With the push to exascale, in situ visualization and analysis will continue to play an important role in high performance computing. Tightly coupling in situ visualization with simulations constrains resources for both, and these constraints force a complex balance of trade-offs. A performance model that provides an a priori answer for the cost of using an in situ approach for a given task would assist in managing the trade-offs between simulation and visualization resources. In this work, we present new statistical performance models, based on algorithmic complexity, that accurately predict the run-time cost of a set of representative rendering algorithms, an essential in situ visualization task. To train and validate the models, we conduct a performance study of an MPI+X rendering infrastructure used in situ with three HPC simulation applications. We then explore feasibility issues using the model for selected in situ rendering questions.

Rapid advancements in processor and networking technologies have led to the evolution of cluster and grid computing frameworks. These high-performance computing environments exploit geographically distributed, diverse resources with the goal of providing efficient computing solutions to all kinds of parallel and distributed applications. OCEAN (Open Computation Exchange and Arbitration Network) provides a scalable market-based infrastructure to such meta-computing frameworks. OCEAN aims to build a marketplace where resources like CPU time, associated memory usage and network bandwidth are the traded commodities. This paper explains the technical challenges faced in the design of OCEAN and discusses our proposed solution. To facilitate finding suitable resources for buyers, we developed efficient matching and evolution protocols for the peer-to-peer matching network. The architecture and various components of OCEAN are described in detail. We implemented OCEAN on Java and .NET platforms and describe results from our preliminary experiments.