About: Recursive Implementation of High Performance Numerical Algebra Library

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Recursive Implementation of High Performance Numerical Algebra Library Goto Sponge Distinct Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Vysledek, within Data Space : linked.opendata.cz associated with source document(s)

Attributes	Values
rdf:type	skos:Concept http://linked.opendata.cz/ontology/domain/vavai/Vysledek
rdfs:seeAlso	http://shimi.webzdarma.cz/vyzkum/workshop06/Recursive_workshop.doc
Description	For a good performance of every computer program, the efficient cache utilization is crucial. In numerical algebra libraries (such as BLAS or LAPACK) is the good cache utilization achieved by the explicit loop restructuring. It includes loop unrolling-and-jam which increase the FPU pipeline utilization in the innermost loop, loop blocking (that is why we called these codes shortly blocked) and loop interchange to maximize the a cache hit ratio. After application of these transformations, these codes are divided into two parts. Outer loops are %22out-cache%22, inner loops are %22in-cache%22. Codes have almost the same performance independently on the amount of data, but all these code transformations require the difficult cache behavior analysis. In this paper, we represent the recursive implementation of some routines from the numerical algebra library. This implementation leads to cache-sensitive codes due to the %22natural%22 partition of data without need to analyze the cache behavior. For a good performance of every computer program, the efficient cache utilization is crucial. In numerical algebra libraries (such as BLAS or LAPACK) is the good cache utilization achieved by the explicit loop restructuring. It includes loop unrolling-and-jam which increase the FPU pipeline utilization in the innermost loop, loop blocking (that is why we called these codes shortly blocked) and loop interchange to maximize the a cache hit ratio. After application of these transformations, these codes are divided into two parts. Outer loops are %22out-cache%22, inner loops are %22in-cache%22. Codes have almost the same performance independently on the amount of data, but all these code transformations require the difficult cache behavior analysis. In this paper, we represent the recursive implementation of some routines from the numerical algebra library. This implementation leads to cache-sensitive codes due to the %22natural%22 partition of data without need to analyze the cache behavior. (en)
Title	Recursive Implementation of High Performance Numerical Algebra Library Recursive Implementation of High Performance Numerical Algebra Library (en)
skos:prefLabel	Recursive Implementation of High Performance Numerical Algebra Library Recursive Implementation of High Performance Numerical Algebra Library (en)
skos:notation	RIV/68407700:21230/06:00114523!RIV12-MSM-21230___
http://linked.open...avai/riv/aktivita	P Z
http://linked.open...avai/riv/aktivity	P(IBS3086102), Z(MSM6840770014)
http://linked.open...vai/riv/dodaniDat	2012
http://linked.open...aciTvurceVysledku	Šimeček, Ivan
http://linked.open.../riv/druhVysledku	D - Článek ve sborníku
http://linked.open...iv/duvernostUdaju	S - Úplné a pravdivé údaje nepodléhající ochraně podle zvláštních právních předpisů
http://linked.open...titaPredkladatele	České vysoké učení technické v Praze / Fakulta elektrotechnická
http://linked.open...dnocenehoVysledku	496752
http://linked.open...ai/riv/idVysledku	RIV/68407700:21230/06:00114523
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	High Performance; cache utilization; numerical algebra library; recursive implementation (en)
http://linked.open.../riv/klicoveSlovo	numerical algebra library High Performance cache utilization recursive implementation
http://linked.open...ontrolniKodProRIV	[B8E9E1B36DD1]
http://linked.open...v/mistoKonaniAkce	Praha
http://linked.open...i/riv/mistoVydani	Praha
http://linked.open...i/riv/nazevZdroje	Proceedings of Workshop 2006
http://linked.open...in/vavai/riv/obor	IN
http://linked.open...ichTvurcuVysledku	1 (xsd:int)
http://linked.open...cetTvurcuVysledku	1 (xsd:int)
http://linked.open...vavai/riv/projekt	Parallel Algorithms for Large Scale Simulation on PC Clusters
http://linked.open...UplatneniVysledku	2006
http://linked.open...iv/tvurceVysledku	Šimeček, Ivan
http://linked.open...vavai/riv/typAkce	EUR - Evropská
http://linked.open.../riv/zahajeniAkce	2006-02-20 (xsd:date)
http://linked.open...n/vavai/riv/zamer	Výzkum perspektivních informačních a komunikačních technologií
number of pages	2 (xsd:int)
http://purl.org/ne...btex#hasPublisher	České vysoké učení technické v Praze
https://schema.org/isbn	80-01-03439-9
http://localhost/t...ganizacniJednotka	21230

Faceted Search & Find service v1.16.118 as of Jun 21 2024

Alternative Linked Data Documents: ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 112 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software