A novel algorithm of optimal matrix partitioning for parallel dense factorization on heterogeneous processors

被引：0

作者：

Lastovetsky, Alexey ^{[1
]}

Reddy, Ravi ^{[1
]}

机构：

[1] Univ Coll Dublin, Sch Informat & Comp Sci, Dublin 4, Ireland

来源：

PARALLEL COMPUTING TECHNOLOGIES, PROCEEDINGS | 2007年 / 4671卷

基金：

爱尔兰科学基金会;

关键词：

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, we present a novel algorithm of optimal matrix partitioning for parallel dense matrix factorization on heterogeneous processors based on their constant performance model. We prove the correctness of the algorithm and estimate its complexity. We demonstrate that this algorithm better suits extensions to more complicated, non-constant, performance models of heterogeneous processors than traditional algorithms.

引用

页码：261 / +

页数：2

共 50 条

[1] Partitioning for Parallel Matrix-Matrix Multiplication with Heterogeneous Processors: The Optimal Solution
DeFlumere, Ashley
Lastovetsky, Alexey
Becker, Brett A.
2012 IEEE 26TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM WORKSHOPS & PHD FORUM (IPDPSW), 2012, : 125 - 139
[2] A New Approximation Algorithm for Matrix Partitioning in Presence of Strongly Heterogeneous Processors
Beaumont, Olivier
Eyraud-Dubois, Lionel
Lambert, Thomas
2016 IEEE 30TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM (IPDPS 2016), 2016, : 474 - 483
[3] Determination of the optimal shape of matrix elements partitioning on three abstract heterogeneous processors
Klyuyeva, Ye. G.
Yavorskij, V. V.
Adamov, A. A.
Utepbergenov, I. T.
COGENT ENGINEERING, 2020, 7 (01):
[4] Searching for the Optimal Data Partitioning Shape for Parallel Matrix Matrix Multiplication on 3 Heterogenous Processors
DeFlumere, Ashley
Lastovetsky, Alexey
PROCEEDINGS OF 2014 IEEE INTERNATIONAL PARALLEL & DISTRIBUTED PROCESSING SYMPOSIUM WORKSHOPS (IPDPSW), 2014, : 17 - 28
[5] Optimal Matrix Partitioning for Data Parallel Computing on Hybrid Heterogeneous Platforms
Malik, Tania
Lastovetsky, Alexey
2020 19TH INTERNATIONAL SYMPOSIUM ON PARALLEL AND DISTRIBUTED COMPUTING (ISPDC 2020), 2020, : 1 - 11
[6] Optimal Data Partitioning Shape for Matrix Multiplication on Three Fully Connected Heterogeneous Processors
DeFlumere, Ashley
Lastovetsky, Alexey
EURO-PAR 2014: PARALLEL PROCESSING WORKSHOPS, PT I, 2014, 8805 : 201 - 214
[7] On grid-based matrix partitioning for heterogeneous processors
Lastovetsky, Alexey
ISPDC 2007: SIXTH INTERNATIONAL SYMPOSIUM ON PARALLEL AND DISTRIBUTED COMPUTING, PROCEEDINGS, 2007, : 383 - 390
[8] Column-Based Matrix Partitioning for Parallel Matrix Multiplication on Heterogeneous Processors Based on Functional Performance Models
Clarke, David
Lastovetsky, Alexey
Rychkov, Vladimir
EURO-PAR 2011: PARALLEL PROCESSING WORKSHOPS, PT I, 2012, 7155 : 450 - 459
[9] Towards Optimal Matrix Partitioning for Data Parallel Computing on a Hybrid Heterogeneous Server
Malik, Tania
Lastovetsky, Alexey
IEEE Access, 2021, 9 : 17229 - 17244
[10] Towards Optimal Matrix Partitioning for Data Parallel Computing on a Hybrid Heterogeneous Server
Malik, Tania
Lastovetsky, Alexey
IEEE ACCESS, 2021, 9 : 17229 - 17244

← 1 2 3 4 5 →