Introduction: Enabling Large-Scale Computational Science—Motivations, Requirements, and Challenges

The exponential growth in computing, networking, and storage technologies has ushered in unprecedented opportunities for parallel and distributed computing research and applications. In the meantime, emerging large-scale adaptive scientific and engineering applications are requiring an increasing amount of computing and storage resources to provide new insights into complex systems. Furthermore, dynamically adaptive techniques are being widely used to address the intrinsic heterogeneity and high dynamism of the phenomena modeled by these applications. Adaptive techniques have been applied to real-world applications in a variety of scientific and engineering disciplines, including computational fluid dynamics, subsurface and oil reservoir simulations, astronomy, relativity, and weather modeling. The increasing complexity, dynamism, and heterogeneity of these applications, coupled with similarly complex and heterogeneous parallel and distributed computing systems, have led to the development and deployment of advanced computational infrastructures that provide programming, execution, and runtime management support for such large-scale adaptive implementations. The objective of this book is to investigate the