Bandwidth Availability of Multiple-Bus Multiprocessors

Chitaranjan Das, Laxmi N. Bhuyan

Research output: Contribution to journalArticle

62 Citations (Scopus)

Abstract

Multiprocessor systems should be designed considering both performance and reliability issues. They should support graceful degradation by isolating the failed components and by reconfiguring to a new state with decreased performance. We present in this paper the effect of failures on the performance of multiple-bus multiprocessors. Bandwidth expressions for this architecture are derived for uniform and nonuniform memory references. Mathematical models are developed to compute the reliability and the performance related bandwidth availability (BA). The results obtained for the multiple-bus interconnection are compared with those of a crossbar. The models are also extended to analyze the partial bus structure where the memories are divided into groups and each group is connected to a subset of buses. The reliability and the BA of the multiple-bus and partial-buses architectures are compared.

Original languageEnglish (US)
Pages (from-to)918-926
Number of pages9
JournalIEEE Transactions on Computers
VolumeC-34
Issue number10
DOIs
StatePublished - Jan 1 1985

Fingerprint

Multiprocessor
Availability
Bandwidth
Partial
Multiprocessor Systems
Interconnection
Data storage equipment
Degradation
Mathematical Model
Subset
Mathematical models
Architecture
Model

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Hardware and Architecture
  • Computational Theory and Mathematics

Cite this

Das, Chitaranjan ; Bhuyan, Laxmi N. / Bandwidth Availability of Multiple-Bus Multiprocessors. In: IEEE Transactions on Computers. 1985 ; Vol. C-34, No. 10. pp. 918-926.
@article{83df1f52262c45bf9f26c137f816d40e,
title = "Bandwidth Availability of Multiple-Bus Multiprocessors",
abstract = "Multiprocessor systems should be designed considering both performance and reliability issues. They should support graceful degradation by isolating the failed components and by reconfiguring to a new state with decreased performance. We present in this paper the effect of failures on the performance of multiple-bus multiprocessors. Bandwidth expressions for this architecture are derived for uniform and nonuniform memory references. Mathematical models are developed to compute the reliability and the performance related bandwidth availability (BA). The results obtained for the multiple-bus interconnection are compared with those of a crossbar. The models are also extended to analyze the partial bus structure where the memories are divided into groups and each group is connected to a subset of buses. The reliability and the BA of the multiple-bus and partial-buses architectures are compared.",
author = "Chitaranjan Das and Bhuyan, {Laxmi N.}",
year = "1985",
month = "1",
day = "1",
doi = "10.1109/TC.1985.6312195",
language = "English (US)",
volume = "C-34",
pages = "918--926",
journal = "IEEE Transactions on Computers",
issn = "0018-9340",
publisher = "IEEE Computer Society",
number = "10",

}

Bandwidth Availability of Multiple-Bus Multiprocessors. / Das, Chitaranjan; Bhuyan, Laxmi N.

In: IEEE Transactions on Computers, Vol. C-34, No. 10, 01.01.1985, p. 918-926.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Bandwidth Availability of Multiple-Bus Multiprocessors

AU - Das, Chitaranjan

AU - Bhuyan, Laxmi N.

PY - 1985/1/1

Y1 - 1985/1/1

N2 - Multiprocessor systems should be designed considering both performance and reliability issues. They should support graceful degradation by isolating the failed components and by reconfiguring to a new state with decreased performance. We present in this paper the effect of failures on the performance of multiple-bus multiprocessors. Bandwidth expressions for this architecture are derived for uniform and nonuniform memory references. Mathematical models are developed to compute the reliability and the performance related bandwidth availability (BA). The results obtained for the multiple-bus interconnection are compared with those of a crossbar. The models are also extended to analyze the partial bus structure where the memories are divided into groups and each group is connected to a subset of buses. The reliability and the BA of the multiple-bus and partial-buses architectures are compared.

AB - Multiprocessor systems should be designed considering both performance and reliability issues. They should support graceful degradation by isolating the failed components and by reconfiguring to a new state with decreased performance. We present in this paper the effect of failures on the performance of multiple-bus multiprocessors. Bandwidth expressions for this architecture are derived for uniform and nonuniform memory references. Mathematical models are developed to compute the reliability and the performance related bandwidth availability (BA). The results obtained for the multiple-bus interconnection are compared with those of a crossbar. The models are also extended to analyze the partial bus structure where the memories are divided into groups and each group is connected to a subset of buses. The reliability and the BA of the multiple-bus and partial-buses architectures are compared.

UR - http://www.scopus.com/inward/record.url?scp=0022143080&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0022143080&partnerID=8YFLogxK

U2 - 10.1109/TC.1985.6312195

DO - 10.1109/TC.1985.6312195

M3 - Article

AN - SCOPUS:0022143080

VL - C-34

SP - 918

EP - 926

JO - IEEE Transactions on Computers

JF - IEEE Transactions on Computers

SN - 0018-9340

IS - 10

ER -