Proteus

A runtime reconfigurable distributed shared memory system

Jyh Chang Ueng, Ce-Kuen Shieh, Wu Hwa Liu, Chi Chang Lin

Research output: Contribution to journal › Article

1 Citation (Scopus)

Abstract

This paper describes a Distributed Shared Memory (DSM) system called Proteus, which aims to support runtime node reconfiguration. To make the system execute efficiently after node reconfiguration and reduce the overhead of reconfiguration, Proteus employs an adaptive workload redistribution strategy to perform workload redistribution as well as an affinity page movement strategy to redistribute memory pages. Furthermore, a forced update technique and a set of scalable synchronization mechanisms are developed to keep memory consistent and to perform a correct synchronization, respectively.

Original languageEnglish
Pages (from-to)347-348
Number of pages2
JournalIEEE International Symposium on High Performance Distributed Computing, Proceedings
Publication statusPublished - 1999

Fingerprint

Computer systems
Data storage equipment
Synchronization

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture

Cite this

Ueng, Jyh Chang ; Shieh, Ce-Kuen ; Liu, Wu Hwa ; Lin, Chi Chang. / Proteus : A runtime reconfigurable distributed shared memory system. In: IEEE International Symposium on High Performance Distributed Computing, Proceedings. 1999 ; pp. 347-348.
@article{9dcf073ca6b346029c21163a5276ea95,
title = "Proteus: A runtime reconfigurable distributed shared memory system",
abstract = "This paper describes a Distributed Shared Memory (DSM) system called Proteus, which aims to support runtime node reconfiguration. To make the system execute efficiently after node reconfiguration and reduce the overhead of reconfiguration, Proteus employs an adaptive workload redistribution strategy to perform workload redistribution as well as an affinity page movement strategy to redistribute memory pages. Furthermore, a forced update technique and a set of scalable synchronization mechanisms are developed to keep memory consistent and to perform a correct synchronization, respectively.",
author = "Ueng, {Jyh Chang} and Ce-Kuen Shieh and Liu, {Wu Hwa} and Lin, {Chi Chang}",
year = "1999",
language = "English",
pages = "347--348",
journal = "IEEE International Symposium on High Performance Distributed Computing, Proceedings",
issn = "1082-8907",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Ueng, JC, Shieh, C-K, Liu, WH & Lin, CC 1999, 'Proteus: A runtime reconfigurable distributed shared memory system', IEEE International Symposium on High Performance Distributed Computing, Proceedings, pp. 347-348.

Proteus : A runtime reconfigurable distributed shared memory system. / Ueng, Jyh Chang; Shieh, Ce-Kuen; Liu, Wu Hwa; Lin, Chi Chang.

In: IEEE International Symposium on High Performance Distributed Computing, Proceedings, 1999, p. 347-348.

Research output: Contribution to journal › Article

TY - JOUR

T1 - Proteus

T2 - A runtime reconfigurable distributed shared memory system

AU - Ueng, Jyh Chang

AU - Shieh, Ce-Kuen

AU - Liu, Wu Hwa

AU - Lin, Chi Chang

PY - 1999

Y1 - 1999

N2 - This paper describes a Distributed Shared Memory (DSM) system called Proteus, which aims to support runtime node reconfiguration. To make the system execute efficiently after node reconfiguration and reduce the overhead of reconfiguration, Proteus employs an adaptive workload redistribution strategy to perform workload redistribution as well as an affinity page movement strategy to redistribute memory pages. Furthermore, a forced update technique and a set of scalable synchronization mechanisms are developed to keep memory consistent and to perform a correct synchronization, respectively.

AB - This paper describes a Distributed Shared Memory (DSM) system called Proteus, which aims to support runtime node reconfiguration. To make the system execute efficiently after node reconfiguration and reduce the overhead of reconfiguration, Proteus employs an adaptive workload redistribution strategy to perform workload redistribution as well as an affinity page movement strategy to redistribute memory pages. Furthermore, a forced update technique and a set of scalable synchronization mechanisms are developed to keep memory consistent and to perform a correct synchronization, respectively.

UR - http://www.scopus.com/inward/record.url?scp=0033362522&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033362522&partnerID=8YFLogxK

M3 - Article

SP - 347

EP - 348

JO - IEEE International Symposium on High Performance Distributed Computing, Proceedings

JF - IEEE International Symposium on High Performance Distributed Computing, Proceedings

SN - 1082-8907

ER -

Ueng JC, Shieh C-K, Liu WH, Lin CC. Proteus: A runtime reconfigurable distributed shared memory system. IEEE International Symposium on High Performance Distributed Computing, Proceedings. 1999;347-348.

Access to Document