Paper Info
Title
Architecture of an automatically tuned linear algebra library
Abstract
One approach for a hierarchical architecture of a set of linear algebra libraries with self-optimisation capacity is shown. In previous works the optimisation of several routines was studied separately, and in this work the ideas applied to individual routines are combined with the classical hierarchy of linear algebra libraries. Each self-optimised library consists of the former routines of the library and additional special routines which obtain information of the characteristics on the system and tune certain parameters of the former routines accordingly. The relationship between libraries of the different levels of the hierarchy is also strengthened. Just as each routine has in its code different calls to lower levels, so this routine will use the self-optimisation information of these other routines to generate its own information. Experiments with routines of different levels and on different kinds of platforms with constant, variable and heterogeneous load have been carried out. The results obtained allow us to conclude that the proposed methodology is valid for obtaining self-optimised linear algebra libraries.
Year
DOI
Venue
2004
10.1016/j.parco.2003.11.002
Parallel Computing
Keywords
Field
DocType
polylibraries,block methods,different level,linear algebra,former routine,self-optimised linear algebra library,additional special routine,own information,linear algebra library,automatic tuning,different kind,code different call,self-optimisation information,high performance computing,classical hierarchy
Linear algebra,Architecture,Programming language,Supercomputer,Computer science,Parallel computing,Theoretical computer science,Automatic tuning,Hierarchy,Basic Linear Algebra Subprograms
Journal
Volume
Issue
ISSN
30
2
Parallel Computing
Citations 
PageRank 
References 
19
1.72
19
Authors
3
Name
Order
Citations
PageRank
Javier Cuenca114522.48
Domingo Giménez218033.64
José González352635.85