Development of real-time OLAP algorithm using multicore distributed processing /
Online analytical processing (OLAP) is becoming increasingly essential technique, particularly for decision support systems (DSS). OLAP is considered a suitable technology for online analysis, in comparison to its counterpart: Online transaction processing (OLTP), due to the fact that OLAP offers in...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
Kuala Lumpur :
Kulliyyah of Engineering, International Islamic University Malaysia,
2014
|
| 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: | Online analytical processing (OLAP) is becoming increasingly essential technique, particularly for decision support systems (DSS). OLAP is considered a suitable technology for online analysis, in comparison to its counterpart: Online transaction processing (OLTP), due to the fact that OLAP offers instantaneous answers to the immediate queries that decision makers urgently need to make their decisions at some critical moments based on the latest updates of the warehouse. However, despite its speed processing capabilities; OLAP does not satisfy stringent Real-Time applications' requirements. Rather, current OLAP approaches the Real-Time. In other words OLAP can achieve partial Real-Time results and the reset is materialized. Our study addresses this shortcoming and attempts to propose a novel solution taking advantage of revolutionary hardware development on two levels; namely, the multi-core processors as well as distributed heterogeneous systems processing. This new approach exploits the hardware resources optimally, and as a result; significantly increases the processing speed. Our results have shown gain from 350% to 1200% in terms of response time compared to our benchmark in which multi-core CPU only has been utilized. In addition, the results have shown a propositionally increased gain with increasing size of data due to the fact that the Graphical Processing Unit (GPU) becomes more dominant component in the searching process as the data size increases. We argue that with the new results, the heterogeneous solution is a very strong candidate to our Real-Time OLAP problem |
|---|---|
| Physical Description: | xiv, 112 leaves : ill. 30cm. |
| Bibliography: | Includes bibliographical references (leaves 93-100) |