RT info:eu-repo/semantics/article
T1 Empirical Installation of Linear Algebra Shared-Memory Subroutines for Auto-Tuning
A1 Cámara Moreno, Jesús
A1 Cuenca, Javier
A1 Giménez, Domingo
A1 García, Luis Pedro
A1 Vidal, Antonio M.
K1 Computación Paralela
K1 Auto-Tuning
K1 Linear Algebra Libraries
K1 Empirical Installation
K1 Shared-memory
K1 Auto-tuning
K1 1203 Ciencia de Los Ordenadores
K1 3304 Tecnología de Los Ordenadores
AB The introduction of auto-tuning techniques in linear algebra shared-memory routines is analyzed. Information obtained in the installation of the routines is used at running time to take some decisions to reduce the total execution time. The study is carried out with routines at different levels (matrix multiplication, LU and Cholesky factorizations and linear systems symmetric or general routines) and with calls to routines in the LAPACK and PLASMA libraries with multithread implementations. Medium NUMA and large cc-NUMA systems are used in the experiments. This variety of routines, libraries and systems allows us to obtain general conclusions about the methodology to use for linear algebra shared-memory routines auto-tuning. Satisfactory execution times are obtained with the proposed methodology.
PB Springer
SN 0885-7458
YR 2014
FD 2014
LK https://uvadoc.uva.es/handle/10324/74460
UL https://uvadoc.uva.es/handle/10324/74460
LA eng
NO International Journal of Parallel Programming, 2014, Volume 42, Issue 3, Pages 408-434
NO Producción Científica
DS UVaDOC
RD 05-abr-2025