Raquel Cortina

Neville elimination on multi- and many-core systems: OpenMP, MPI and CUDA

This paper describes several parallel algorithmic variations of the Neville elimination. This elimination solves a system of linear equations making zeros in a matrix column by adding to each row an adequate multiple of the preceding one. The parallel algorithms are run and compared on different multi- and many-core platforms using parallel programming techniques as MPI, OpenMP and CUDA.

A study of the performance of Neville elimination using two kinds of partitioning techniques

Abstract In this paper, a method to compute the solution of a system of linear equations by means of Neville elimination is described using two kinds of partitioning techniques: Block and Block-striped. This type of approach is especially suited to the case of totally positive linear systems, which is present in different fields of application. Although Neville elimination carried out more floating point operations than Gaussian elimination in some cases, in this study we confirm that these advantages disappear when we use multiprocessor systems. On the other hand, the overall parallel run time of Neville elimination is better than Gauss time as Neville elimination uses a lower cost communication model.

Block-Striped Partitioning and Neville Elimination

In this paper a message-passing parallel implementation of the solution of linear systems by means of the Neville elimination is described. This type of approach is especially suited to the case of totally positive linear systems, which appears in different application fields. Standard data partitioning techniques, such as block row and block column schemes, are considered on three different topologies: ring, mesh and hypercube. The theoretical performance of the proposed parallel algorithms, in terms of run time, speed-up and efficiency, is derived. Experimental results obtained on an IBM SP2 multicomputer confirm the high performance of the block row parallel algorithm.

Parallel online time warping for real-time audio-to-score alignment in multi-core systems

The audio-to-score framework consists of two separate stages: preprocessing and alignment. The alignment is commonly solved through offline dynamic time warping (DTW), which is a method to find the path over the distortion matrix with the minimum cost to determine the relation between the performance and the musical score times. In this work we propose a parallel online DTW solution based on a client–server architecture. The current version of the application has been implemented for multi-core architectures (

Scalability of Neville elimination using checkerboard partitioning

\times

Detecting point sources in CMB maps using an efficient parallel algorithm

×86,

A Columnwise Block Striping in Neville Elimination

\times