Virtual Infrastructures for Computational Science

P-O Östberg
Division of Scientific Computing
Department of Information Technology
Uppsala University and
Department of Computer Science
Umeå University


In computational science, the scale of problems addressed and the resolution of solutions achieved are often limited by the available computational capacity. The current methodology of scaling computational capacity to large scale (i.e. larger than individual resource site capacity) includes aggregation and federation of distributed resource systems. Regardless of how this aggregation manifests, scaling of scientific computational problems typically involves (re)formulation of computational structures and problems to exploit problem and resource parallelism. Efficient parallelization and scaling of scientific computations to large scale is difficult and further complicated by a number of factors introduced by resource aggregation, e.g., resource heterogeneity and coupling of computational methodology. In summary, scaling complexity severely impacts the complexity of computation enactment and necessitates the use of mechanisms that provide higher abstraction levels for management of computations in distributed computing environments.

In this talk I will present some of my dissertation work related to the definition and construction of virtual infrastructures for computational science. Topics addressed include brief introductions to the concepts of virtual infrastructures, Grid and Cloud computing methodology, as well as service-based software construction for virtual infrastructures. The talk will also include some information about current and planned collaboration efforts in Uppsala and within the national eScience project eSSENCE.