Articles

Found 4 Documents
Search

PARALLEL MATRIX-MULTIPLICATION ALGORITHM ON NETWORK OF WORKSTATIONS Aminuddin, Rusdi Md.; Abdullah, Rosni; Hassan, Suhaidi
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 4, No 2 (2004)
Publisher : Program Studi Statistika Unisba

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29313/jstat.v4i2.897

Abstract

Matrix multiplication is one of the important operations in scientific and engineering application. However, it is also one ofthe operations that are time consuming. Continuous researches have been conducted to improve this operation. One of thealternatives is to have the operation performed in parallel. However, these types of algorithms often carried out onexpensive supercomputers or multiprocessing systems. With the advancement of personal computers and networking, theuse of network of computers has become an advantage to the computing community. Although programming in suchenvironment is relatively harder compared to that of in shared memory multiprocessing environment, its advantagesoutweigh its complexity. In this paper, we introduce the concept of Network of Computers (NOW) or Cluster computingand present its advantages. We discuss matrix-multiplication algorithm and highlight one of the parallel matrixmultiplicationalgorithms. We present the comparison in terms of speed between serial algorithm and the parallel algorithmwhen we run them on our cluster. We end our discussion by outlining our future works.
EARLIER STAGE FOR STRAGGLER DETECTION AND HANDLING USING COMBINED CPU TEST AND LATE METHODOLOGY Katrawi, Anwar H.; Abdullah, Rosni; Anbar, Mohammed; Abasi, Ammar Kamal
International Journal of Electrical and Computer Engineering (IJECE) Vol 10, No 5: October 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v10i5.pp4910-4917

Abstract

Using MapReduce in Hadoop helps in lowering the execution time and power consumption for large scale data. However, there can be a delay in job processing in circumstances where tasks are assigned to bad or congested machines called "straggler tasks"; which increases the time, power consumptions and therefore increasing the costs and leading to a poor performance of computing systems. This research proposes a hybrid MapReduce framework referred to as the combinatory late-machine (CLM) framework. Implementation of this framework will facilitate early and timely detection and identification of stragglers thereby facilitating prompt appropriate and effective actions.
Mathematics Curriculum Review by Advancing the Use of Learning Design Map and Subjects Classification Fathurrohman, Maman; Porter, Anne; Worthy, Annette; Abdullah, Rosni; Supriyanto, Supriyanto; Pamungkas, Aan Subhan
International Journal on Emerging Mathematics Education IJEME, Vol. 3 No. 1, March 2019
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1053.708 KB) | DOI: 10.12928/ijeme.v3i1.11929

Abstract

Curriculum review is a long process. Typically, the people responsible for these activities are one or two people (coordinators) who are responsible for this and it can be burdensome. Authors propose a new computer-based method for mathematics curriculum review by advancing the use of Learning Designs Maps (LDMaps). The LDMaps have already been developed by authors to document expected mathematics teaching and learning experiences as expected by curriculum. The proposed method can disperse the process allowing the responsible coordinators to conduct the simple task of collating available LDMaps for the review. In this paper, an example of mathematics curriculum review in counting mathematics subjects classification entries is presented.
STRAGGLER HANDLING APPROACHES IN MAPREDUCE FRAMEWORK: A COMPARATIVE STUDY Katrawi, Anwar H.; Abdullah, Rosni; Anbar, Mohammed; AlShourbaji, Ibrahim; Abasi, Ammar Kamal
International Journal of Electrical and Computer Engineering (IJECE) Vol 11, No 1: February 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v11i1.pp%p

Abstract

The proliferation of information technology produces a huge amount of data called big data that cannot be processed by traditional database systems. These Various types of data come from different sources. However, stragglers are a major bottleneck in big data processing, and hence the early detection and accurate identification of stragglers can have important impacts on the performance of big data processing. This work aims to assess five stragglers identification methods: Hadoop native scheduler, LATE Scheduler, Mantri, MonTool, and Dolly. The performance of these techniques was evaluated based on three benchmarked methods: Sort, Grep and WordCount. The results show that the LATE Scheduler performs the best and it would be efficient to obtain better results for stragglers identification.