Developing an efficient approach to support portability in grid environment /
There has been a growing interest in GRID computing, a technique that enables computers and resources to communicate and work collaboratively to solve complex problems. GRID computing provides many features one of which is resource sharing. Major advances are being made in the various sub domains of...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
Gombak, Selangor :
Kulliyyah of Engineering, International Islamic University Malaysia,
2010
|
| Subjects: | |
| Online Access: | Click here to view 1st 24 pages of the thesis. Members can view fulltext at the specified PCs in the library. |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | There has been a growing interest in GRID computing, a technique that enables computers and resources to communicate and work collaboratively to solve complex problems. GRID computing provides many features one of which is resource sharing. Major advances are being made in the various sub domains of GRID computing. However, current applications are developed without GRID in mind. A need arises to develop applications that will enable the end users to run their tasks without configurations. The different current approaches were studied and an understanding was developed. A thorough literature review of related works gave an understanding of the anatomy of GRID computing. The main aim of this research is to come out with an efficient strategy to develop portable applications for the GRID environment. This is achieved by extending the current parallel programming approach to support portable applications that suit the GID environment. The change has been incorporated to the agglomeration stage, which is the code development stage. This improvement enables the developed application to run in the heterogeneous GRID environment. An application (Simple Notepad) based on this design strategy was developed using JAVA programming and was tested in the GRID environment at IIUM GRID. It was benchmarked with an application (Greenstone) which was developed based on the binary distribution portability approach. The portable application was run on IIUM GRID and its performance was recorded. The performance metric used was CPU time. CPU time/ Execution time is the amount of time that a computer program uses in processing Central Processing Unit (CPU) instructions. The tools used to measure the CPU time are Task Manager in Windows XP and the “top” command in Linux. The performance of Simple Notepad is 1.2 times better than Greenstone when run on Windows XP and the performance of Simple Notepad is 1.4 times better than Greenstone when run on CentOS 5. |
|---|---|
| Item Description: | “A dissertation submitted in partial fulfilment of the requirements for the degree of Master of Science (Computer science and Information Engineering).”--On t.p. Abstract in English. |
| Physical Description: | xii, 117 leaves: ill. 30cm |
| Bibliography: | Includes bibliographical references (leaves 91-93) |