Properties and Performance of Cube-Based Multiprocessor Architectures

Properties and Performance of Cube-Based Multiprocessor Architectures

Abdus Samad (University Women's Polytechnic, Aligarh Muslim University, Aligarh, India), Jamshed Siddiqui (Department of Computer Science, Aligarh Muslim University, Aligarh, India) and Zaki Ahmed Khan (Department of Computer Science, Aligarh Muslim University, Aligarh, India)
Copyright: © 2016 |Pages: 16
DOI: 10.4018/IJAEC.2016010105
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Parallel architectures provide the possibility of solving highly computational parallel applications in a variety of ways. Numerous interconnection topologies have been designed to achieve the desired performance. Nevertheless, the actual performance is far below the expectation of users when executing parallel applications on a particular multiprocessor network. This paper presents the performance study on a special class of parallel architectures known as cube based multiprocessor architectures. It describes the issues and challenges related to the design of cube-based architectures. The issues related to the design of highly parallel system such as scalability, complexity of the system and mapping of parallel application on to it are discussed. Furthermore, the problem of routing between nodes has been analyzed along with the topological properties of cube-based architectures. Simulation results are obtained by applying task scheduling algorithm on various multiprocessor networks. The comparative study implies the various aspects while designing an efficient multiprocessor interconnection network with optimal scheduling algorithm.
Article Preview

1. Introduction

Parallel computing have been widely studied in the field of computer science and has proven to be critical when researching high performance solutions. Modern computer systems employ multiple processors which may take part in execution in parallel to enhance the performance of an application. The benefits of parallel computing need to take into consideration the number of processors being deployed, the complexity of the system as well as the communication incurred between various processing units known as nodes. The topology of interconnection networks plays a key role in the performance of parallel computing systems. Significant progress has been made in the past decades in the design and development of efficient interconnection networks (Chhabra et al., 2009; Parhami, 2000; Kim et al., 1999; Cheng et al., 1994; Shi et al., 2005; Zhang, 2002). Hypercube architecture is a promising approach to improve the performance of multiprocessor parallel systems. Numerous variants of hypercube have been reported in the literature (Amway et al., 1991; Kumar et al., 1992; Efe, 1991; Loh et al., 2005; Khan et al., 2013). These variants include many attractive properties, including regularity, symmetry, small diameter, high connectivity and scalability. A number of approaches have been suggested and implemented to improve the overall performance of such systems (Efe, 1992; Ghose et al., 1995; Kumar, 2012). Nevertheless, no single topology claims to have all the desirable topological features. For example the Crossed Cube architecture denoted by CC is derived from the hypercube to have a smaller diameter which is almost half of its parent architecture (Efe, 1992). However, the CC makes no significant improvement in the hardware cost compared to the hypercube. Similarly, a new architecture known as Folded Crossed Hypercube (FCH) (Khan et al., 2013) network is designed by augmenting the CC network. Some extra links called complementary links are introduced which help to reduce the diameter further. The improved diameter is obtained however at a greater value of degree. The Exchange Hypercube (EH) is another example which is also derived from hypercube and has lesser hardware cost by reducing number of links in the hypercube (Loh et al., 2005). This, however, results no improvement in the diameter and the connectivity in the EH is decreased. Similarly, there are other numerous interconnection networks which are designed by improving a particular topological parameter. Some examples are the Folded Hypercube (FH) (Amway et al., 1991), Dual Cube (DC) (Li et al., 2000), Folded Dual Cube (FDC) (Adhikari et al., 2008), Meta Cube (MC) (Li et al., 2002), Folded Met cube (FMC) (Adhikari et al., 2009), and the Folded Cross Cube (FCC) (Adhikari et al., 2010).

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 8: 4 Issues (2017): 3 Released, 1 Forthcoming
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing