Download now Free registration required
A compute grid is essentially a collection of distributed computing resources, aggregated to act as a unified processing resource or virtual supercomputer. Collecting these compute resources into a unified pool involves not only coordinated usage policies, job scheduling and queuing characteristics but also grid-wide security and user authentication. The first phase of grid computing evolution tends to be the creation of intra-grids; two or three clusters may be interconnected between departments within an enterprise to increase processing capacity and share data sets. Because the clusters are within one enterprise domain, things like security and authentication, although still important, are not so critical.
- Format: PDF
- Size: 95.7 KB