Accelerating Scientific Computations with Mixed Precision Algorithms

Autor: Baboulin, Marc, Buttari, Alfredo, Dongarra, Jack, Kurzak, Jakub, Langou, Julie, Langou, Julien, Luszczek, Piotr, Tomov, Stanimire

On modern architectures, the performance of 32-bit operations is often at least twice as fast as the performance of 64-bit operations. By using a combination of 32-bit and 64-bit floating point arithmetic, the performance of many dense and sparse lin

Externí odkaz: http://arxiv.org/abs/0808.2794

Rectangular Full Packed Format for Cholesky's Algorithm: Factorization, Solution and Inversion are already in LAPACK

Autor: Gustavson, Fred G., Wasniewski, Jerzy, Dongarra, Jack J., Langou, Julie

Publikováno v: Gustavson, F G, Wasniewski, J, Dongarra, J J & Langou, J 2009, Rectangular Full Packed Format for Cholesky's Algorithm: Factorization, Solution and Inversion are already in LAPACK . Technical University of Denmark, DTU Informatics, Building 321, Kongens Lyngby .

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______1202::bfb272b7e0b1689f8fd0c7d67bb381f3
http://orbit.dtu.dk/en/publications/rectangular-full-packed-format-for-choleskys-algorithm-factorization-solution-and-inversion-are-already-in-lapack(afcc22c7-1856-48df-8af2-81dc36a65bea).html

Exploiting the performance of 32 bit floating point arithmetic in obtaining 64 bit accuracy (revisiting iterative refinement for linear systems).

Autor: Langou, Julie, Langou, Julien, Luszczek, Piotr, Kurzak, Jakub, Buttari, Alfredo, Dongarra, Jack

Publikováno v: ACM/IEEE SC 2006 Conference (SC'06); Nov2006, p113-es, 1p