Provided by: Texas State Technical College
Topic: Big Data
Date Added: Sep 2012
High-speed and cost-effective architecture design has become a great challenge for future data-intensive scalable High Performance Computing (HPC) systems. In this paper, the authors discuss the significant architecture design challenges of a large scale satellite images processing and distribution system maintained by the U.S. Geological Survey (USGS) Earth Resources Observation and Science Center (EROS). Specifically, they conduct a real-world case study on how can changing workload greatly affect existing system architecture; how does EROS's new system architecture adapt to the significant workload changes; and how to further optimize the performance of the current EROS system.