Big Data, Small Languages, Scalable Systems
3.0
creditsAverage Course Rating
This class will study domain-specific data management tools, focusing on extremely scalable system design based on the domain's semantic and structural properties. We will study a variety of data models including stream, graph, array and probabilistic data, and their processing on modern architectures such as column- and key-value stores, stream and XQuery engines. Further topics include the use of novel hardware such as solid state disks, phase change memory, GPUs, and FPGAs. The class includes a semester long group project to develop a query processor for an application of the group's choice (e.g. on system log, finance, web, sensor, speech data). Recommended Course Background: EN.600.315/EN.600.415 or equivalent.