A Multi-Application Controller for a Tiled Display Wall for Wide-Area Distributed Computing

Recently, both networking and high-performance computing technologies have dramatically advanced. As a result, scientists can access large-scale data captured by scientific measurement devices with ease. Also, recent high-performance computing technologies such as the Grid and cloud computing have allowed scientists to use huge computational power harnessed on the Internet for their analysis of scientific data. However, visualization technology, which plays the role of great importance for scientists intuitively in understanding the analysis results of such scientific data, is not fully utilized so that it can benefit from recent high-performance and networking technologies although many sophisticated visualization technologies exists nowadays. One of such visualization technologies is SAGE (Scalable Adaptive Graphics Environment), which allows people to build an arbitrary size of a tiled display wall and is expected to be applied to scientific research. In this paper, we describe a multi-application controller for SAGE middleware, which we have developed, in the hope that it will help scientists perform their analysis on a wide- area distributed computing environment. The evaluation in the paper indicates the efficiency of completing a comparison task among multiple data is raised by our system.