On Algorithmic Variants of Parallel Gaussian Elimination: Comparison of Implementations in Terms of Performance and Numerical Properties

Abstract : Gaussian elimination is a canonical linear algebra procedure for solving linear systems of equations. In the last few years, the algorithm received a lot of attention in an attempt to improve its parallel performance. This article surveys recent developments in parallel implementations of the Gaussian elimination. Five different flavors are investigated. Three of them are based on different strategies for pivoting: partial pivoting, incremental pivoting, and tournament pivoting. The fourth one replaces pivoting with the Random Butterfly Transformation, and finally, an implementation without pivoting is used as a performance baseline. The technique of iterative refinement is applied to recover numerical accuracy when necessary. All parallel implementations are produced using dynamic, superscalar, runtime scheduling and tile matrix layout. Results on two multi-socket multicore systems are presented. Performance and numerical accuracy is analyzed.
Complete list of metadatas

Cited literature [47 references]  Display  Hide  Download

https://hal.inria.fr/hal-00867837
Contributor : Mathieu Faverge <>
Submitted on : Friday, November 15, 2013 - 9:35:22 AM
Last modification on : Thursday, December 13, 2018 - 6:48:05 PM
Long-term archiving on: Sunday, February 16, 2014 - 4:28:26 AM

File

lawn280.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00867837, version 1

Collections

Citation

Simplice Donfack, Jack Dongarra, Mathieu Faverge, Mark Gates, Jakub Kurzak, et al.. On Algorithmic Variants of Parallel Gaussian Elimination: Comparison of Implementations in Terms of Performance and Numerical Properties. [Research Report] 2013. ⟨hal-00867837⟩

Share

Metrics

Record views

493

Files downloads

366