Parallel processing model for cholesky decomposition algorithm in AlgoWiki project

Alexander S. Antonov; Alexey V. Frolov; Hiroaki Kobayashi; Igor N. Konshin; Alexey M. Teplov; Vadim V. Voevodin; Vladimir V. Voevodin

doi:10.14529/jsfi160307

Parallel processing model for cholesky decomposition algorithm in AlgoWiki project

Alexander S. Antonov, Alexey V. Frolov, Hiroaki Kobayashi, Igor N. Konshin, Alexey M. Teplov, Vadim V. Voevodin, Vladimir V. Voevodin

INF - Computer and Mathematical Sciences

Research output: Contribution to journal › Article › peer-review

9 Citations (Scopus)

Abstract

The comprehensive analysis of algorithmic properties of well-known Cholesky decomposition is performed on the basis of multifold AlgoWiki technologies. A detailed analysis of information graph, data structure, memory access profile, computation locality, scalability and other algorithm properties is conducted, which allows us to demonstrate a lot of unevident properties split up into machine-independent and machine-dependent subsets. The comprehension of the parallel algorithm structure enable us to implement efficiently the algorithm at hardware platform specified.

Original language	English
Pages (from-to)	61-70
Number of pages	10
Journal	Supercomputing Frontiers and Innovations
Volume	3
Issue number	3
DOIs	https://doi.org/10.14529/jsfi160307
Publication status	Published - 2016

Keywords

AlgoWiki
Algorithm properties
Cholesky decomposition
Dynamic characteristics
Memory access locality
Scalability

ASJC Scopus subject areas

Software
Information Systems
Hardware and Architecture
Computer Science Applications
Computer Networks and Communications
Computational Theory and Mathematics

Access to Document

10.14529/jsfi160307

Cite this

@article{ba8d1f2f38b24832a5acb5f8005895d7,

title = "Parallel processing model for cholesky decomposition algorithm in AlgoWiki project",

abstract = "The comprehensive analysis of algorithmic properties of well-known Cholesky decomposition is performed on the basis of multifold AlgoWiki technologies. A detailed analysis of information graph, data structure, memory access profile, computation locality, scalability and other algorithm properties is conducted, which allows us to demonstrate a lot of unevident properties split up into machine-independent and machine-dependent subsets. The comprehension of the parallel algorithm structure enable us to implement efficiently the algorithm at hardware platform specified.",

keywords = "AlgoWiki, Algorithm properties, Cholesky decomposition, Dynamic characteristics, Memory access locality, Scalability",

author = "Antonov, {Alexander S.} and Frolov, {Alexey V.} and Hiroaki Kobayashi and Konshin, {Igor N.} and Teplov, {Alexey M.} and Voevodin, {Vadim V.} and Voevodin, {Vladimir V.}",

note = "Funding Information: The results described in all sections except 2.4 were obtained in the Moscow State University with the financial support of the Russian Science Foundation (agreement No. 14-11-00190). The research presented in section 2.4 was supported by the Russian Foundation for Basic Research (No. 16-07-01003). Numerical experiments were performed in the Supercomputing Center of Lomonosov Moscow State University [14]. Publisher Copyright: {\textcopyright} The Authors 2016.",

year = "2016",

doi = "10.14529/jsfi160307",

language = "English",

volume = "3",

pages = "61--70",

journal = "Supercomputing Frontiers and Innovations",

issn = "2409-6008",

publisher = "South Ural State University",

number = "3",

}

TY - JOUR

T1 - Parallel processing model for cholesky decomposition algorithm in AlgoWiki project

AU - Antonov, Alexander S.

AU - Frolov, Alexey V.

AU - Kobayashi, Hiroaki

AU - Konshin, Igor N.

AU - Teplov, Alexey M.

AU - Voevodin, Vadim V.

AU - Voevodin, Vladimir V.

N1 - Funding Information: The results described in all sections except 2.4 were obtained in the Moscow State University with the financial support of the Russian Science Foundation (agreement No. 14-11-00190). The research presented in section 2.4 was supported by the Russian Foundation for Basic Research (No. 16-07-01003). Numerical experiments were performed in the Supercomputing Center of Lomonosov Moscow State University [14]. Publisher Copyright: © The Authors 2016.

PY - 2016

Y1 - 2016

N2 - The comprehensive analysis of algorithmic properties of well-known Cholesky decomposition is performed on the basis of multifold AlgoWiki technologies. A detailed analysis of information graph, data structure, memory access profile, computation locality, scalability and other algorithm properties is conducted, which allows us to demonstrate a lot of unevident properties split up into machine-independent and machine-dependent subsets. The comprehension of the parallel algorithm structure enable us to implement efficiently the algorithm at hardware platform specified.

AB - The comprehensive analysis of algorithmic properties of well-known Cholesky decomposition is performed on the basis of multifold AlgoWiki technologies. A detailed analysis of information graph, data structure, memory access profile, computation locality, scalability and other algorithm properties is conducted, which allows us to demonstrate a lot of unevident properties split up into machine-independent and machine-dependent subsets. The comprehension of the parallel algorithm structure enable us to implement efficiently the algorithm at hardware platform specified.

KW - AlgoWiki

KW - Algorithm properties

KW - Cholesky decomposition

KW - Dynamic characteristics

KW - Memory access locality

KW - Scalability

UR - http://www.scopus.com/inward/record.url?scp=85032488308&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032488308&partnerID=8YFLogxK

U2 - 10.14529/jsfi160307

DO - 10.14529/jsfi160307

M3 - Article

AN - SCOPUS:85032488308

SN - 2409-6008

VL - 3

SP - 61

EP - 70

JO - Supercomputing Frontiers and Innovations

JF - Supercomputing Frontiers and Innovations

IS - 3

ER -

Parallel processing model for cholesky decomposition algorithm in AlgoWiki project

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this