Bridging the Gap Between Cluster and Grid Computing

The Internet computing model with its ubiquitous networking and computing infrastructure is driving a new class of interoperable applications that benefit both from high computing power and multiple Internet connections. In this context, grids are promising computing platforms that allow to aggregate distributed resources such as workstations and clusters to solve large-scale problems. However, because most parallel programming tools were primarily developed for MPP and cluster computing, to exploit the new environment higher abstraction and cooperative interfaces are required. Rocmeμ is a platform originally designed to support the operation of multi-SAN clusters that integrates application modeling and resource allocation. In this paper we show how the underlying resource oriented computation model provides the necessary abstractions to accommodate the migration from cluster to multicluster grid enabled computing.