High Performance Recursive Linear Algebra Library

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F09%3A00165009" target="_blank" >RIV/68407700:21240/09:00165009 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

High Performance Recursive Linear Algebra Library

Original language description

For good performance of every computer program, the good cache utilization is crucial. In numerical algebra libraries (such as BLAS or LAPACK) is good cache utilization achieved by explicit loop restructuring (mainly loop blocking), but it requires difficult cache behavior analysis. In this paper, we represent recursive implementation of some routines from numerical algebra library. This implementation leads to good cache utilization with no need to analyze cache behavior due to the "natural" partitionof data.

Czech name

—

Czech description

—

Type

R - Software

CEP classification

IN - Informatics

OECD FORD branch

—

Project

—

Continuities

Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2009

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Internal product ID

RecBLAS1.00

Technical parameters

cca 80-100% výkonnosti knihovny Intel MKL

Economical parameters

—

Owner IČO

68407700

Owner name

Fakulta informačních technologií ČVUT v Praze