@article {699, title = {A Survey of Recent Developments in Parallel Implementations of Gaussian Elimination}, journal = {Concurrency and Computation: Practice and Experience}, volume = {27}, year = {2015}, month = {2015-04}, pages = {1292-1309}, abstract = {Gaussian elimination is a canonical linear algebra procedure for solving linear systems of equations. In the last few years, the algorithm has received a lot of attention in an attempt to improve its parallel performance. This article surveys recent developments in parallel implementations of Gaussian elimination for shared memory architecture. 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 Partial 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 multisocket multicore systems are presented. Performance and numerical accuracy is analyzed.}, keywords = {Gaussian elimination, lu factorization, Multicore, parallel, plasma, shared memory}, doi = {10.1002/cpe.3306}, author = {Simplice Donfack and Jack Dongarra and Mathieu Faverge and Mark Gates and Jakub Kurzak and Piotr Luszczek and Ichitaro Yamazaki} }