Computing angular correlation function using message passing interface.

Fareed Ahmed  Jokhio; Umair Ali  Khan; Intesab Hussain  Sadhayo

Author(s)

Fareed Ahmed Jokhio Department of Computer Systems Engineering, Quaid-e-Awam University of Engineering, Science & Technology, Nawabshah Pakistan

Umair Ali Khan Department of Computer Systems Engineering, Quaid-e-Awam University of Engineering, Science & Technology, Nawabshah, Pakistan

Intesab Hussain Sadhayo Department of Computer Systems Engineering, Quaid-e-Awam University of Engineering, Science & Technology, Nawabshah, Pakistan;Department of Information Technologies, Åbo Akademi University, Finland

Abstract

There are many fields of science where the Two- Point Angular Correlation Function (TPACF) is used, such as in statistics, and astronomy. In cosmology, it is used to calculate the distribution of galaxies. The number of galaxies in the Universe is more than 170 billion in a limited region of 13.8 billion light years distance. To compute the distribution of such a large number of galaxies requires huge computational resources. This paper adopts a parallel processing approach to compute angular correlation function. The distribution of galaxies using the TPACF is computed by using a message passing programming model in a cluster based parallel processing environment. To get a better speedup, we adopt a coarse grain approach in which the computation is split among different processes. Each process gets a fixed number of data lines and performs the required computation. The results indicate that the parallel processing of the TPACF provides a significant speedup in terms of execution time.

Publication Details

Page(s) 38-45

DOI DOI not available

Published Journal: Quaid-e-Awam University Research Journal of Engineering, Science and Technology, Volume: 14, Issue: 1, Year: 2015

Request the full text from PASTIC