A compacting non-contiguous processor allocation strategy for 2d mesh-connected multicomputers

Other Title(s)

التخصيص غير المتجاور باستخدام التحشير في متعددات الحواسيب ثنائية الأبعاد

Dissertant

Yasin, Muhammad Husayn Muhammad

Thesis advisor

Ababinah, Ismail M.
Bani Muhammad, Sad

Comitee Members

Shatnawi, Umar Ali
Battayihah, Khalid
Qatawinah, Umar

University

Al albayt University

Faculty

Prince Hussein Bin Abdullah Faculty for Information Technology

Department

Department of Computer Science

University Country

Jordan

Degree

Master

Degree Date

2012

English Abstract

In non-contiguous allocation, a job request can be split into smaller parts that are allocated possibly non-adjacent free sub-meshes rather than always waiting until a single sub-mesh of the requested size and shape is available.

Lifting the contiguity condition is expected to reduce processor fragmentation and increase system utilization.

However, the distances traversed by messages can be long, and as a result the communication overhead, especially contention, is increased.

The extra communication overhead depends on how the allocation request is partitioned and assigned to free sub-meshes.

In this research, a new non-contiguous processor allocation strategy, referred to as A Compacting Non-Contiguous Processor Allocation Strategy (CNCPA), is suggested for the 2D mesh networks.

In the proposed strategy, a single job is compacting into more than one free location within the allocated processors, where the remaining available processors (free processors) form a large sub-mesh in the system.

To evaluate the performance improvement achieved by the proposed strategy and compare it against well-known existing noncontiguous strategies, we conducted extensive simulation experiments under the assumption of wormhole routing and the communication patterns, one-to-all, random and near neighbor.

The results show that the proposed strategy eliminates both the internal and external fragmentation and reduce the communication overhead and hence improves performance in terms of job turnaround time and system utilization.

Main Subjects

Information Technology and Computer Science

No. of Pages

55

Table of Contents

Table of contents.

Abstract.

Chapter One : introduction.

Chapter Two : related work.

Chapter Three : a compacting non-contiguous processor allocation.

Chapter Four : performance evaluation.

Chapter Five : conclusion and future works.

References.

American Psychological Association (APA)

Yasin, Muhammad Husayn Muhammad. (2012). A compacting non-contiguous processor allocation strategy for 2d mesh-connected multicomputers. (Master's theses Theses and Dissertations Master). Al albayt University, Jordan
https://search.emarefa.net/detail/BIM-321638

Modern Language Association (MLA)

Yasin, Muhammad Husayn Muhammad. A compacting non-contiguous processor allocation strategy for 2d mesh-connected multicomputers. (Master's theses Theses and Dissertations Master). Al albayt University. (2012).
https://search.emarefa.net/detail/BIM-321638

American Medical Association (AMA)

Yasin, Muhammad Husayn Muhammad. (2012). A compacting non-contiguous processor allocation strategy for 2d mesh-connected multicomputers. (Master's theses Theses and Dissertations Master). Al albayt University, Jordan
https://search.emarefa.net/detail/BIM-321638

Language

English

Data Type

Arab Theses

Record ID

BIM-321638