A group-based load balance scheme for software distributed shared memory systems

Yi Chang Zhuang, Tyng Yue Liang, Ce-Kuen Shieh, Jun Qi Lee, Laurence Tianruo Yang

研究成果: Article

7 引文 (Scopus)

摘要

Load balance is an important issue for the performance of software distributed shared memory (DSM) systems. One solution of addressing this issue is exploiting dynamic thread migration. In order to reduce the data consistency communication increased by thread migration, an effective load balance scheme must carefully choose threads and destination nodes for workload migration. In this paper, a group-based load balance scheme is proposed to resolve this problem. The main characteristic of this scheme is to classify the overloaded nodes and the lightly loaded nodes into a sender group and a receiver group, and then consider all the threads of the sender group and all the nodes of the receiver group for each decision. The experimental results show that the group-based scheme reduces more communication than the previous schemes. Besides, this paper also resolves the problem of the high costs caused by group-based schemes. Therefore, the performance of the test programs is effectively enhanced after minimizing the communication increased by thread migration.

原文English
頁(從 - 到)295-309
頁數15
期刊Journal of Supercomputing
28
發行號3
DOIs
出版狀態Published - 2004 六月 1

指紋

Distributed Shared Memory
Load Balance
Computer systems
Thread
Data storage equipment
Software
Communication
Migration
Vertex of a graph
Resolve
Receiver
Data Consistency
Costs
Workload
Choose
Classify
Experimental Results

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Information Systems
  • Hardware and Architecture

引用此文

Zhuang, Yi Chang ; Liang, Tyng Yue ; Shieh, Ce-Kuen ; Lee, Jun Qi ; Yang, Laurence Tianruo. / A group-based load balance scheme for software distributed shared memory systems. 於: Journal of Supercomputing. 2004 ; 卷 28, 編號 3. 頁 295-309.
@article{4f6e2c9862744d94b6d4d77a6498473c,
title = "A group-based load balance scheme for software distributed shared memory systems",
abstract = "Load balance is an important issue for the performance of software distributed shared memory (DSM) systems. One solution of addressing this issue is exploiting dynamic thread migration. In order to reduce the data consistency communication increased by thread migration, an effective load balance scheme must carefully choose threads and destination nodes for workload migration. In this paper, a group-based load balance scheme is proposed to resolve this problem. The main characteristic of this scheme is to classify the overloaded nodes and the lightly loaded nodes into a sender group and a receiver group, and then consider all the threads of the sender group and all the nodes of the receiver group for each decision. The experimental results show that the group-based scheme reduces more communication than the previous schemes. Besides, this paper also resolves the problem of the high costs caused by group-based schemes. Therefore, the performance of the test programs is effectively enhanced after minimizing the communication increased by thread migration.",
author = "Zhuang, {Yi Chang} and Liang, {Tyng Yue} and Ce-Kuen Shieh and Lee, {Jun Qi} and Yang, {Laurence Tianruo}",
year = "2004",
month = "6",
day = "1",
doi = "10.1023/B:SUPE.0000022101.41799.cc",
language = "English",
volume = "28",
pages = "295--309",
journal = "Journal of Supercomputing",
issn = "0920-8542",
publisher = "Springer Netherlands",
number = "3",

}

A group-based load balance scheme for software distributed shared memory systems. / Zhuang, Yi Chang; Liang, Tyng Yue; Shieh, Ce-Kuen; Lee, Jun Qi; Yang, Laurence Tianruo.

於: Journal of Supercomputing, 卷 28, 編號 3, 01.06.2004, p. 295-309.

研究成果: Article

TY - JOUR

T1 - A group-based load balance scheme for software distributed shared memory systems

AU - Zhuang, Yi Chang

AU - Liang, Tyng Yue

AU - Shieh, Ce-Kuen

AU - Lee, Jun Qi

AU - Yang, Laurence Tianruo

PY - 2004/6/1

Y1 - 2004/6/1

N2 - Load balance is an important issue for the performance of software distributed shared memory (DSM) systems. One solution of addressing this issue is exploiting dynamic thread migration. In order to reduce the data consistency communication increased by thread migration, an effective load balance scheme must carefully choose threads and destination nodes for workload migration. In this paper, a group-based load balance scheme is proposed to resolve this problem. The main characteristic of this scheme is to classify the overloaded nodes and the lightly loaded nodes into a sender group and a receiver group, and then consider all the threads of the sender group and all the nodes of the receiver group for each decision. The experimental results show that the group-based scheme reduces more communication than the previous schemes. Besides, this paper also resolves the problem of the high costs caused by group-based schemes. Therefore, the performance of the test programs is effectively enhanced after minimizing the communication increased by thread migration.

AB - Load balance is an important issue for the performance of software distributed shared memory (DSM) systems. One solution of addressing this issue is exploiting dynamic thread migration. In order to reduce the data consistency communication increased by thread migration, an effective load balance scheme must carefully choose threads and destination nodes for workload migration. In this paper, a group-based load balance scheme is proposed to resolve this problem. The main characteristic of this scheme is to classify the overloaded nodes and the lightly loaded nodes into a sender group and a receiver group, and then consider all the threads of the sender group and all the nodes of the receiver group for each decision. The experimental results show that the group-based scheme reduces more communication than the previous schemes. Besides, this paper also resolves the problem of the high costs caused by group-based schemes. Therefore, the performance of the test programs is effectively enhanced after minimizing the communication increased by thread migration.

UR - http://www.scopus.com/inward/record.url?scp=3543067536&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=3543067536&partnerID=8YFLogxK

U2 - 10.1023/B:SUPE.0000022101.41799.cc

DO - 10.1023/B:SUPE.0000022101.41799.cc

M3 - Article

AN - SCOPUS:3543067536

VL - 28

SP - 295

EP - 309

JO - Journal of Supercomputing

JF - Journal of Supercomputing

SN - 0920-8542

IS - 3

ER -