Downsampling Algorithms for Large Sparse Matrices

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F15%3A00218582" target="_blank" >RIV/68407700:21240/15:00218582 - isvavai.cz</a>

Výsledek na webu

<a href="http://link.springer.com/article/10.1007%2Fs10766-014-0315-8#" target="_blank" >http://link.springer.com/article/10.1007%2Fs10766-014-0315-8#</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s10766-014-0315-8" target="_blank" >10.1007/s10766-014-0315-8</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Downsampling Algorithms for Large Sparse Matrices

Popis výsledku v původním jazyce

Mapping of sparse matrices to processors of a parallel system may have a significant impact on the development of sparse-matrix algorithms and, in effect, to their efficiency. We present and empirically compare two downsampling algorithms for sparse matrices. The first algorithm is independent of particular matrix-processors mapping, while the second one is adapted for cases where matrices are partitioned among processors according to contiguous chunks of rows/columns. We show that the price for the versatility of the first algorithm is the collective communication performed by all processors. The second algorithm uses more efficient communication strategy, which stems from the knowledge of mapping of matrices to processors, and effectively outperformsthe first algorithm in terms of running time.

Název v anglickém jazyce

Downsampling Algorithms for Large Sparse Matrices

Popis výsledku anglicky

Mapping of sparse matrices to processors of a parallel system may have a significant impact on the development of sparse-matrix algorithms and, in effect, to their efficiency. We present and empirically compare two downsampling algorithms for sparse matrices. The first algorithm is independent of particular matrix-processors mapping, while the second one is adapted for cases where matrices are partitioned among processors according to contiguous chunks of rows/columns. We show that the price for the versatility of the first algorithm is the collective communication performed by all processors. The second algorithm uses more efficient communication strategy, which stems from the knowledge of mapping of matrices to processors, and effectively outperformsthe first algorithm in terms of running time.

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

<a href="/cs/project/GAP202%2F12%2F2011" target="_blank" >GAP202/12/2011: Paralelní vstupně/výstupní algoritmy pro rozsáhlé řídké matice</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2015

Kód důvěrnosti údajů

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

Název periodika

International Journal of Parallel Programming

ISSN

0885-7458

e-ISSN

—

Svazek periodika

43

Číslo periodika v rámci svazku

5

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

24

Strana od-do

679-702

Kód UT WoS článku

000358648600001

EID výsledku v databázi Scopus

2-s2.0-84938963170