzerland;Weierstrass Institute for Applied Analysis and Stochastics, Mohrenstr 39, D-10117, Berlin, Germany
Venue:
Parallel Computing - Parallel matrix algorithms and applications
Year:
2002

Citing 10
Cited 6

The role of elimination trees in sparse factorization

SIAM Journal on Matrix Analysis and Applications
A supernodal Cholesky factorization algorithm for shared-memory multiprocessors

SIAM Journal on Scientific Computing
An Unsymmetric-Pattern Multifrontal Method for Sparse LU Factorization

SIAM Journal on Matrix Analysis and Applications
A Supernodal Approach to Sparse Partial Pivoting

SIAM Journal on Matrix Analysis and Applications
The Design and Use of Algorithms for Permuting Large Entries to the Diagonal of Sparse Matrices

SIAM Journal on Matrix Analysis and Applications
An Asynchronous Parallel Supernodal Algorithm for Sparse Gaussian Elimination

SIAM Journal on Matrix Analysis and Applications
Algorithm 575: Permutations for a Zero-Free Diagonal [F1]

ACM Transactions on Mathematical Software (TOMS)
Making sparse Gaussian elimination scalable by static pivoting

SC '98 Proceedings of the 1998 ACM/IEEE conference on Supercomputing
PARDISO: a high-performance serial and parallel sparse linear solver in semiconductor device simulation

Future Generation Computer Systems - I. High Performance Numerical Methods and Applications. II. Performance Data Mining: Automated Diagnosis, Adaption, and Optimization
A Fully Asynchronous Multifrontal Solver Using Distributed Dynamic Scheduling

SIAM Journal on Matrix Analysis and Applications

Solving Unsymmetric Sparse Systems of Linear Equations with PARDISO

ICCS '02 Proceedings of the International Conference on Computational Science-Part II
Solving unsymmetric sparse systems of linear equations with PARDISO

Future Generation Computer Systems - Special issue: Selected numerical algorithms
Matching-based preprocessing algorithms to the solution of saddle-point problems in large-scale nonconvex interior-point optimization

Computational Optimization and Applications
PARFES: A method for solving finite element linear equations on multi-core computers

Advances in Engineering Software
Exploiting thread-level parallelism in the iterative solution of sparse linear systems

Parallel Computing
Parallel numerical simulation of seismic waves propagation with intel math kernel library

PARA'12 Proceedings of the 11th international conference on Applied Parallel and Scientific Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The PARDISO package is a mathematical library of OpenMP routines for the parallel direct solution of large sparse linear systems of equations. One objective of PARDISO is to achieve a high efficiency on shared memory multiprocessing systems. A new parallelization strategy based on a dynamic two-level scheduling scheme is therefore explored. The method aims at minimizing cache conflicts and interprocessor communication costs and, at the same time, maximizing processor load balance and Level-3 BLAS performance. The synchronization events are reduced by one order of magnitude compared with a one-level scheduling strategy. This results in an efficient parallel sparse LU decomposition method. An overview of the two-level scheduling algorithm and the key algorithmic features of the solver PARDISO is given, Finally, numerical results and a comparison with another software package demonstrate the performance.