Cited By
View all- Torun TTorun FManguoglu MAykanat C(2022)Partitioning and Reordering for Spike-Based Distributed-Memory Parallel Gauss--SeidelSIAM Journal on Scientific Computing10.1137/21M141160344:2(C99-C123)Online publication date: 1-Jan-2022
A Feature-complete SPIKE Dense Banded Solver
Article No.: 36, Pages 1 - 35
Abstract
This article presents a parallel, effective, and feature-complete recursive SPIKE algorithm that achieves near feature-parity with the standard linear algebra package banded linear system solver. First, we present a flexible parallel implementation of the recursive SPIKE scheme that aims at removing its original limitation that the number of cores/processors be restricted to powers of two. A new transpose solve option for SPIKE is then developed to satisfy a standard requirement of most numerical solver libraries. Finally, a pivoting recursive SPIKE strategy is presented as an alternative to the non-pivoting scheme to improve numerical stability. All these new enhancements lead to the release of a new black-box feature-complete SPIKE-OpenMP package that significantly improves upon the performance and scalability obtained with other state-of-the-art banded solvers.
References
[1]
E. Anderson, Z. Bai, J. Dongarra, A. Greenbaum, A. McKenney, J. Du Croz, S. Hammarling, J. Demmel, C. Bischof, and D. Sorensen. 1990. LAPACK: A portable linear algebra library for high-performance computers. In Proceedings of the ACM/IEEE Conference on Supercomputing (Supercomputing’90). IEEE Computer Society Press, Los Alamitos, CA, 2--11. Retrieved from http://dl.acm.org/citation.cfm?id=110382.110385.
[2]
M. W. Berry and A. H. Sameh. 1988. Multiprocessor schemes for solving block tridiagonal linear systems. Int. J. Supercomput. Appl. 2, 3 (1988), 37--57.
[3]
L. S. Blackford, J. Choi, A. Cleary, E. D’Azeuedo, J. Demmel, I. Dhillon, S. Hammarling, G. Henry, A. Petitet, K. Stanley, D. Walker, and R. C. Whaley. 1997. ScaLAPACK User’s Guide. Society for Industrial and Applied Mathematics, Philadelphia, PA.
[4]
L.-W. Chang, J. A. Stratton, H.-S. Kim, and W.-M. W. Hwu. 2012. A scalable, numerically stable, high-performance tridiagonal solver using GPUs. In Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (SC’12). IEEE Computer Society Press, Los Alamitos, CA, Article 27, 11 pages. Retrieved from http://dl.acm.org/citation.cfm?id=2388996.2389033.
[5]
S. C. Chen, D. J. Kuck, and A. H. Sameh. 1978. Practical parallel band triangular system solvers. ACM Trans. Math. Softw. 4, 3 (Sept. 1978), 270--277.
[6]
E. Cuthill and J. McKee. 1969. Reducing the bandwidth of sparse symmetric matrices. In Proceedings of the 1969 24th National Conference (ACM’69). ACM, New York, NY, 157--172.
[7]
J. J. Dongarra and A. H. Sameh. 1984. On some parallel banded system solvers. Parallel Comput. 1, 3–4 (Dec. 1984), 223--235.
[8]
J. Du Croz, P. Mayes, and G. Radicati. 1990. Factorizations of Band Matrices Using Level 3 BLAS. Technical Report 21. LAPACK Working Note. Retrieved from http://www.netlib.org/lapack/lawnspdf/lawn21.pdf.
[9]
V. Eijkhout and R. van de Geijn. 2012. The spike factorization as a domain decomposition method: Equivalent and variant approaches. In High-Performance Scientific Computing: Algorithms and Applications, M. W. Berry, K. A. Gallivan, E. Gallopoulos, A. Grama, B. Philippe, Y. Saad, and F. Saied (Eds.). Springer, London, 157--170.
[10]
FEAST-library. 2009-2020. FEAST Eigenvalue Solver. Retrieved from http://www.feast-solver.org/.
[11]
K. A. Gallivan, E. Gallopoulos, A. Grama, B. Philippe, E. Polizzi, Y. Saad, F. Saied, and D. Sorensen. 2012. Parallel numerical computing from Illiac IV to exascale—The contributions of Ahmed H. Sameh. In High-Performance Scientific Computing: Algorithms and Applications, M. W. Berry, K. A. Gallivan, E. Gallopoulos, A. Grama, B. Philippe, Y. Saad, and F. Saied (Eds.). Springer, London, 1--44.
[12]
E. Gallopoulos, P. Bernard, and A. H. Sameh. 2016. Parallelism in Matrix Computations. Springer.
[13]
N. J. Higham. 2002. Accuracy and Stability of Numerical Algorithms. Society for Industrial and Applied Mathematics, Philadelphia, PA, Chapter 9, 157--193.
[14]
J. Kestyn, E. Polizzi, and P. T. P. Tang. 2016. Feast eigensolver for non-hermitian problems. SIAM J. Sci. Comput. 38, 5 (2016).
[15]
D. H. Lawrie and A. H. Sameh. 1984. The computation and communication complexity of a parallel banded system solver. ACM Trans. Math. Softw. 10, 2 (May 1984), 185--195.
[16]
A. Li, A. Seidl, R. Serban, and D. Negrut. 2014. SPIKE::GPU—A SPIKE-based Preconditioned GPU Solver for Sparse Linear Systems. Technical Report.
