Load balancing by redundant decomposition and mapping

被引：9

作者：

deRonde, JF

Schoneveld, A

Sloot, PMA

机构：

[1] Department of Mathematics and Computer Science, University of Amsterdam, 1098 SJ Amsterdam

来源：

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE | 1997年 / 12卷 / 05期

关键词：

redundant domain decomposition; mapping; graph based parallel process/processor modelling;

D O I：

10.1016/S0167-739X(97)83341-9

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In this paper a new methodology for load balancing parallel processes on parallel systems is proposed. The problem of load balancing is considered to be an NP-hard optimization task. Taking static parallel finite element applications as a case study, the benefits and losses that follow from applying the methodology are studied. It is found that the proposed methodology can be especially useful for load balancing in asymmetric processor topologies, and therefore is of importance for work load balancing in workstation clusters.

引用

页码：391 / 406

页数：16

共 28 条

[1]

AARTS EHL, 1990, PARALLEL PROBLEM SOL, V1, P4

[2]

Azencott R., 1992, SIMULATED ANNEALING

[3]

BENNO J, 1996, FUTURE GENERATION CO

[4]

Bovet D. P., 1994, INTRO THEORY COMPLEX

[5] LOAD BALANCING DATA-PARALLEL PROGRAMS ON DISTRIBUTED-MEMORY COMPUTERS [J].

DEKEYSER, J ;

ROOSE, D .

PARALLEL COMPUTING, 1993, 19 (11) :1199-1219

[6]

DEMES A, 1994, CAMASTR2114 U AMST

[7]

DERONDE JF, 1994, MASSIVELY PARALLEL PROCESSING APPLICATIONS AND DEVELOPMENT, P381

[8]

DERONDE JF, 1996, LECT NOTES COMPUTER, V1067, P555, DOI DOI 10.1007/3-540-61142-8_596

[9]

DERONDE JF, 1996, CS9603 U AMST

[10]

FLOROS N, 1995, TR2228 U SOUTH CAM

← 1 2 3 →