What have we learnt from using real parallel machines to solve real problems?
C3P Proceedings of the third conference on Hypercube concurrent computers and applications - Volume 2
High Performance Cluster Computing: Programming and Applications
High Performance Cluster Computing: Programming and Applications
High-level Parallelism in a Database Cluster: A Feasibility Study Using Document Services
Proceedings of the 17th International Conference on Data Engineering
The Berkeley Networks of Workstations (NOW) Project
COMPCON '95 Proceedings of the 40th IEEE Computer Society International Conference
The Grid 2: Blueprint for a New Computing Infrastructure
The Grid 2: Blueprint for a New Computing Infrastructure
Hi-index | 0.00 |
In order to provide computer facilities for almost 20,000 students plus a thousand of faculty, university have to spend a lot of budget. The time has changed, the technology has changed either. Most of computer utilize only 5-20% of peak time, so they are almost idle. So the previous system might not have enough capacity to support the use of end-user in term of number of users and number of applications used. The new budget must be provided for the new system. Instead of spend more budget, more advance techniques such as clustering, load balancing and grid technology has been raised to improve the system performance by using current system. Our team has researched and tried to implement these techniques deployed into current system With more than 3,000 PC computers, we would have a supercomputer as powerful as 3TFlopps in performance. We have developed and implemented a small model of grid system. The process is on the progress. We would like our case to show the advantages aspect to others especially in Thailand.