[17]
M. Manguoglu, M. Koyutürk, A. H. Sameh, and A. Grama. 2010. Weighted matrix ordering and parallel banded preconditioners for iterative linear system solvers. SIAM J. Sci. Comput. 32, 3 (2010), 1201--1216.
[18]
M. Manguoglu, F. Saied, A. H. Sameh, and A. Grama. 2011. Performance models for the Spike banded linear system solver. Sci. Program. 19, 1 (2011), 13--25.
[19]
M. Manguoglu, A. H. Sameh, and O. Schenk. 2009. PSPIKE: A parallel hybrid sparse linear system solver. In Proceedings of the International Conference on Parallel Computing (Euro-Par’09), Henk Sips, Dick Epema, and Hai-Xiang Lin (Eds.). Springer, Berlin, 797--808.
[20]
K. Mendiratta and E. Polizzi. 2011. A threaded “SPIKE” algorithm for solving general banded systems. Parallel Comput. 37, 12 (2011), 733--741.
[21]
C. Mikkelsen and M. Manguoglu. 2009. Analysis of the truncated SPIKE algorithm. SIAM J. Matrix Anal. Appl. 30, 4 (2009), 1500--1519.
[22]
M. Naumov, M. Manguoglu, and A. H. Sameh. 2010. A tearing-based hybrid parallel sparse linear system solver. J. Comput. Appl. Math. 234, 10 (2010), 3025--3038.
[23]
E. Polizzi. 2009. Density-matrix-based algorithm for solving eigenvalue problems. Phys. Rev. B 79 (Mar. 2009), 115112. Issue 11.
[24]
E. Polizzi. 2011. SPIKE. In Encyclopedia of Parallel Computing, D. Padua (Ed.). Springer U.S., 1912--1920.
[25]
E. Polizzi. 2020. FEAST eigenvalue solver v4.0 user guide. Retrieved from arxiv:cs.MS/2002.04807.
[26]
E. Polizzi and N. Ben Abdallah. 2005. Subband decomposition approach for the simulation of quantum electron transport in nanostructures. J. Comput. Phys. 202, 1 (Jan. 2005), 150--180.
[27]
E. Polizzi and A. Sameh. 2006. A parallel hybrid banded system solver: The SPIKE algorithm. Parallel Comput. 32, 2 (2006), 177--194.
[28]
E. Polizzi and A. Sameh. 2007. SPIKE: A parallel environment for solving banded linear systems. Comput. Fluids 36, 1 (2007), 113--120.
[29]
A. H. Sameh and D. J. Kuck. 1978. On stable parallel linear system solvers. J. ACM 25, 1 (Jan. 1978), 81--91.
[30]
A. H. Sameh and V. Sarin. 1999. Hybrid parallel linear system solvers. Int. J. Comput. Fluid Dynam. 12, 3–4 (1999), 213--223.
[31]
SPIKE-library. 2018. SPIKE shared-memory solver, v1.0. Retrieved from http://www.spike-solver.org/.
[32]
SPIKE-MPI-library. 2011. Intel Adaptive Spike-based Solver. Retrieved from https://software.intel.com/en-us/articles/intel-adaptive-spike-based-solver/.
[33]
B. S. Spring. 2014. Enhanced Capabilities of the Spike Algorithm and a New Spike-OpenMP Solver. Master’s thesis. University of Massachusetts, Amherst. Retrieved from http://scholarworks.umass.edu/masters_theses_2/116.
[34]
Ioannis E. Venetis, Alexandros Kouris, Alexandros Sobczyk, Efstratios Gallopoulos, and Ahmed H. Sameh. 2015. A direct tridiagonal solver based on Givens rotations for GPU architectures. Parallel Comput. 49 (2015), 101--116.
Index Terms
- A Feature-complete SPIKE Dense Banded Solver
Recommendations
A parallel hybrid banded system solver: the SPIKE algorithm
Parallel matrix algorithms and applications (PMAA'04)This paper describes an efficient and robust hybrid parallel solver ''the SPIKE algorithm'' for narrow-banded linear systems. Two versions of SPIKE with their built-in-options are described in detail: the Recursive SPIKE version for handling non-...
The Snap-Back Pivoting Method for Symmetric Banded Indefinite Matrices
The four existing stable factorization methods for symmetric indefinite matrices suffer serious defects when applied to banded matrices. Partial pivoting (row or column exchanges) maintains a band structure in the reduced matrix and the factors, but ...
A fast algorithm for solving banded Toeplitz systems
A fast algorithm for solving systems of linear equations with banded Toeplitz matrices is presented. This new approach is based on extending the given matrix with several rows on the top and several columns on the right and to assign zeros and some ...
Comments
Information & Contributors
Information
Published In
December 2020
272 pages
ISSN:0098-3500
EISSN:1557-7295
DOI:10.1145/3430683
- Editors:
- Zhaojun Bai,
- Wolfgang Bangerth
Copyright © 2020 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 16 October 2020
Accepted: 01 July 2020
Revised: 01 July 2020
Received: 01 November 2018
Published in TOMS Volume 46, Issue 4
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed
Funding Sources
- NSF
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 201Total Downloads
- Downloads (Last 12 months)75
- Downloads (Last 6 weeks)10
Reflects downloads up to 22 Sep 2024
Other Metrics
Citations
Cited By
View all- Torun TTorun FManguoglu MAykanat C(2022)Partitioning and Reordering for Spike-Based Distributed-Memory Parallel Gauss--SeidelSIAM Journal on Scientific Computing10.1137/21M141160344:2(C99-C123)Online publication date: 1-Jan-2022
View Options
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML FormatGet Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in